Token | worst |
Token ID | 5290 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
anonymously | +1.330 |
orr | +1.278 |
oux | +1.233 |
disse | +1.200 |
church | +1.199 |
Neg logit contributions | |
advertising | -1.272 |
Dresden | -1.183 |
��� | -1.176 |
education | -1.147 |
defense | -1.145 |
Token | year |
Token ID | 614 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
advertising | +4.228 |
ary | +4.101 |
Dresden | +4.093 |
education | +3.849 |
defense | +3.813 |
Neg logit contributions | |
anonymously | -4.838 |
oux | -4.714 |
orr | -4.681 |
church | -4.435 |
disse | -4.418 |
Token | for |
Token ID | 329 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
advertising | +3.705 |
ary | +3.540 |
Dresden | +3.514 |
education | +3.330 |
defense | +3.296 |
Neg logit contributions | |
anonymously | -4.005 |
orr | -3.922 |
oux | -3.879 |
disse | -3.741 |
church | -3.687 |
Token | jobs |
Token ID | 3946 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
advertising | +3.217 |
Dresden | +3.084 |
ary | +2.993 |
education | +2.933 |
defense | +2.863 |
Neg logit contributions | |
anonymously | -3.598 |
orr | -3.555 |
oux | -3.483 |
disse | -3.337 |
church | -3.302 |
Token | in |
Token ID | 287 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
advertising | +3.096 |
Dresden | +2.894 |
ary | +2.866 |
education | +2.765 |
defense | +2.702 |
Neg logit contributions | |
anonymously | -3.725 |
orr | -3.671 |
oux | -3.550 |
disse | -3.454 |
church | -3.452 |
Token | almost |
Token ID | 2048 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Dresden | +6.133 |
advertising | +6.100 |
ary | +5.841 |
education | +5.635 |
defense | +5.371 |
Neg logit contributions | |
anonymously | -9.098 |
orr | -9.029 |
oux | -8.865 |
disse | -8.557 |
church | -8.444 |
Token | two |
Token ID | 734 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Dresden | +9.044 |
advertising | +8.274 |
ary | +8.089 |
education | +7.540 |
Morales | +7.216 |
Neg logit contributions | |
orr | -15.060 |
oux | -14.804 |
ococ | -14.524 |
anonymously | -14.290 |
disse | -14.133 |
Token | decades |
Token ID | 4647 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
advertising | +7.019 |
Dresden | +6.880 |
ary | +6.799 |
education | +6.159 |
Morales | +5.741 |
Neg logit contributions | |
orr | -12.742 |
anonymously | -12.618 |
oux | -12.612 |
kef | -12.039 |
church | -12.030 |
Token | . |
Token ID | 13 |
Feature activation | +5.22e-04 |
Pos logit contributions | |
advertising | +2.080 |
Dresden | +1.941 |
ary | +1.900 |
education | +1.863 |
defense | +1.848 |
Neg logit contributions | |
anonymously | -2.292 |
orr | -2.229 |
oux | -2.168 |
disse | -2.112 |
church | -2.097 |
Token | " |
Token ID | 366 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
advertising | +0.004 |
Dresden | +0.003 |
��� | +0.003 |
education | +0.003 |
defense | +0.003 |
Neg logit contributions | |
anonymously | -0.004 |
orr | -0.003 |
oux | -0.003 |
disse | -0.003 |
church | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
advertising | +0.042 |
Dresden | +0.038 |
��� | +0.037 |
education | +0.037 |
defense | +0.037 |
Neg logit contributions | |
anonymously | -0.045 |
orr | -0.043 |
oux | -0.042 |
disse | -0.041 |
church | -0.041 |
Token | Irvine |
Token ID | 37277 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
advertising | +1.069 |
Dresden | +0.972 |
ary | +0.911 |
��� | +0.910 |
education | +0.906 |
Neg logit contributions | |
anonymously | -2.151 |
orr | -2.103 |
oux | -2.043 |
disse | -2.010 |
church | -1.997 |
Token | , |
Token ID | 11 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
anonymously | +0.486 |
orr | +0.463 |
oux | +0.443 |
disse | +0.427 |
church | +0.427 |
Neg logit contributions | |
advertising | -0.689 |
Dresden | -0.649 |
��� | -0.646 |
education | -0.633 |
defense | -0.631 |
Token | California |
Token ID | 3442 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
advertising | +1.312 |
Dresden | +1.173 |
education | +1.133 |
��� | +1.130 |
defense | +1.121 |
Neg logit contributions | |
anonymously | -2.704 |
orr | -2.668 |
oux | -2.584 |
disse | -2.551 |
church | -2.548 |
Token | . |
Token ID | 13 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
anonymously | +0.980 |
orr | +0.929 |
oux | +0.900 |
church | +0.869 |
disse | +0.853 |
Neg logit contributions | |
advertising | -1.170 |
��� | -1.113 |
Dresden | -1.107 |
education | -1.071 |
defense | -1.068 |
Token | Hide |
Token ID | 10415 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
advertising | +1.785 |
Dresden | +1.669 |
��� | +1.606 |
ary | +1.605 |
education | +1.599 |
Neg logit contributions | |
anonymously | -1.796 |
orr | -1.730 |
oux | -1.657 |
disse | -1.650 |
church | -1.618 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
advertising | +5.493 |
Dresden | +5.209 |
ary | +5.153 |
education | +4.847 |
Morales | +4.721 |
Neg logit contributions | |
anonymously | -6.157 |
disse | -6.099 |
orr | -5.886 |
oux | -5.684 |
church | -5.609 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
advertising | +5.980 |
Dresden | +5.245 |
ary | +5.239 |
Morales | +4.828 |
Helpful | +4.444 |
Neg logit contributions | |
mosqu | -19.699 |
disse | -19.264 |
cryst | -19.120 |
oux | -18.912 |
church | -18.796 |
Token | of |
Token ID | 286 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
anonymously | +1.313 |
orr | +1.262 |
oux | +1.218 |
church | +1.184 |
disse | +1.170 |
Neg logit contributions | |
advertising | -1.234 |
��� | -1.190 |
Dresden | -1.151 |
education | -1.116 |
defense | -1.114 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
advertising | +1.884 |
Dresden | +1.747 |
ary | +1.683 |
education | +1.624 |
defense | +1.616 |
Neg logit contributions | |
anonymously | -3.328 |
orr | -3.245 |
disse | -3.170 |
oux | -3.138 |
church | -3.086 |
Token | Photos |
Token ID | 9434 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
advertising | +0.142 |
Dresden | +0.134 |
ary | +0.130 |
education | +0.130 |
defense | +0.130 |
Neg logit contributions | |
anonymously | -0.091 |
orr | -0.086 |
oux | -0.082 |
disse | -0.081 |
church | -0.079 |
Token | : |
Token ID | 25 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
advertising | +1.756 |
ary | +1.632 |
Dresden | +1.629 |
education | +1.587 |
defense | +1.577 |
Neg logit contributions | |
anonymously | -1.270 |
orr | -1.206 |
disse | -1.186 |
oux | -1.158 |
church | -1.120 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
advertising | +2.012 |
Dresden | +1.924 |
ary | +1.854 |
��� | +1.829 |
education | +1.819 |
Neg logit contributions | |
anonymously | -1.781 |
orr | -1.750 |
oux | -1.682 |
church | -1.639 |
disse | -1.600 |
Token | cerebral |
Token ID | 31169 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
advertising | +1.318 |
Dresden | +1.254 |
��� | +1.211 |
ary | +1.204 |
education | +1.197 |
Neg logit contributions | |
anonymously | -1.275 |
orr | -1.236 |
oux | -1.189 |
church | -1.157 |
disse | -1.143 |
Token | journalist |
Token ID | 10099 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
anonymously | +2.627 |
orr | +2.494 |
oux | +2.402 |
disse | +2.375 |
church | +2.324 |
Neg logit contributions | |
advertising | -3.024 |
��� | -2.840 |
Dresden | -2.783 |
defense | -2.738 |
education | -2.732 |
Token | played |
Token ID | 2826 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
advertising | +2.878 |
Dresden | +2.775 |
ary | +2.693 |
education | +2.648 |
��� | +2.647 |
Neg logit contributions | |
anonymously | -2.541 |
orr | -2.508 |
oux | -2.394 |
church | -2.322 |
disse | -2.285 |
Token | by |
Token ID | 416 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
advertising | +2.511 |
Dresden | +2.376 |
��� | +2.267 |
ary | +2.267 |
education | +2.233 |
Neg logit contributions | |
anonymously | -3.510 |
orr | -3.466 |
oux | -3.327 |
church | -3.278 |
disse | -3.258 |
Token | Diane |
Token ID | 26542 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
advertising | +0.731 |
Dresden | +0.684 |
��� | +0.672 |
education | +0.659 |
ary | +0.657 |
Neg logit contributions | |
anonymously | -0.792 |
orr | -0.764 |
oux | -0.737 |
church | -0.718 |
disse | -0.717 |
Token | Ke |
Token ID | 3873 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Dresden | +9.732 |
advertising | +9.693 |
ary | +9.114 |
Morales | +9.068 |
lance | +8.554 |
Neg logit contributions | |
anonymously | -14.878 |
orr | -14.044 |
disse | -13.670 |
church | -13.494 |
scribe | -13.465 |
Token | aton |
Token ID | 13951 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
advertising | +7.446 |
ary | +6.806 |
education | +6.244 |
peria | +6.153 |
amily | +6.089 |
Neg logit contributions | |
anonymously | -12.395 |
disse | -11.665 |
orr | -10.959 |
church | -10.531 |
kef | -10.522 |
Token | , |
Token ID | 11 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
advertising | +5.261 |
Dresden | +4.954 |
ary | +4.904 |
education | +4.692 |
ebted | +4.677 |
Neg logit contributions | |
anonymously | -5.528 |
orr | -5.337 |
oux | -5.126 |
church | -5.092 |
disse | -5.012 |
Token | who |
Token ID | 508 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
advertising | +2.482 |
Dresden | +2.356 |
ary | +2.275 |
��� | +2.268 |
education | +2.259 |
Neg logit contributions | |
anonymously | -2.244 |
orr | -2.198 |
oux | -2.109 |
church | -2.052 |
disse | -2.030 |
Token | proudly |
Token ID | 23017 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
advertising | +3.348 |
Dresden | +3.149 |
ary | +3.101 |
��� | +3.044 |
education | +3.040 |
Neg logit contributions | |
anonymously | -3.096 |
orr | -3.029 |
oux | -2.932 |
church | -2.892 |
disse | -2.814 |
Token | do |
Token ID | 466 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
advertising | +4.956 |
ary | +4.888 |
Dresden | +4.884 |
education | +4.685 |
defense | +4.545 |
Neg logit contributions | |
orr | -4.960 |
anonymously | -4.902 |
oux | -4.901 |
church | -4.851 |
disse | -4.740 |
Token | everything |
Token ID | 2279 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
advertising | +5.002 |
Dresden | +4.798 |
ary | +4.495 |
education | +4.489 |
��� | +4.312 |
Neg logit contributions | |
anonymously | -8.488 |
orr | -8.400 |
oux | -7.993 |
church | -7.939 |
disse | -7.848 |
Token | we |
Token ID | 356 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
advertising | +6.592 |
Dresden | +6.178 |
ary | +6.094 |
education | +5.696 |
defense | +5.539 |
Neg logit contributions | |
anonymously | -9.670 |
orr | -9.667 |
oux | -9.487 |
church | -9.456 |
disse | -9.347 |
Token | can |
Token ID | 460 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
advertising | +7.324 |
education | +6.769 |
ary | +6.673 |
Dresden | +6.671 |
defense | +6.487 |
Neg logit contributions | |
oux | -9.046 |
orr | -9.042 |
church | -9.039 |
anonymously | -8.796 |
disse | -8.644 |
Token | to |
Token ID | 284 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
advertising | +4.258 |
Dresden | +4.024 |
ary | +3.933 |
education | +3.845 |
defense | +3.735 |
Neg logit contributions | |
anonymously | -5.882 |
orr | -5.881 |
oux | -5.736 |
disse | -5.592 |
church | -5.582 |
Token | find |
Token ID | 1064 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
advertising | +5.768 |
Dresden | +5.637 |
ary | +5.561 |
education | +5.410 |
defense | +5.296 |
Neg logit contributions | |
orr | -6.126 |
oux | -6.040 |
anonymously | -6.006 |
church | -5.989 |
disse | -5.784 |
Token | cool |
Token ID | 3608 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
Dresden | +9.701 |
advertising | +9.537 |
ary | +9.382 |
contestant | +8.833 |
education | +8.722 |
Neg logit contributions | |
oux | -12.683 |
orr | -12.600 |
anonymously | -12.506 |
church | -12.354 |
kef | -12.173 |
Token | things |
Token ID | 1243 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
advertising | +0.258 |
Dresden | +0.242 |
��� | +0.234 |
education | +0.233 |
ary | +0.233 |
Neg logit contributions | |
anonymously | -0.242 |
orr | -0.232 |
oux | -0.225 |
church | -0.218 |
disse | -0.217 |
Token | to |
Token ID | 284 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
advertising | +1.411 |
Dresden | +1.323 |
ary | +1.271 |
��� | +1.260 |
education | +1.258 |
Neg logit contributions | |
anonymously | -1.485 |
orr | -1.455 |
oux | -1.425 |
disse | -1.377 |
church | -1.370 |
Token | take |
Token ID | 1011 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
advertising | +0.667 |
Dresden | +0.631 |
education | +0.611 |
ary | +0.610 |
��� | +0.607 |
Neg logit contributions | |
anonymously | -0.619 |
orr | -0.600 |
oux | -0.587 |
church | -0.574 |
disse | -0.570 |
Token | their |
Token ID | 511 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
anonymously | +3.634 |
orr | +3.454 |
oux | +3.301 |
church | +3.205 |
disse | +3.173 |
Neg logit contributions | |
advertising | -4.076 |
��� | -3.829 |
Dresden | -3.766 |
peria | -3.682 |
education | -3.682 |
Token | constitution |
Token ID | 11784 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
advertising | +3.710 |
Dresden | +3.512 |
ary | +3.455 |
education | +3.447 |
defense | +3.393 |
Neg logit contributions | |
anonymously | -3.945 |
orr | -3.881 |
oux | -3.739 |
disse | -3.566 |
church | -3.555 |
Token | , |
Token ID | 11 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
advertising | +3.375 |
Dresden | +3.187 |
ary | +3.167 |
education | +3.095 |
defense | +3.074 |
Neg logit contributions | |
anonymously | -3.267 |
orr | -3.211 |
oux | -3.088 |
disse | -3.017 |
church | -3.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
anonymously | +2.965 |
orr | +2.798 |
oux | +2.692 |
church | +2.651 |
disse | +2.630 |
Neg logit contributions | |
advertising | -3.232 |
��� | -3.034 |
Dresden | -3.004 |
peria | -2.940 |
defense | -2.900 |
Token | Kim |
Token ID | 6502 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
anonymously | +0.727 |
orr | +0.699 |
oux | +0.675 |
disse | +0.655 |
church | +0.655 |
Neg logit contributions | |
advertising | -0.708 |
Dresden | -0.660 |
��� | -0.654 |
education | -0.640 |
defense | -0.639 |
Token | Jong |
Token ID | 17960 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
advertising | +5.560 |
Dresden | +5.449 |
ary | +5.375 |
��� | +5.240 |
defense | +5.192 |
Neg logit contributions | |
anonymously | -7.350 |
oux | -7.063 |
orr | -7.060 |
disse | -6.854 |
church | -6.798 |
Token | - |
Token ID | 12 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
advertising | +7.506 |
Dresden | +7.275 |
education | +6.899 |
ary | +6.859 |
defense | +6.854 |
Neg logit contributions | |
anonymously | -11.371 |
orr | -11.040 |
oux | -10.861 |
church | -10.681 |
disse | -10.551 |
Token | il |
Token ID | 346 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
advertising | +8.781 |
education | +8.504 |
defense | +8.206 |
ary | +7.765 |
amily | +7.549 |
Neg logit contributions | |
anonymously | -14.332 |
disse | -14.042 |
oux | -13.430 |
orr | -13.398 |
church | -12.912 |
Token | elected |
Token ID | 7018 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
advertising | +2.932 |
Dresden | +2.780 |
ary | +2.757 |
��� | +2.703 |
education | +2.690 |
Neg logit contributions | |
anonymously | -2.793 |
orr | -2.696 |
oux | -2.578 |
disse | -2.560 |
church | -2.533 |
Token | as |
Token ID | 355 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
anonymously | +4.520 |
orr | +4.229 |
oux | +4.075 |
disse | +4.026 |
church | +4.018 |
Neg logit contributions | |
advertising | -3.945 |
��� | -3.654 |
Dresden | -3.524 |
peria | -3.504 |
ebted | -3.460 |
Token | chairman |
Token ID | 8900 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
advertising | +3.780 |
Dresden | +3.695 |
defense | +3.625 |
education | +3.618 |
ary | +3.601 |
Neg logit contributions | |
anonymously | -3.340 |
orr | -3.288 |
oux | -3.166 |
disse | -3.024 |
church | -2.984 |
Token | of |
Token ID | 286 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
advertising | +3.793 |
Dresden | +3.643 |
ary | +3.513 |
defense | +3.495 |
education | +3.486 |
Neg logit contributions | |
anonymously | -4.423 |
orr | -4.320 |
oux | -4.182 |
disse | -4.060 |
church | -4.027 |
Token | � |
Token ID | 251 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
anonymously | +2.116 |
orr | +2.048 |
oux | +1.971 |
church | +1.932 |
disse | +1.911 |
Neg logit contributions | |
advertising | -1.671 |
Dresden | -1.546 |
��� | -1.533 |
peria | -1.501 |
defense | -1.493 |
Token | and |
Token ID | 290 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
anonymously | +1.377 |
orr | +1.319 |
oux | +1.270 |
church | +1.234 |
disse | +1.230 |
Neg logit contributions | |
advertising | -1.448 |
��� | -1.355 |
Dresden | -1.352 |
defense | -1.308 |
peria | -1.306 |
Token | not |
Token ID | 407 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
anonymously | +1.217 |
orr | +1.161 |
oux | +1.117 |
disse | +1.088 |
church | +1.084 |
Neg logit contributions | |
advertising | -1.294 |
Dresden | -1.205 |
��� | -1.204 |
education | -1.168 |
defense | -1.167 |
Token | � |
Token ID | 564 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
anonymously | +0.211 |
orr | +0.203 |
oux | +0.196 |
church | +0.190 |
disse | +0.190 |
Neg logit contributions | |
advertising | -0.230 |
Dresden | -0.215 |
��� | -0.213 |
education | -0.209 |
defense | -0.208 |
Token | � |
Token ID | 250 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
anonymously | +0.894 |
orr | +0.865 |
oux | +0.837 |
church | +0.819 |
disse | +0.817 |
Neg logit contributions | |
advertising | -0.620 |
Dresden | -0.569 |
��� | -0.563 |
education | -0.546 |
peria | -0.545 |
Token | throw |
Token ID | 16939 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
advertising | +0.496 |
Dresden | +0.459 |
��� | +0.454 |
education | +0.449 |
defense | +0.448 |
Neg logit contributions | |
anonymously | -0.514 |
orr | -0.493 |
oux | -0.476 |
disse | -0.465 |
church | -0.461 |
Token | away |
Token ID | 1497 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ary | +11.533 |
advertising | +11.497 |
Dresden | +10.845 |
education | +10.422 |
defense | +10.182 |
Neg logit contributions | |
anonymously | -10.946 |
oux | -10.576 |
disse | -10.327 |
orr | -10.039 |
church | -9.895 |
Token | � |
Token ID | 447 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
advertising | +3.500 |
Dresden | +3.325 |
ary | +3.224 |
education | +3.223 |
��� | +3.211 |
Neg logit contributions | |
anonymously | -3.854 |
orr | -3.700 |
oux | -3.609 |
disse | -3.539 |
church | -3.526 |
Token | � |
Token ID | 251 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
advertising | +0.060 |
Dresden | +0.055 |
��� | +0.055 |
education | +0.053 |
defense | +0.053 |
Neg logit contributions | |
anonymously | -0.094 |
orr | -0.090 |
oux | -0.088 |
disse | -0.086 |
church | -0.086 |
Token | their |
Token ID | 511 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
advertising | +2.226 |
Dresden | +2.087 |
ary | +2.047 |
education | +2.047 |
��� | +2.018 |
Neg logit contributions | |
anonymously | -2.242 |
orr | -2.145 |
oux | -2.089 |
disse | -2.042 |
church | -2.016 |
Token | votes |
Token ID | 5690 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
advertising | +5.181 |
Dresden | +5.054 |
ary | +4.896 |
education | +4.824 |
defense | +4.715 |
Neg logit contributions | |
anonymously | -5.147 |
orr | -5.109 |
oux | -4.988 |
church | -4.834 |
ucci | -4.718 |
Token | No |
Token ID | 2949 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
advertising | +4.276 |
Dresden | +3.884 |
ary | +3.879 |
defense | +3.867 |
peria | +3.755 |
Neg logit contributions | |
anonymously | -5.626 |
orr | -5.310 |
disse | -5.244 |
oux | -5.204 |
church | -5.129 |
Token | ar |
Token ID | 283 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
advertising | +2.847 |
Dresden | +2.685 |
defense | +2.635 |
ary | +2.633 |
��� | +2.624 |
Neg logit contributions | |
anonymously | -3.126 |
orr | -2.962 |
oux | -2.911 |
disse | -2.852 |
church | -2.843 |
Token | Ha |
Token ID | 9398 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
advertising | +0.546 |
Dresden | +0.515 |
��� | +0.509 |
education | +0.499 |
defense | +0.498 |
Neg logit contributions | |
anonymously | -0.492 |
orr | -0.472 |
oux | -0.453 |
disse | -0.443 |
church | -0.442 |
Token | O |
Token ID | 46 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
advertising | +6.035 |
defense | +5.555 |
Dresden | +5.554 |
peria | +5.551 |
ary | +5.545 |
Neg logit contributions | |
anonymously | -6.812 |
orr | -6.376 |
oux | -6.340 |
disse | -6.296 |
church | -6.220 |
Token | ved |
Token ID | 1079 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
advertising | +5.369 |
defense | +4.984 |
education | +4.896 |
Dresden | +4.868 |
ary | +4.861 |
Neg logit contributions | |
anonymously | -4.974 |
orr | -4.558 |
disse | -4.486 |
oux | -4.384 |
church | -4.240 |
Token | Ve |
Token ID | 8016 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
advertising | +4.061 |
ary | +3.845 |
Dresden | +3.813 |
education | +3.757 |
defense | +3.731 |
Neg logit contributions | |
anonymously | -4.617 |
orr | -4.435 |
oux | -4.277 |
disse | -4.254 |
church | -4.248 |
Token | Ha |
Token ID | 23303 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
advertising | +11.446 |
ary | +11.169 |
amily | +11.013 |
peria | +10.898 |
defense | +10.872 |
Neg logit contributions | |
anonymously | -10.235 |
oux | -9.253 |
church | -9.114 |
disse | -8.876 |
orr | -8.846 |
Token | L |
Token ID | 43 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
advertising | +6.538 |
ary | +6.286 |
Dresden | +6.253 |
defense | +6.161 |
��� | +6.132 |
Neg logit contributions | |
anonymously | -6.503 |
orr | -6.223 |
oux | -6.083 |
church | -6.041 |
disse | -6.004 |
Token | omed |
Token ID | 12657 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
advertising | +1.051 |
Dresden | +0.983 |
��� | +0.974 |
education | +0.960 |
ary | +0.958 |
Neg logit contributions | |
anonymously | -1.021 |
orr | -0.975 |
oux | -0.940 |
disse | -0.920 |
church | -0.918 |
Token | , |
Token ID | 11 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
advertising | +4.011 |
Dresden | +3.856 |
ary | +3.804 |
��� | +3.736 |
defense | +3.732 |
Neg logit contributions | |
anonymously | -3.772 |
orr | -3.617 |
oux | -3.463 |
church | -3.456 |
disse | -3.432 |
Token | D |
Token ID | 360 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
anonymously | +3.245 |
orr | +3.055 |
oux | +2.941 |
disse | +2.841 |
church | +2.834 |
Neg logit contributions | |
advertising | -3.448 |
��� | -3.200 |
Dresden | -3.155 |
peria | -3.135 |
education | -3.109 |
Token | strictly |
Token ID | 14084 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
anonymously | +2.947 |
orr | +2.775 |
oux | +2.643 |
disse | +2.602 |
church | +2.587 |
Neg logit contributions | |
advertising | -3.161 |
Dresden | -2.941 |
��� | -2.901 |
education | -2.895 |
defense | -2.884 |
Token | prohibited |
Token ID | 12244 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
anonymously | +4.515 |
orr | +4.313 |
oux | +3.964 |
church | +3.923 |
disse | +3.892 |
Neg logit contributions | |
advertising | -5.864 |
Dresden | -5.477 |
education | -5.432 |
peria | -5.419 |
��� | -5.402 |
Token | without |
Token ID | 1231 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
advertising | +0.339 |
Dresden | +0.317 |
��� | +0.313 |
education | +0.307 |
ary | +0.307 |
Neg logit contributions | |
anonymously | -0.295 |
orr | -0.285 |
oux | -0.275 |
church | -0.267 |
disse | -0.265 |
Token | the |
Token ID | 262 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
advertising | +6.711 |
��� | +6.484 |
ary | +6.477 |
Dresden | +6.444 |
education | +6.110 |
Neg logit contributions | |
anonymously | -8.145 |
orr | -8.139 |
oux | -7.947 |
church | -7.786 |
kef | -7.610 |
Token | express |
Token ID | 4911 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
advertising | +6.666 |
Dresden | +6.278 |
ary | +6.143 |
��� | +6.036 |
education | +5.961 |
Neg logit contributions | |
anonymously | -8.707 |
orr | -8.470 |
oux | -8.079 |
church | -8.065 |
kef | -8.027 |
Token | written |
Token ID | 3194 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
advertising | +4.790 |
ary | +4.531 |
Dresden | +4.526 |
education | +4.330 |
defense | +4.269 |
Neg logit contributions | |
anonymously | -6.076 |
orr | -5.913 |
oux | -5.646 |
church | -5.519 |
ucci | -5.476 |
Token | permission |
Token ID | 7170 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
ary | +6.412 |
Dresden | +6.406 |
advertising | +6.330 |
defense | +5.577 |
Morales | +5.542 |
Neg logit contributions | |
orr | -14.988 |
anonymously | -14.589 |
kef | -14.309 |
ucci | -14.306 |
oux | -14.173 |
Token | of |
Token ID | 286 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
advertising | +2.357 |
Dresden | +2.182 |
��� | +2.169 |
ary | +2.112 |
education | +2.107 |
Neg logit contributions | |
anonymously | -2.750 |
orr | -2.657 |
oux | -2.576 |
disse | -2.513 |
church | -2.510 |
Token | Money |
Token ID | 12911 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
advertising | +2.930 |
Dresden | +2.734 |
��� | +2.644 |
ary | +2.631 |
education | +2.609 |
Neg logit contributions | |
anonymously | -3.245 |
orr | -3.167 |
oux | -3.099 |
church | -2.999 |
disse | -2.975 |
Token | Morning |
Token ID | 14410 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
anonymously | +2.502 |
orr | +2.379 |
oux | +2.269 |
church | +2.202 |
disse | +2.159 |
Neg logit contributions | |
advertising | -3.481 |
��� | -3.364 |
Dresden | -3.262 |
defense | -3.199 |
peria | -3.193 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
advertising | +0.423 |
Dresden | +0.396 |
��� | +0.390 |
education | +0.384 |
ary | +0.383 |
Neg logit contributions | |
anonymously | -0.379 |
orr | -0.366 |
oux | -0.352 |
disse | -0.342 |
church | -0.341 |
Token | Anyway |
Token ID | 21836 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
anonymously | +1.504 |
orr | +1.446 |
oux | +1.392 |
church | +1.349 |
disse | +1.346 |
Neg logit contributions | |
advertising | -1.547 |
��� | -1.456 |
Dresden | -1.442 |
education | -1.407 |
defense | -1.403 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
anonymously | +1.067 |
orr | +1.018 |
oux | +0.976 |
disse | +0.945 |
church | +0.943 |
Neg logit contributions | |
advertising | -1.378 |
Dresden | -1.294 |
��� | -1.289 |
education | -1.261 |
defense | -1.258 |
Token | we |
Token ID | 356 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
advertising | +1.489 |
Dresden | +1.396 |
defense | +1.341 |
ary | +1.336 |
��� | +1.336 |
Neg logit contributions | |
anonymously | -1.559 |
orr | -1.517 |
oux | -1.459 |
church | -1.436 |
disse | -1.420 |
Token | had |
Token ID | 550 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
advertising | +2.883 |
Dresden | +2.774 |
ary | +2.698 |
��� | +2.653 |
education | +2.651 |
Neg logit contributions | |
anonymously | -2.672 |
orr | -2.631 |
oux | -2.531 |
church | -2.501 |
disse | -2.419 |
Token | to |
Token ID | 284 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
advertising | +1.358 |
Dresden | +1.275 |
��� | +1.248 |
ary | +1.226 |
education | +1.221 |
Neg logit contributions | |
anonymously | -1.683 |
orr | -1.630 |
oux | -1.570 |
church | -1.546 |
disse | -1.540 |
Token | throw |
Token ID | 3714 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
advertising | +3.608 |
Dresden | +3.571 |
ary | +3.441 |
defense | +3.432 |
education | +3.377 |
Neg logit contributions | |
orr | -3.263 |
anonymously | -3.255 |
church | -3.143 |
oux | -3.137 |
disse | -3.036 |
Token | a |
Token ID | 257 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
Dresden | +9.978 |
advertising | +9.963 |
ary | +9.846 |
Morales | +9.343 |
defense | +9.091 |
Neg logit contributions | |
anonymously | -11.216 |
oux | -11.048 |
orr | -11.023 |
church | -10.917 |
ococ | -10.687 |
Token | party |
Token ID | 2151 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
advertising | +3.758 |
Dresden | +3.702 |
ary | +3.557 |
defense | +3.489 |
��� | +3.453 |
Neg logit contributions | |
anonymously | -3.493 |
orr | -3.415 |
oux | -3.305 |
church | -3.181 |
disse | -3.130 |
Token | ! |
Token ID | 0 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
anonymously | +1.020 |
orr | +0.973 |
oux | +0.935 |
disse | +0.909 |
church | +0.907 |
Neg logit contributions | |
advertising | -1.116 |
��� | -1.044 |
Dresden | -1.041 |
education | -1.013 |
defense | -1.011 |
Token | Friends |
Token ID | 14213 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
advertising | +0.834 |
Dresden | +0.784 |
��� | +0.754 |
education | +0.751 |
ary | +0.750 |
Neg logit contributions | |
anonymously | -0.854 |
orr | -0.820 |
oux | -0.792 |
disse | -0.775 |
church | -0.771 |
Token | , |
Token ID | 11 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
advertising | +0.922 |
Dresden | +0.873 |
��� | +0.851 |
ary | +0.845 |
education | +0.842 |
Neg logit contributions | |
anonymously | -0.819 |
orr | -0.792 |
oux | -0.764 |
disse | -0.737 |
church | -0.737 |
Token | ) |
Token ID | 8 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
anonymously | +2.220 |
orr | +2.144 |
oux | +2.067 |
church | +2.009 |
disse | +1.971 |
Neg logit contributions | |
advertising | -2.120 |
��� | -2.075 |
Dresden | -1.986 |
education | -1.925 |
peria | -1.922 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
anonymously | +2.170 |
orr | +2.067 |
oux | +1.989 |
church | +1.921 |
disse | +1.902 |
Neg logit contributions | |
advertising | -2.729 |
��� | -2.569 |
Dresden | -2.536 |
education | -2.499 |
peria | -2.490 |
Token |
|
Token ID | 198 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
anonymously | +1.120 |
orr | +1.071 |
oux | +1.028 |
church | +0.996 |
disse | +0.994 |
Neg logit contributions | |
advertising | -1.338 |
��� | -1.256 |
Dresden | -1.255 |
education | -1.220 |
defense | -1.218 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
anonymously | +2.262 |
orr | +2.188 |
oux | +2.112 |
church | +2.064 |
disse | +2.025 |
Neg logit contributions | |
advertising | -2.073 |
��� | -2.004 |
Dresden | -1.968 |
education | -1.886 |
peria | -1.879 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
anonymously | +1.135 |
orr | +1.090 |
oux | +1.046 |
church | +1.013 |
disse | +1.001 |
Neg logit contributions | |
advertising | -1.297 |
��� | -1.249 |
Dresden | -1.212 |
education | -1.188 |
defense | -1.185 |
Token | Rob |
Token ID | 3851 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
advertising | +1.512 |
Dresden | +1.416 |
ary | +1.366 |
��� | +1.359 |
education | +1.354 |
Neg logit contributions | |
anonymously | -1.565 |
orr | -1.495 |
oux | -1.446 |
disse | -1.437 |
church | -1.403 |
Token | Harley |
Token ID | 27440 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
advertising | +6.932 |
ary | +6.602 |
lance | +6.479 |
Dresden | +6.399 |
��� | +5.956 |
Neg logit contributions | |
anonymously | -14.895 |
disse | -14.288 |
orr | -14.279 |
oux | -13.616 |
church | -13.360 |
Token | ( |
Token ID | 357 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
anonymously | +6.572 |
oux | +6.211 |
orr | +6.155 |
church | +5.830 |
disse | +5.747 |
Neg logit contributions | |
advertising | -6.324 |
��� | -5.957 |
peria | -5.846 |
education | -5.831 |
Dresden | -5.666 |
Token | 152 |
Token ID | 17827 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
anonymously | +1.869 |
orr | +1.801 |
oux | +1.721 |
church | +1.680 |
disse | +1.633 |
Neg logit contributions | |
advertising | -2.384 |
��� | -2.315 |
Dresden | -2.264 |
peria | -2.190 |
education | -2.190 |
Token | ) |
Token ID | 8 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
advertising | +1.329 |
Dresden | +1.211 |
ary | +1.194 |
defense | +1.170 |
education | +1.167 |
Neg logit contributions | |
anonymously | -1.699 |
orr | -1.626 |
disse | -1.601 |
oux | -1.584 |
church | -1.542 |
Token | ( |
Token ID | 357 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
anonymously | +1.778 |
orr | +1.717 |
oux | +1.666 |
church | +1.624 |
disse | +1.621 |
Neg logit contributions | |
advertising | -1.260 |
��� | -1.163 |
Dresden | -1.155 |
education | -1.116 |
defense | -1.113 |
Token | , |
Token ID | 11 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
advertising | +3.778 |
Dresden | +3.582 |
ary | +3.497 |
education | +3.470 |
defense | +3.465 |
Neg logit contributions | |
anonymously | -3.405 |
orr | -3.330 |
oux | -3.282 |
church | -3.186 |
disse | -3.175 |
Token | who |
Token ID | 508 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
advertising | +0.519 |
Dresden | +0.490 |
education | +0.478 |
defense | +0.477 |
��� | +0.477 |
Neg logit contributions | |
anonymously | -0.461 |
orr | -0.447 |
oux | -0.433 |
church | -0.418 |
disse | -0.416 |
Token | have |
Token ID | 423 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
advertising | +2.637 |
Dresden | +2.576 |
ary | +2.492 |
��� | +2.456 |
defense | +2.454 |
Neg logit contributions | |
anonymously | -2.763 |
orr | -2.761 |
oux | -2.720 |
church | -2.644 |
disse | -2.559 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
advertising | +1.211 |
Dresden | +1.163 |
ary | +1.128 |
��� | +1.121 |
defense | +1.111 |
Neg logit contributions | |
anonymously | -1.223 |
orr | -1.218 |
oux | -1.186 |
church | -1.150 |
disse | -1.117 |
Token | up |
Token ID | 510 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Dresden | +6.436 |
advertising | +6.273 |
ary | +6.177 |
defense | +5.910 |
education | +5.903 |
Neg logit contributions | |
orr | -6.353 |
oux | -6.197 |
anonymously | -6.127 |
church | -5.853 |
nect | -5.779 |
Token | their |
Token ID | 511 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
advertising | +4.302 |
Dresden | +4.149 |
ary | +4.048 |
education | +3.995 |
defense | +3.978 |
Neg logit contributions | |
anonymously | -4.410 |
orr | -4.319 |
oux | -4.168 |
church | -4.004 |
nect | -3.993 |
Token | criticism |
Token ID | 7734 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
Dresden | +10.104 |
ary | +9.352 |
advertising | +9.149 |
defense | +8.902 |
education | +8.819 |
Neg logit contributions | |
orr | -11.546 |
nect | -11.200 |
oux | -11.136 |
church | -10.741 |
anonymously | -10.704 |
Token | of |
Token ID | 286 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
advertising | +0.541 |
Dresden | +0.505 |
��� | +0.497 |
ary | +0.490 |
defense | +0.490 |
Neg logit contributions | |
anonymously | -0.562 |
orr | -0.543 |
oux | -0.527 |
disse | -0.511 |
church | -0.511 |
Token | the |
Token ID | 262 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
anonymously | +4.898 |
orr | +4.516 |
oux | +4.294 |
church | +4.255 |
disse | +4.223 |
Neg logit contributions | |
advertising | -6.373 |
��� | -5.895 |
peria | -5.749 |
Dresden | -5.611 |
education | -5.594 |
Token | election |
Token ID | 3071 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
anonymously | +2.959 |
orr | +2.789 |
oux | +2.671 |
church | +2.627 |
disse | +2.609 |
Neg logit contributions | |
advertising | -3.635 |
��� | -3.356 |
Dresden | -3.301 |
peria | -3.285 |
education | -3.225 |
Token | and |
Token ID | 290 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
advertising | +1.112 |
Dresden | +1.043 |
��� | +1.025 |
ary | +1.014 |
education | +1.012 |
Neg logit contributions | |
anonymously | -1.056 |
orr | -1.023 |
oux | -0.994 |
church | -0.959 |
disse | -0.958 |
Token | late |
Token ID | 2739 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
anonymously | +0.485 |
orr | +0.470 |
oux | +0.456 |
church | +0.445 |
disse | +0.445 |
Neg logit contributions | |
advertising | -0.342 |
Dresden | -0.317 |
��� | -0.310 |
education | -0.302 |
defense | -0.302 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
anonymously | +2.423 |
orr | +2.337 |
oux | +2.263 |
disse | +2.218 |
church | +2.209 |
Neg logit contributions | |
advertising | -1.587 |
��� | -1.466 |
Dresden | -1.436 |
education | -1.401 |
defense | -1.392 |
Token | . |
Token ID | 13 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
advertising | +0.946 |
Dresden | +0.882 |
��� | +0.861 |
ary | +0.858 |
defense | +0.855 |
Neg logit contributions | |
anonymously | -0.864 |
orr | -0.831 |
oux | -0.802 |
disse | -0.779 |
church | -0.774 |
Token | It |
Token ID | 632 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
advertising | +2.120 |
Dresden | +2.010 |
ary | +1.902 |
defense | +1.881 |
education | +1.860 |
Neg logit contributions | |
anonymously | -2.376 |
orr | -2.275 |
oux | -2.242 |
disse | -2.212 |
church | -2.162 |
Token | took |
Token ID | 1718 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
advertising | +1.275 |
Dresden | +1.181 |
ary | +1.167 |
��� | +1.142 |
defense | +1.140 |
Neg logit contributions | |
anonymously | -1.336 |
orr | -1.302 |
oux | -1.268 |
church | -1.234 |
disse | -1.226 |
Token | almost |
Token ID | 2048 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
advertising | +1.150 |
Dresden | +1.098 |
ary | +1.059 |
defense | +1.050 |
education | +1.041 |
Neg logit contributions | |
anonymously | -1.253 |
orr | -1.215 |
oux | -1.182 |
church | -1.148 |
disse | -1.140 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Dresden | +7.687 |
advertising | +7.338 |
ary | +7.110 |
Morales | +6.742 |
defense | +6.616 |
Neg logit contributions | |
orr | -13.804 |
oux | -13.289 |
church | -13.150 |
nect | -13.066 |
ococ | -13.028 |
Token | years |
Token ID | 812 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
advertising | +6.762 |
Dresden | +6.284 |
ary | +6.139 |
defense | +5.978 |
education | +5.869 |
Neg logit contributions | |
anonymously | -8.141 |
orr | -7.898 |
oux | -7.882 |
church | -7.683 |
disse | -7.648 |
Token | for |
Token ID | 329 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
advertising | +1.943 |
Dresden | +1.824 |
ary | +1.788 |
defense | +1.771 |
education | +1.763 |
Neg logit contributions | |
anonymously | -1.840 |
orr | -1.779 |
oux | -1.726 |
church | -1.673 |
disse | -1.670 |
Token | Bitcoin |
Token ID | 6185 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
advertising | +1.701 |
Dresden | +1.621 |
ary | +1.562 |
defense | +1.556 |
��� | +1.555 |
Neg logit contributions | |
anonymously | -1.645 |
orr | -1.596 |
oux | -1.553 |
church | -1.502 |
disse | -1.490 |
Token | prices |
Token ID | 4536 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
anonymously | +2.754 |
orr | +2.606 |
oux | +2.493 |
disse | +2.458 |
church | +2.427 |
Neg logit contributions | |
advertising | -2.791 |
��� | -2.656 |
Dresden | -2.576 |
education | -2.530 |
peria | -2.528 |
Token | promote |
Token ID | 7719 |
Feature activation | -7.66e-03 |
Pos logit contributions | |
anonymously | +1.739 |
orr | +1.659 |
oux | +1.594 |
disse | +1.550 |
church | +1.548 |
Neg logit contributions | |
advertising | -1.935 |
��� | -1.811 |
Dresden | -1.806 |
education | -1.756 |
defense | -1.753 |
Token | public |
Token ID | 1171 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
anonymously | +0.052 |
orr | +0.050 |
oux | +0.048 |
disse | +0.047 |
church | +0.047 |
Neg logit contributions | |
advertising | -0.052 |
Dresden | -0.049 |
��� | -0.048 |
education | -0.048 |
defense | -0.047 |
Token | health |
Token ID | 1535 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
advertising | +2.908 |
Dresden | +2.730 |
education | +2.711 |
ary | +2.664 |
defense | +2.651 |
Neg logit contributions | |
anonymously | -2.598 |
orr | -2.520 |
oux | -2.448 |
disse | -2.314 |
church | -2.309 |
Token | ," |
Token ID | 553 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
anonymously | +0.447 |
orr | +0.430 |
oux | +0.415 |
disse | +0.403 |
church | +0.403 |
Neg logit contributions | |
advertising | -0.459 |
Dresden | -0.428 |
��� | -0.424 |
education | -0.416 |
defense | -0.415 |
Token | said |
Token ID | 531 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
anonymously | +0.321 |
orr | +0.310 |
oux | +0.298 |
disse | +0.290 |
church | +0.289 |
Neg logit contributions | |
advertising | -0.335 |
Dresden | -0.315 |
��� | -0.309 |
defense | -0.305 |
education | -0.305 |
Token | Diane |
Token ID | 26542 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
anonymously | +0.511 |
orr | +0.491 |
oux | +0.474 |
disse | +0.461 |
church | +0.460 |
Neg logit contributions | |
advertising | -0.510 |
Dresden | -0.478 |
��� | -0.471 |
education | -0.462 |
defense | -0.461 |
Token | Brown |
Token ID | 4373 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Dresden | +10.516 |
Morales | +10.109 |
advertising | +9.935 |
ary | +9.822 |
lance | +8.820 |
Neg logit contributions | |
anonymously | -11.903 |
disse | -10.983 |
orr | -10.890 |
oux | -10.674 |
ococ | -10.430 |
Token | , |
Token ID | 11 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
advertising | +0.979 |
Dresden | +0.923 |
��� | +0.911 |
ary | +0.898 |
education | +0.896 |
Neg logit contributions | |
anonymously | -0.787 |
orr | -0.748 |
oux | -0.715 |
disse | -0.706 |
church | -0.691 |
Token | executive |
Token ID | 4640 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
anonymously | +0.055 |
orr | +0.053 |
oux | +0.051 |
church | +0.050 |
disse | +0.050 |
Neg logit contributions | |
advertising | -0.065 |
Dresden | -0.061 |
��� | -0.060 |
education | -0.059 |
defense | -0.059 |
Token | director |
Token ID | 3437 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
anonymously | +1.356 |
orr | +1.293 |
oux | +1.251 |
disse | +1.214 |
church | +1.212 |
Neg logit contributions | |
advertising | -1.396 |
��� | -1.302 |
Dresden | -1.299 |
education | -1.259 |
defense | -1.256 |
Token | of |
Token ID | 286 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
anonymously | +2.573 |
orr | +2.441 |
oux | +2.379 |
church | +2.292 |
disse | +2.257 |
Neg logit contributions | |
advertising | -2.697 |
��� | -2.497 |
Dresden | -2.476 |
peria | -2.415 |
education | -2.393 |
Token | un |
Token ID | 403 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
anonymously | +4.421 |
orr | +4.283 |
oux | +4.158 |
church | +4.014 |
ucci | +3.878 |
Neg logit contributions | |
advertising | -3.964 |
��� | -3.848 |
Dresden | -3.749 |
peria | -3.582 |
defense | -3.560 |
Token | zel |
Token ID | 17396 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
anonymously | +2.379 |
orr | +2.265 |
oux | +2.185 |
church | +2.082 |
disse | +2.067 |
Neg logit contributions | |
advertising | -3.537 |
��� | -3.365 |
Dresden | -3.313 |
peria | -3.240 |
education | -3.220 |
Token | ?" |
Token ID | 1701 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
advertising | +0.217 |
Dresden | +0.205 |
��� | +0.201 |
ary | +0.199 |
defense | +0.198 |
Neg logit contributions | |
anonymously | -0.174 |
orr | -0.166 |
oux | -0.159 |
disse | -0.155 |
church | -0.154 |
Token | I |
Token ID | 314 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
advertising | +4.331 |
Dresden | +4.116 |
ary | +3.980 |
defense | +3.964 |
education | +3.896 |
Neg logit contributions | |
anonymously | -5.034 |
orr | -4.901 |
oux | -4.724 |
church | -4.644 |
disse | -4.624 |
Token | finally |
Token ID | 3443 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
advertising | +3.803 |
Dresden | +3.692 |
ary | +3.631 |
defense | +3.551 |
education | +3.471 |
Neg logit contributions | |
orr | -3.896 |
anonymously | -3.873 |
church | -3.802 |
oux | -3.782 |
disse | -3.643 |
Token | found |
Token ID | 1043 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ary | +6.258 |
Dresden | +6.171 |
advertising | +6.166 |
defense | +6.025 |
education | +5.885 |
Neg logit contributions | |
church | -6.335 |
orr | -6.331 |
anonymously | -6.192 |
oux | -6.114 |
disse | -5.947 |
Token | my |
Token ID | 616 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Dresden | +8.905 |
advertising | +8.494 |
ary | +8.394 |
defense | +8.079 |
Morales | +7.961 |
Neg logit contributions | |
orr | -11.975 |
church | -11.899 |
anonymously | -11.667 |
oux | -11.514 |
disse | -11.484 |
Token | voice |
Token ID | 3809 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
advertising | +7.720 |
Dresden | +7.691 |
ary | +7.500 |
defense | +7.376 |
education | +7.046 |
Neg logit contributions | |
orr | -9.119 |
anonymously | -9.026 |
church | -8.598 |
oux | -8.594 |
kef | -8.435 |
Token | and |
Token ID | 290 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
advertising | +4.145 |
Dresden | +3.989 |
ary | +3.925 |
defense | +3.891 |
education | +3.839 |
Neg logit contributions | |
anonymously | -4.399 |
orr | -4.398 |
oux | -4.227 |
church | -4.182 |
disse | -4.114 |
Token | gave |
Token ID | 2921 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
Dresden | +4.712 |
advertising | +4.711 |
ary | +4.550 |
defense | +4.461 |
��� | +4.401 |
Neg logit contributions | |
orr | -4.481 |
anonymously | -4.447 |
oux | -4.269 |
church | -4.250 |
disse | -4.100 |
Token | her |
Token ID | 607 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
advertising | +3.806 |
Dresden | +3.662 |
ary | +3.511 |
defense | +3.490 |
��� | +3.488 |
Neg logit contributions | |
anonymously | -4.337 |
orr | -4.240 |
oux | -4.091 |
church | -4.018 |
disse | -3.998 |
Token | 53 |
Token ID | 4310 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
advertising | +2.465 |
Dresden | +2.263 |
ary | +2.167 |
defense | +2.156 |
education | +2.135 |
Neg logit contributions | |
anonymously | -2.922 |
orr | -2.786 |
disse | -2.748 |
oux | -2.722 |
church | -2.630 |
Token | p |
Token ID | 279 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
advertising | +3.433 |
Dresden | +3.252 |
ary | +3.174 |
defense | +3.149 |
peria | +3.145 |
Neg logit contributions | |
anonymously | -2.611 |
orr | -2.482 |
oux | -2.409 |
church | -2.340 |
disse | -2.336 |
Token | . |
Token ID | 13 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
advertising | +0.269 |
Dresden | +0.250 |
ary | +0.243 |
education | +0.243 |
defense | +0.243 |
Neg logit contributions | |
anonymously | -0.258 |
orr | -0.247 |
oux | -0.238 |
disse | -0.235 |
church | -0.231 |
Token | m |
Token ID | 76 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
anonymously | +0.242 |
orr | +0.230 |
oux | +0.222 |
disse | +0.219 |
church | +0.215 |
Neg logit contributions | |
advertising | -0.263 |
Dresden | -0.245 |
education | -0.238 |
defense | -0.238 |
ary | -0.237 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
advertising | +6.314 |
Dresden | +5.832 |
defense | +5.814 |
ary | +5.796 |
ebted | +5.670 |
Neg logit contributions | |
anonymously | -8.187 |
orr | -7.967 |
disse | -7.794 |
church | -7.631 |
oux | -7.613 |
Token | PT |
Token ID | 19310 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
advertising | +7.875 |
Dresden | +7.807 |
defense | +7.578 |
ary | +7.518 |
Morales | +7.358 |
Neg logit contributions | |
anonymously | -5.105 |
orr | -4.954 |
disse | -4.765 |
oux | -4.738 |
church | -4.638 |
Token | with |
Token ID | 351 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
advertising | +10.562 |
ary | +10.249 |
Dresden | +10.244 |
defense | +10.086 |
Morales | +9.790 |
Neg logit contributions | |
orr | -9.801 |
anonymously | -9.796 |
disse | -9.590 |
oux | -9.234 |
kef | -9.234 |
Token | additional |
Token ID | 3224 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
advertising | +4.943 |
Dresden | +4.713 |
ary | +4.539 |
��� | +4.469 |
defense | +4.448 |
Neg logit contributions | |
anonymously | -5.332 |
orr | -5.287 |
oux | -5.034 |
church | -4.946 |
disse | -4.898 |
Token | details |
Token ID | 3307 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
advertising | +4.762 |
Dresden | +4.509 |
ary | +4.390 |
defense | +4.311 |
education | +4.283 |
Neg logit contributions | |
anonymously | -4.250 |
orr | -4.203 |
oux | -4.074 |
church | -3.947 |
disse | -3.860 |
Token | and |
Token ID | 290 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
advertising | +1.717 |
Dresden | +1.608 |
ary | +1.573 |
��� | +1.565 |
education | +1.555 |
Neg logit contributions | |
anonymously | -1.559 |
orr | -1.509 |
oux | -1.465 |
church | -1.424 |
disse | -1.417 |
Token | analysis |
Token ID | 3781 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
advertising | +1.675 |
Dresden | +1.575 |
��� | +1.532 |
ary | +1.525 |
defense | +1.522 |
Neg logit contributions | |
anonymously | -1.650 |
orr | -1.614 |
oux | -1.561 |
church | -1.514 |
disse | -1.492 |
Token | returned |
Token ID | 4504 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
anonymously | +0.292 |
orr | +0.281 |
oux | +0.271 |
church | +0.263 |
disse | +0.262 |
Neg logit contributions | |
advertising | -0.308 |
Dresden | -0.286 |
��� | -0.281 |
education | -0.279 |
defense | -0.278 |
Token | to |
Token ID | 284 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
advertising | +1.717 |
Dresden | +1.624 |
ary | +1.558 |
education | +1.554 |
defense | +1.550 |
Neg logit contributions | |
anonymously | -1.838 |
orr | -1.798 |
oux | -1.730 |
disse | -1.692 |
church | -1.688 |
Token | Al |
Token ID | 978 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
advertising | +1.219 |
Dresden | +1.141 |
��� | +1.112 |
education | +1.101 |
defense | +1.093 |
Neg logit contributions | |
anonymously | -1.312 |
orr | -1.261 |
oux | -1.225 |
church | -1.191 |
disse | -1.188 |
Token | cat |
Token ID | 9246 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
advertising | +1.412 |
Dresden | +1.280 |
ary | +1.254 |
defense | +1.247 |
education | +1.246 |
Neg logit contributions | |
anonymously | -1.886 |
orr | -1.773 |
disse | -1.737 |
oux | -1.730 |
church | -1.671 |
Token | raz |
Token ID | 3247 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
anonymously | +3.157 |
orr | +3.107 |
oux | +3.040 |
church | +2.938 |
disse | +2.863 |
Neg logit contributions | |
��� | -1.912 |
advertising | -1.900 |
Dresden | -1.736 |
education | -1.654 |
defense | -1.645 |
Token | nearly |
Token ID | 3016 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
advertising | +1.481 |
Dresden | +1.382 |
ary | +1.343 |
education | +1.336 |
defense | +1.332 |
Neg logit contributions | |
anonymously | -1.644 |
orr | -1.605 |
oux | -1.543 |
church | -1.515 |
disse | -1.513 |
Token | 50 |
Token ID | 2026 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
Dresden | +7.973 |
advertising | +7.577 |
Morales | +7.450 |
ary | +7.319 |
education | +6.881 |
Neg logit contributions | |
orr | -13.421 |
oux | -13.076 |
ococ | -12.628 |
church | -12.403 |
nect | -12.241 |
Token | years |
Token ID | 812 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
advertising | +4.958 |
Dresden | +4.382 |
defense | +4.377 |
ary | +4.278 |
education | +4.228 |
Neg logit contributions | |
anonymously | -7.550 |
orr | -7.357 |
oux | -7.146 |
church | -6.986 |
disse | -6.965 |
Token | after |
Token ID | 706 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
advertising | +2.461 |
Dresden | +2.283 |
ary | +2.256 |
��� | +2.213 |
defense | +2.201 |
Neg logit contributions | |
anonymously | -3.230 |
orr | -3.133 |
oux | -3.070 |
church | -2.994 |
disse | -2.973 |
Token | the |
Token ID | 262 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
anonymously | +4.137 |
orr | +3.945 |
oux | +3.786 |
disse | +3.723 |
church | +3.674 |
Neg logit contributions | |
advertising | -4.823 |
��� | -4.571 |
peria | -4.432 |
Dresden | -4.428 |
ebted | -4.408 |
Token | prison |
Token ID | 3770 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
anonymously | +2.112 |
orr | +2.025 |
oux | +1.951 |
disse | +1.900 |
church | +1.896 |
Neg logit contributions | |
advertising | -2.147 |
��� | -1.993 |
Dresden | -1.993 |
education | -1.938 |
defense | -1.936 |
Token | much |
Token ID | 881 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
advertising | +1.915 |
Dresden | +1.783 |
ary | +1.718 |
��� | +1.717 |
education | +1.716 |
Neg logit contributions | |
anonymously | -1.900 |
orr | -1.843 |
oux | -1.787 |
church | -1.742 |
disse | -1.729 |
Token | as |
Token ID | 355 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
anonymously | +1.336 |
orr | +1.256 |
oux | +1.175 |
disse | +1.129 |
church | +1.114 |
Neg logit contributions | |
advertising | -2.909 |
��� | -2.761 |
Dresden | -2.758 |
education | -2.701 |
peria | -2.697 |
Token | he |
Token ID | 339 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
advertising | +0.630 |
Dresden | +0.590 |
��� | +0.583 |
education | +0.571 |
defense | +0.570 |
Neg logit contributions | |
anonymously | -0.601 |
orr | -0.578 |
oux | -0.556 |
church | -0.542 |
disse | -0.541 |
Token | � |
Token ID | 564 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
advertising | +1.089 |
Dresden | +1.013 |
��� | +0.992 |
education | +0.983 |
ary | +0.983 |
Neg logit contributions | |
anonymously | -1.057 |
orr | -1.016 |
oux | -0.983 |
church | -0.966 |
disse | -0.954 |
Token | � |
Token ID | 250 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
advertising | +2.390 |
Dresden | +2.128 |
education | +2.025 |
defense | +2.022 |
ary | +1.949 |
Neg logit contributions | |
anonymously | -5.287 |
disse | -5.048 |
orr | -5.034 |
oux | -5.009 |
church | -4.883 |
Token | w |
Token ID | 86 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
anonymously | +0.678 |
orr | +0.653 |
oux | +0.632 |
disse | +0.617 |
church | +0.616 |
Neg logit contributions | |
advertising | -0.539 |
Dresden | -0.496 |
��� | -0.491 |
education | -0.481 |
defense | -0.479 |
Token | ants |
Token ID | 1187 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
ary | +10.890 |
advertising | +10.146 |
education | +9.879 |
lance | +9.467 |
amily | +9.286 |
Neg logit contributions | |
anonymously | -11.583 |
church | -9.953 |
disse | -9.933 |
oux | -9.707 |
orr | -9.685 |
Token | to |
Token ID | 284 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
advertising | +3.175 |
Dresden | +2.958 |
defense | +2.854 |
ary | +2.851 |
education | +2.838 |
Neg logit contributions | |
anonymously | -3.646 |
orr | -3.553 |
oux | -3.429 |
church | -3.402 |
disse | -3.334 |
Token | be |
Token ID | 307 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
anonymously | +0.249 |
orr | +0.240 |
oux | +0.232 |
church | +0.227 |
disse | +0.223 |
Neg logit contributions | |
advertising | -0.276 |
Dresden | -0.260 |
��� | -0.254 |
ary | -0.252 |
defense | -0.252 |
Token | able |
Token ID | 1498 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
advertising | +0.118 |
Dresden | +0.110 |
��� | +0.108 |
ary | +0.107 |
education | +0.107 |
Neg logit contributions | |
anonymously | -0.097 |
orr | -0.093 |
oux | -0.090 |
church | -0.087 |
disse | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
advertising | +2.311 |
Dresden | +2.139 |
��� | +2.125 |
ary | +2.080 |
education | +2.067 |
Neg logit contributions | |
anonymously | -2.795 |
orr | -2.712 |
oux | -2.625 |
church | -2.568 |
disse | -2.543 |
Token | which |
Token ID | 543 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
anonymously | +0.227 |
orr | +0.219 |
oux | +0.210 |
church | +0.205 |
disse | +0.204 |
Neg logit contributions | |
advertising | -0.255 |
Dresden | -0.240 |
��� | -0.237 |
education | -0.232 |
ary | -0.231 |
Token | I |
Token ID | 314 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
advertising | +3.541 |
Dresden | +3.468 |
ary | +3.309 |
��� | +3.238 |
education | +3.199 |
Neg logit contributions | |
anonymously | -3.988 |
orr | -3.912 |
oux | -3.802 |
church | -3.730 |
disse | -3.645 |
Token | have |
Token ID | 423 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
anonymously | +1.357 |
orr | +1.302 |
oux | +1.253 |
church | +1.218 |
disse | +1.215 |
Neg logit contributions | |
advertising | -1.548 |
Dresden | -1.453 |
��� | -1.441 |
education | -1.410 |
defense | -1.407 |
Token | kept |
Token ID | 4030 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
anonymously | +1.778 |
orr | +1.687 |
oux | +1.617 |
disse | +1.571 |
church | +1.566 |
Neg logit contributions | |
advertising | -2.165 |
Dresden | -2.021 |
��� | -2.020 |
education | -1.975 |
defense | -1.974 |
Token | for |
Token ID | 329 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
advertising | +2.699 |
Dresden | +2.639 |
ary | +2.559 |
��� | +2.483 |
education | +2.473 |
Neg logit contributions | |
orr | -2.635 |
anonymously | -2.609 |
oux | -2.568 |
church | -2.471 |
disse | -2.459 |
Token | almost |
Token ID | 2048 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Dresden | +6.430 |
advertising | +6.208 |
ary | +6.051 |
education | +5.903 |
��� | +5.795 |
Neg logit contributions | |
orr | -6.841 |
anonymously | -6.837 |
oux | -6.834 |
church | -6.674 |
nect | -6.612 |
Token | 30 |
Token ID | 1542 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Dresden | +7.568 |
advertising | +6.987 |
ary | +6.895 |
education | +6.467 |
peria | +6.313 |
Neg logit contributions | |
orr | -13.407 |
oux | -13.128 |
church | -13.054 |
nect | -12.935 |
ucci | -12.897 |
Token | years |
Token ID | 812 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
advertising | +1.728 |
Dresden | +1.613 |
��� | +1.573 |
defense | +1.549 |
ary | +1.549 |
Neg logit contributions | |
anonymously | -1.929 |
orr | -1.857 |
oux | -1.798 |
disse | -1.757 |
church | -1.757 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
advertising | +2.325 |
Dresden | +2.197 |
ary | +2.147 |
��� | +2.110 |
education | +2.107 |
Neg logit contributions | |
anonymously | -2.143 |
orr | -2.096 |
oux | -2.050 |
church | -1.985 |
disse | -1.971 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
advertising | +1.882 |
Dresden | +1.792 |
ary | +1.697 |
education | +1.681 |
��� | +1.667 |
Neg logit contributions | |
anonymously | -2.038 |
orr | -1.951 |
oux | -1.893 |
disse | -1.882 |
church | -1.861 |
Token |
|
Token ID | 198 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
advertising | +0.781 |
Dresden | +0.722 |
ary | +0.709 |
education | +0.700 |
defense | +0.697 |
Neg logit contributions | |
anonymously | -0.761 |
orr | -0.724 |
disse | -0.705 |
oux | -0.704 |
church | -0.682 |
Token | MORE |
Token ID | 12011 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
anonymously | +2.264 |
orr | +2.182 |
oux | +2.113 |
disse | +2.065 |
church | +2.056 |
Neg logit contributions | |
advertising | -2.122 |
Dresden | -1.978 |
��� | -1.956 |
education | -1.915 |
defense | -1.910 |
Token | and |
Token ID | 290 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
anonymously | +2.923 |
orr | +2.760 |
oux | +2.660 |
church | +2.535 |
disse | +2.496 |
Neg logit contributions | |
advertising | -3.902 |
��� | -3.755 |
Dresden | -3.616 |
peria | -3.578 |
defense | -3.555 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
advertising | +1.401 |
Dresden | +1.326 |
ary | +1.281 |
��� | +1.277 |
education | +1.276 |
Neg logit contributions | |
anonymously | -1.398 |
orr | -1.369 |
oux | -1.321 |
church | -1.278 |
disse | -1.277 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
advertising | +4.323 |
Dresden | +4.191 |
ary | +4.017 |
Morales | +3.777 |
education | +3.769 |
Neg logit contributions | |
anonymously | -6.689 |
orr | -6.591 |
disse | -6.523 |
oux | -6.473 |
church | -6.322 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
advertising | +4.632 |
Dresden | +4.449 |
ary | +4.308 |
education | +4.165 |
peria | +4.039 |
Neg logit contributions | |
anonymously | -6.994 |
orr | -6.923 |
church | -6.875 |
oux | -6.842 |
disse | -6.790 |
Token | Diane |
Token ID | 26542 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
anonymously | +1.784 |
orr | +1.684 |
oux | +1.632 |
disse | +1.582 |
church | +1.581 |
Neg logit contributions | |
advertising | -1.698 |
��� | -1.617 |
Dresden | -1.549 |
peria | -1.531 |
education | -1.525 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Dresden | +3.451 |
advertising | +3.305 |
lance | +2.621 |
ary | +2.620 |
Morales | +2.410 |
Neg logit contributions | |
orr | -19.423 |
anonymously | -19.138 |
oux | -18.802 |
disse | -18.690 |
church | -18.246 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
advertising | +2.447 |
Dresden | +2.283 |
education | +2.183 |
ary | +2.177 |
defense | +2.165 |
Neg logit contributions | |
anonymously | -2.962 |
orr | -2.870 |
oux | -2.778 |
disse | -2.745 |
church | -2.716 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
anonymously | +0.472 |
orr | +0.449 |
oux | +0.430 |
church | +0.418 |
disse | +0.413 |
Neg logit contributions | |
advertising | -0.524 |
��� | -0.500 |
Dresden | -0.496 |
peria | -0.478 |
education | -0.478 |
Token | : |
Token ID | 25 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
advertising | +0.075 |
Dresden | +0.070 |
��� | +0.069 |
education | +0.068 |
defense | +0.068 |
Neg logit contributions | |
anonymously | -0.079 |
orr | -0.076 |
oux | -0.074 |
disse | -0.071 |
church | -0.071 |
Token | ' |
Token ID | 705 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
anonymously | +0.187 |
orr | +0.181 |
oux | +0.175 |
disse | +0.171 |
church | +0.171 |
Neg logit contributions | |
advertising | -0.139 |
Dresden | -0.128 |
��� | -0.127 |
education | -0.123 |
defense | -0.123 |
Token | war |
Token ID | 1175 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
advertising | +2.223 |
Dresden | +2.133 |
ary | +2.083 |
education | +2.067 |
defense | +2.064 |
Neg logit contributions | |
anonymously | -2.276 |
orr | -2.197 |
oux | -2.152 |
church | -2.068 |
disse | -2.027 |
Token | � |
Token ID | 447 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
advertising | +1.958 |
Dresden | +1.827 |
ary | +1.781 |
��� | +1.773 |
defense | +1.772 |
Neg logit contributions | |
anonymously | -2.062 |
orr | -1.980 |
oux | -1.929 |
disse | -1.881 |
church | -1.870 |
Token | � |
Token ID | 251 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
advertising | +0.040 |
Dresden | +0.037 |
��� | +0.036 |
education | +0.036 |
defense | +0.035 |
Neg logit contributions | |
anonymously | -0.061 |
orr | -0.058 |
oux | -0.057 |
disse | -0.056 |
church | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
advertising | +0.819 |
Dresden | +0.767 |
��� | +0.752 |
education | +0.747 |
defense | +0.746 |
Neg logit contributions | |
anonymously | -0.725 |
orr | -0.693 |
oux | -0.669 |
disse | -0.652 |
church | -0.646 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
advertising | +3.836 |
Dresden | +3.694 |
ary | +3.537 |
education | +3.522 |
defense | +3.511 |
Neg logit contributions | |
anonymously | -3.947 |
orr | -3.903 |
oux | -3.804 |
church | -3.733 |
disse | -3.611 |
Token | contr |
Token ID | 3445 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
advertising | +1.328 |
Dresden | +1.260 |
��� | +1.227 |
education | +1.212 |
defense | +1.211 |
Neg logit contributions | |
anonymously | -1.271 |
orr | -1.224 |
oux | -1.183 |
disse | -1.145 |
church | -1.144 |
Token | aband |
Token ID | 49248 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
advertising | +8.589 |
ary | +8.575 |
education | +7.482 |
amily | +7.448 |
defense | +7.315 |
Neg logit contributions | |
anonymously | -13.401 |
disse | -12.441 |
oux | -12.437 |
church | -12.330 |
orr | -12.144 |
Token | trade |
Token ID | 3292 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
anonymously | +0.895 |
orr | +0.858 |
oux | +0.826 |
disse | +0.803 |
church | +0.802 |
Neg logit contributions | |
advertising | -0.942 |
Dresden | -0.879 |
��� | -0.875 |
education | -0.853 |
defense | -0.852 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
anonymously | +2.361 |
orr | +2.246 |
oux | +2.150 |
disse | +2.086 |
church | +2.081 |
Neg logit contributions | |
advertising | -2.659 |
��� | -2.515 |
Dresden | -2.476 |
peria | -2.422 |
education | -2.413 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
advertising | +1.251 |
Dresden | +1.172 |
defense | +1.124 |
��� | +1.122 |
ary | +1.122 |
Neg logit contributions | |
anonymously | -1.269 |
orr | -1.214 |
oux | -1.177 |
disse | -1.157 |
church | -1.145 |
Token |
|
Token ID | 198 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
anonymously | +0.085 |
orr | +0.080 |
oux | +0.078 |
disse | +0.077 |
church | +0.075 |
Neg logit contributions | |
advertising | -0.094 |
Dresden | -0.087 |
education | -0.085 |
ary | -0.085 |
defense | -0.085 |
Token | ised |
Token ID | 1417 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
anonymously | +3.239 |
oux | +2.953 |
orr | +2.939 |
church | +2.663 |
disse | +2.589 |
Neg logit contributions | |
advertising | -9.148 |
��� | -9.083 |
Dresden | -8.933 |
defense | -8.593 |
peria | -8.469 |
Token | on |
Token ID | 319 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
anonymously | +1.308 |
orr | +1.219 |
oux | +1.180 |
disse | +1.142 |
church | +1.132 |
Neg logit contributions | |
advertising | -1.786 |
Dresden | -1.689 |
��� | -1.685 |
education | -1.637 |
defense | -1.637 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
advertising | +2.863 |
Dresden | +2.678 |
ary | +2.599 |
education | +2.594 |
��� | +2.584 |
Neg logit contributions | |
anonymously | -2.914 |
orr | -2.854 |
oux | -2.750 |
church | -2.685 |
disse | -2.636 |
Token | vast |
Token ID | 5909 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
advertising | +1.183 |
Dresden | +1.115 |
��� | +1.099 |
ary | +1.081 |
education | +1.076 |
Neg logit contributions | |
anonymously | -1.119 |
orr | -1.078 |
oux | -1.035 |
church | -1.008 |
disse | -1.002 |
Token | m |
Token ID | 285 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
anonymously | +0.675 |
orr | +0.647 |
oux | +0.623 |
disse | +0.604 |
church | +0.604 |
Neg logit contributions | |
advertising | -0.731 |
Dresden | -0.683 |
��� | -0.679 |
education | -0.663 |
defense | -0.662 |
Token | iscal |
Token ID | 7860 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
anonymously | +0.259 |
orr | +0.249 |
oux | +0.241 |
disse | +0.235 |
church | +0.235 |
Neg logit contributions | |
advertising | -0.236 |
Dresden | -0.219 |
��� | -0.217 |
education | -0.212 |
defense | -0.212 |
Token | culation |
Token ID | 14902 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
orr | +8.876 |
anonymously | +8.595 |
oux | +7.861 |
church | +7.859 |
ucci | +7.712 |
Neg logit contributions | |
Dresden | -15.569 |
��� | -15.522 |
advertising | -15.088 |
peria | -14.411 |
defense | -14.380 |
Token | about |
Token ID | 546 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
anonymously | +2.166 |
orr | +2.070 |
oux | +1.987 |
disse | +1.938 |
church | +1.931 |
Neg logit contributions | |
advertising | -2.221 |
��� | -2.092 |
Dresden | -2.067 |
education | -2.014 |
defense | -2.013 |
Token | the |
Token ID | 262 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
advertising | +0.526 |
Dresden | +0.493 |
education | +0.479 |
��� | +0.478 |
ary | +0.476 |
Neg logit contributions | |
anonymously | -0.528 |
orr | -0.515 |
oux | -0.495 |
disse | -0.479 |
church | -0.478 |
Token | origins |
Token ID | 15587 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
advertising | +2.458 |
Dresden | +2.329 |
ary | +2.268 |
education | +2.249 |
defense | +2.219 |
Neg logit contributions | |
anonymously | -2.624 |
orr | -2.551 |
oux | -2.439 |
church | -2.371 |
disse | -2.363 |
Token | of |
Token ID | 286 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
advertising | +2.567 |
Dresden | +2.377 |
��� | +2.357 |
ary | +2.314 |
education | +2.314 |
Neg logit contributions | |
anonymously | -2.807 |
orr | -2.700 |
oux | -2.605 |
disse | -2.543 |
church | -2.533 |
Token | where |
Token ID | 810 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
anonymously | +0.119 |
orr | +0.115 |
oux | +0.111 |
church | +0.107 |
disse | +0.107 |
Neg logit contributions | |
advertising | -0.123 |
Dresden | -0.116 |
��� | -0.114 |
education | -0.112 |
defense | -0.112 |
Token | do |
Token ID | 466 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
advertising | +3.609 |
Dresden | +3.402 |
education | +3.297 |
ary | +3.278 |
��� | +3.248 |
Neg logit contributions | |
anonymously | -3.596 |
orr | -3.498 |
oux | -3.367 |
disse | -3.281 |
church | -3.265 |
Token | we |
Token ID | 356 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
advertising | +1.034 |
Dresden | +0.977 |
��� | +0.956 |
education | +0.941 |
ary | +0.939 |
Neg logit contributions | |
anonymously | -1.009 |
orr | -0.975 |
oux | -0.939 |
church | -0.908 |
disse | -0.907 |
Token | draw |
Token ID | 3197 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
anonymously | +5.018 |
orr | +4.648 |
oux | +4.431 |
disse | +4.322 |
church | +4.193 |
Neg logit contributions | |
advertising | -6.988 |
��� | -6.682 |
Dresden | -6.406 |
peria | -6.359 |
ebted | -6.307 |
Token | the |
Token ID | 262 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
anonymously | +2.420 |
orr | +2.288 |
oux | +2.215 |
disse | +2.161 |
church | +2.139 |
Neg logit contributions | |
advertising | -2.641 |
��� | -2.465 |
Dresden | -2.434 |
education | -2.384 |
peria | -2.379 |
Token | line |
Token ID | 1627 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
anonymously | +4.144 |
orr | +3.893 |
oux | +3.782 |
disse | +3.720 |
church | +3.623 |
Neg logit contributions | |
advertising | -5.029 |
��� | -4.731 |
Dresden | -4.592 |
peria | -4.555 |
education | -4.539 |
Token | ? |
Token ID | 30 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
anonymously | +10.218 |
orr | +8.787 |
oux | +8.786 |
disse | +8.509 |
church | +7.988 |
Neg logit contributions | |
��� | -14.829 |
advertising | -14.237 |
peria | -13.553 |
education | -13.428 |
amily | -13.330 |
Token | So |
Token ID | 1406 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
anonymously | +2.543 |
orr | +2.435 |
oux | +2.344 |
church | +2.277 |
disse | +2.262 |
Neg logit contributions | |
advertising | -2.668 |
��� | -2.546 |
Dresden | -2.477 |
peria | -2.438 |
defense | -2.432 |
Token | they |
Token ID | 484 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
anonymously | +0.605 |
orr | +0.581 |
oux | +0.560 |
disse | +0.543 |
church | +0.543 |
Neg logit contributions | |
advertising | -0.665 |
Dresden | -0.622 |
��� | -0.614 |
education | -0.603 |
ary | -0.601 |
Token | say |
Token ID | 910 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
advertising | +0.435 |
Dresden | +0.411 |
��� | +0.402 |
ary | +0.400 |
education | +0.398 |
Neg logit contributions | |
anonymously | -0.396 |
orr | -0.386 |
oux | -0.374 |
church | -0.363 |
disse | -0.357 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
anonymously | +1.331 |
orr | +1.272 |
oux | +1.222 |
disse | +1.187 |
church | +1.186 |
Neg logit contributions | |
advertising | -1.525 |
Dresden | -1.425 |
��� | -1.423 |
education | -1.387 |
defense | -1.385 |
Token | / |
Token ID | 14 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
advertising | +2.260 |
Dresden | +2.080 |
ary | +2.049 |
education | +2.023 |
defense | +2.023 |
Neg logit contributions | |
anonymously | -2.447 |
orr | -2.387 |
oux | -2.286 |
disse | -2.239 |
church | -2.198 |
Token | Office |
Token ID | 27743 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
advertising | +0.951 |
Dresden | +0.868 |
education | +0.854 |
��� | +0.854 |
defense | +0.849 |
Neg logit contributions | |
anonymously | -1.005 |
orr | -0.969 |
oux | -0.932 |
disse | -0.913 |
church | -0.899 |
Token | ) |
Token ID | 8 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
advertising | +1.907 |
Dresden | +1.770 |
��� | +1.739 |
ary | +1.729 |
education | +1.728 |
Neg logit contributions | |
anonymously | -2.010 |
orr | -1.960 |
oux | -1.887 |
disse | -1.833 |
church | -1.825 |
Token | and |
Token ID | 290 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
advertising | +3.006 |
Dresden | +2.814 |
education | +2.740 |
��� | +2.723 |
ary | +2.709 |
Neg logit contributions | |
anonymously | -2.909 |
orr | -2.882 |
oux | -2.754 |
church | -2.667 |
disse | -2.650 |
Token | enable |
Token ID | 7139 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
advertising | +1.111 |
Dresden | +1.039 |
��� | +1.018 |
education | +1.007 |
ary | +1.002 |
Neg logit contributions | |
anonymously | -1.060 |
orr | -1.038 |
oux | -0.991 |
church | -0.964 |
disse | -0.962 |
Token | Broad |
Token ID | 9765 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
advertising | +1.401 |
Dresden | +1.308 |
��� | +1.284 |
ary | +1.268 |
education | +1.265 |
Neg logit contributions | |
anonymously | -1.318 |
orr | -1.282 |
oux | -1.225 |
church | -1.192 |
disse | -1.185 |
Token | band |
Token ID | 3903 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
anonymously | +9.868 |
church | +9.513 |
orr | +9.175 |
oux | +8.591 |
nect | +8.516 |
Neg logit contributions | |
��� | -15.233 |
Dresden | -14.337 |
advertising | -13.939 |
defense | -13.779 |
ebted | -13.711 |
Token | Connection |
Token ID | 26923 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
anonymously | +0.728 |
orr | +0.702 |
oux | +0.677 |
disse | +0.659 |
church | +0.659 |
Neg logit contributions | |
advertising | -0.676 |
Dresden | -0.627 |
��� | -0.621 |
education | -0.608 |
defense | -0.607 |
Token | ( |
Token ID | 357 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
advertising | +1.939 |
Dresden | +1.803 |
ary | +1.769 |
education | +1.745 |
defense | +1.730 |
Neg logit contributions | |
anonymously | -2.051 |
orr | -2.023 |
oux | -1.939 |
church | -1.903 |
disse | -1.886 |
Token | Co |
Token ID | 7222 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
anonymously | +0.135 |
orr | +0.130 |
oux | +0.125 |
disse | +0.123 |
church | +0.121 |
Neg logit contributions | |
advertising | -0.126 |
Dresden | -0.115 |
��� | -0.114 |
education | -0.113 |
defense | -0.113 |
Token | ax |
Token ID | 897 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
anonymously | +1.253 |
orr | +1.211 |
oux | +1.171 |
church | +1.142 |
disse | +1.136 |
Neg logit contributions | |
advertising | -0.986 |
��� | -0.918 |
Dresden | -0.915 |
defense | -0.880 |
education | -0.874 |
Token | a |
Token ID | 257 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
advertising | +2.524 |
Dresden | +2.386 |
��� | +2.317 |
ary | +2.270 |
education | +2.254 |
Neg logit contributions | |
anonymously | -3.028 |
orr | -2.949 |
oux | -2.849 |
church | -2.799 |
disse | -2.752 |
Token | nightmare |
Token ID | 17123 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
advertising | +1.317 |
Dresden | +1.253 |
��� | +1.215 |
ary | +1.195 |
defense | +1.194 |
Neg logit contributions | |
anonymously | -1.303 |
orr | -1.261 |
oux | -1.213 |
church | -1.183 |
disse | -1.168 |
Token | apartment |
Token ID | 7962 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
advertising | +4.443 |
Dresden | +4.309 |
ary | +4.195 |
defense | +4.047 |
education | +4.041 |
Neg logit contributions | |
anonymously | -4.852 |
orr | -4.753 |
oux | -4.575 |
church | -4.477 |
disse | -4.381 |
Token | broker |
Token ID | 20426 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
anonymously | +0.142 |
orr | +0.137 |
oux | +0.132 |
disse | +0.128 |
church | +0.128 |
Neg logit contributions | |
advertising | -0.141 |
Dresden | -0.132 |
��� | -0.131 |
education | -0.128 |
defense | -0.127 |
Token | on |
Token ID | 319 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
advertising | +1.630 |
Dresden | +1.542 |
��� | +1.498 |
ary | +1.494 |
education | +1.484 |
Neg logit contributions | |
anonymously | -1.564 |
orr | -1.513 |
oux | -1.458 |
church | -1.422 |
disse | -1.406 |
Token | Broad |
Token ID | 9765 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
advertising | +0.214 |
Dresden | +0.200 |
��� | +0.197 |
education | +0.192 |
defense | +0.192 |
Neg logit contributions | |
anonymously | -0.227 |
orr | -0.218 |
oux | -0.211 |
church | -0.205 |
disse | -0.205 |
Token | City |
Token ID | 2254 |
Feature activation | +5.88e-04 |
Pos logit contributions | |
church | +9.666 |
anonymously | +8.033 |
orr | +7.305 |
oux | +6.767 |
disse | +6.756 |
Neg logit contributions | |
��� | -16.576 |
advertising | -16.180 |
defense | -15.643 |
Dresden | -15.355 |
education | -15.304 |
Token | and |
Token ID | 290 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
advertising | +0.004 |
Dresden | +0.004 |
��� | +0.004 |
education | +0.004 |
defense | +0.004 |
Neg logit contributions | |
anonymously | -0.004 |
orr | -0.004 |
oux | -0.004 |
church | -0.003 |
disse | -0.003 |
Token | once |
Token ID | 1752 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
advertising | +2.840 |
Dresden | +2.731 |
��� | +2.600 |
ary | +2.584 |
defense | +2.562 |
Neg logit contributions | |
anonymously | -2.947 |
orr | -2.889 |
oux | -2.796 |
church | -2.729 |
disse | -2.689 |
Token | did |
Token ID | 750 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
advertising | +3.055 |
Dresden | +2.910 |
ary | +2.834 |
��� | +2.833 |
defense | +2.770 |
Neg logit contributions | |
anonymously | -2.854 |
orr | -2.832 |
oux | -2.717 |
church | -2.679 |
disse | -2.597 |
Token | cart |
Token ID | 6383 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
advertising | +3.631 |
Dresden | +3.455 |
��� | +3.315 |
ary | +3.297 |
education | +3.283 |
Neg logit contributions | |
anonymously | -3.639 |
orr | -3.532 |
oux | -3.379 |
church | -3.345 |
disse | -3.286 |
Token | including |
Token ID | 1390 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
anonymously | +0.044 |
orr | +0.043 |
oux | +0.041 |
disse | +0.040 |
church | +0.040 |
Neg logit contributions | |
advertising | -0.045 |
Dresden | -0.042 |
��� | -0.042 |
defense | -0.041 |
education | -0.041 |
Token | House |
Token ID | 2097 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
anonymously | +2.650 |
orr | +2.525 |
oux | +2.443 |
disse | +2.378 |
church | +2.376 |
Neg logit contributions | |
advertising | -2.295 |
Dresden | -2.100 |
��� | -2.100 |
education | -2.035 |
peria | -2.031 |
Token | Majority |
Token ID | 22171 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
anonymously | +5.781 |
orr | +5.136 |
oux | +4.998 |
church | +4.939 |
disse | +4.898 |
Neg logit contributions | |
advertising | -9.165 |
��� | -8.652 |
Dresden | -8.476 |
peria | -8.373 |
ebted | -8.239 |
Token | Whip |
Token ID | 40930 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
anonymously | +3.430 |
orr | +3.033 |
oux | +2.857 |
church | +2.683 |
disse | +2.608 |
Neg logit contributions | |
advertising | -8.783 |
��� | -8.296 |
Dresden | -8.204 |
education | -8.109 |
peria | -8.098 |
Token | Steve |
Token ID | 6542 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
anonymously | +1.568 |
orr | +1.472 |
oux | +1.383 |
disse | +1.325 |
church | +1.320 |
Neg logit contributions | |
advertising | -2.960 |
��� | -2.806 |
Dresden | -2.772 |
defense | -2.738 |
education | -2.724 |
Token | Scal |
Token ID | 34529 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
advertising | +1.111 |
Dresden | +1.036 |
��� | +1.023 |
education | +0.999 |
defense | +0.998 |
Neg logit contributions | |
anonymously | -1.249 |
orr | -1.201 |
oux | -1.161 |
disse | -1.133 |
church | -1.128 |
Token | ise |
Token ID | 786 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
orr | +10.340 |
oux | +10.297 |
ucci | +9.162 |
church | +8.698 |
anonymously | +8.408 |
Neg logit contributions | |
advertising | -15.266 |
Dresden | -13.752 |
��� | -13.735 |
defense | -13.658 |
ⓘ | -13.639 |
Token | ( |
Token ID | 357 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
anonymously | +3.723 |
orr | +3.563 |
oux | +3.475 |
disse | +3.292 |
church | +3.287 |
Neg logit contributions | |
advertising | -3.518 |
��� | -3.273 |
Dresden | -3.210 |
education | -3.150 |
defense | -3.139 |
Token | R |
Token ID | 49 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
anonymously | +4.502 |
orr | +4.409 |
oux | +4.275 |
church | +4.176 |
disse | +3.976 |
Neg logit contributions | |
advertising | -6.109 |
��� | -6.089 |
Dresden | -5.873 |
amily | -5.635 |
education | -5.584 |
Token | - |
Token ID | 12 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
anonymously | +2.338 |
orr | +2.270 |
oux | +2.261 |
church | +2.107 |
ucci | +2.043 |
Neg logit contributions | |
advertising | -2.616 |
��� | -2.478 |
Dresden | -2.474 |
defense | -2.398 |
education | -2.338 |
Token | La |
Token ID | 14772 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
anonymously | +5.368 |
orr | +5.169 |
oux | +5.032 |
church | +4.936 |
disse | +4.783 |
Neg logit contributions | |
advertising | -6.350 |
��� | -6.294 |
Dresden | -6.161 |
amily | -5.924 |
education | -5.876 |
Token | that |
Token ID | 326 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
advertising | +4.583 |
Dresden | +4.453 |
ary | +4.388 |
defense | +4.183 |
Morales | +4.117 |
Neg logit contributions | |
anonymously | -5.218 |
orr | -5.120 |
oux | -5.112 |
church | -4.908 |
disse | -4.875 |
Token | today |
Token ID | 1909 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
advertising | +5.107 |
Dresden | +4.982 |
ary | +4.876 |
defense | +4.675 |
Morales | +4.653 |
Neg logit contributions | |
oux | -5.434 |
anonymously | -5.421 |
orr | -5.417 |
church | -5.218 |
nect | -5.089 |
Token | 's |
Token ID | 338 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
advertising | +4.164 |
Dresden | +3.914 |
ary | +3.858 |
defense | +3.743 |
education | +3.696 |
Neg logit contributions | |
anonymously | -4.981 |
orr | -4.822 |
oux | -4.779 |
church | -4.590 |
disse | -4.571 |
Token | crash |
Token ID | 7014 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
advertising | +2.158 |
Dresden | +2.057 |
ary | +1.981 |
��� | +1.950 |
defense | +1.949 |
Neg logit contributions | |
anonymously | -2.227 |
orr | -2.170 |
oux | -2.132 |
church | -2.048 |
disse | -2.009 |
Token | will |
Token ID | 481 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
advertising | +0.689 |
Dresden | +0.646 |
ary | +0.634 |
��� | +0.626 |
defense | +0.624 |
Neg logit contributions | |
anonymously | -0.669 |
orr | -0.651 |
oux | -0.631 |
church | -0.608 |
disse | -0.604 |
Token | inaug |
Token ID | 14243 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
advertising | +3.218 |
ary | +3.154 |
Dresden | +3.121 |
defense | +3.010 |
education | +2.911 |
Neg logit contributions | |
anonymously | -3.193 |
orr | -3.192 |
oux | -3.122 |
church | -3.114 |
disse | -2.976 |
Token | urate |
Token ID | 15537 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
orr | +6.332 |
oux | +6.156 |
scribe | +5.780 |
nect | +5.432 |
urated | +5.385 |
Neg logit contributions | |
��� | -20.180 |
advertising | -17.901 |
Dresden | -17.578 |
Morales | -16.815 |
defense | -16.690 |
Token | a |
Token ID | 257 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
advertising | +0.457 |
Dresden | +0.417 |
��� | +0.412 |
education | +0.399 |
defense | +0.399 |
Neg logit contributions | |
anonymously | -0.745 |
orr | -0.721 |
oux | -0.700 |
disse | -0.684 |
church | -0.684 |
Token | bear |
Token ID | 6842 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
advertising | +4.044 |
Dresden | +3.980 |
ary | +3.880 |
defense | +3.718 |
��� | +3.702 |
Neg logit contributions | |
anonymously | -4.087 |
orr | -3.964 |
oux | -3.882 |
church | -3.748 |
disse | -3.680 |
Token | market |
Token ID | 1910 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
advertising | +2.339 |
ary | +2.186 |
Dresden | +2.094 |
defense | +2.055 |
education | +1.977 |
Neg logit contributions | |
anonymously | -5.162 |
orr | -4.920 |
oux | -4.895 |
church | -4.819 |
disse | -4.798 |
Token | like |
Token ID | 588 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
advertising | +1.332 |
Dresden | +1.254 |
ary | +1.230 |
defense | +1.213 |
education | +1.210 |
Neg logit contributions | |
anonymously | -1.236 |
orr | -1.196 |
oux | -1.158 |
church | -1.121 |
disse | -1.115 |
Token | reached |
Token ID | 4251 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
anonymously | +2.667 |
orr | +2.519 |
oux | +2.418 |
disse | +2.339 |
church | +2.314 |
Neg logit contributions | |
advertising | -3.529 |
��� | -3.325 |
Dresden | -3.303 |
defense | -3.229 |
education | -3.225 |
Token | at |
Token ID | 379 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
anonymously | +1.862 |
orr | +1.765 |
oux | +1.710 |
church | +1.651 |
disse | +1.649 |
Neg logit contributions | |
advertising | -1.904 |
��� | -1.794 |
Dresden | -1.778 |
education | -1.724 |
defense | -1.723 |
Token | j |
Token ID | 474 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
anonymously | +5.151 |
orr | +4.814 |
disse | +4.611 |
oux | +4.520 |
church | +4.411 |
Neg logit contributions | |
advertising | -6.952 |
��� | -6.625 |
Dresden | -6.466 |
peria | -6.385 |
education | -6.356 |
Token | on |
Token ID | 261 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
anonymously | +2.364 |
orr | +2.341 |
oux | +2.224 |
church | +2.206 |
disse | +2.036 |
Neg logit contributions | |
��� | -2.866 |
advertising | -2.753 |
Dresden | -2.738 |
education | -2.525 |
peria | -2.523 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
anonymously | +1.267 |
orr | +1.227 |
oux | +1.164 |
church | +1.160 |
disse | +1.118 |
Neg logit contributions | |
advertising | -1.490 |
Dresden | -1.450 |
��� | -1.446 |
defense | -1.360 |
peria | -1.358 |
Token | chest |
Token ID | 46713 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
anonymously | +1.188 |
orr | +1.154 |
oux | +1.111 |
church | +1.094 |
disse | +1.076 |
Neg logit contributions | |
advertising | -0.944 |
��� | -0.892 |
Dresden | -0.885 |
education | -0.840 |
peria | -0.838 |
Token | o |
Token ID | 78 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
orr | +8.514 |
oux | +8.508 |
anonymously | +7.475 |
ococ | +7.215 |
church | +7.166 |
Neg logit contributions | |
��� | -19.106 |
Dresden | -16.309 |
advertising | -15.353 |
contestant | -14.963 |
lance | -14.751 |
Token | @ |
Token ID | 31 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
anonymously | +4.560 |
orr | +4.292 |
oux | +4.146 |
church | +3.897 |
disse | +3.806 |
Neg logit contributions | |
advertising | -6.347 |
��� | -6.186 |
Dresden | -6.076 |
peria | -5.870 |
defense | -5.823 |
Token | gl |
Token ID | 4743 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
anonymously | +5.746 |
orr | +5.660 |
church | +5.393 |
oux | +5.343 |
disse | +5.067 |
Neg logit contributions | |
advertising | -7.916 |
��� | -7.892 |
Dresden | -7.487 |
Morales | -7.247 |
peria | -7.177 |
Token | obe |
Token ID | 5910 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
orr | +4.612 |
anonymously | +4.528 |
oux | +4.420 |
church | +4.243 |
ococ | +3.775 |
Neg logit contributions | |
��� | -8.356 |
advertising | -8.026 |
Dresden | -7.816 |
peria | -7.369 |
eanor | -7.314 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
advertising | +0.597 |
Dresden | +0.545 |
education | +0.543 |
defense | +0.539 |
ary | +0.538 |
Neg logit contributions | |
anonymously | -0.594 |
orr | -0.564 |
oux | -0.546 |
disse | -0.546 |
church | -0.531 |
Token | HA |
Token ID | 7801 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
advertising | +3.857 |
Dresden | +3.610 |
ary | +3.543 |
defense | +3.479 |
peria | +3.458 |
Neg logit contributions | |
anonymously | -3.644 |
orr | -3.490 |
oux | -3.332 |
disse | -3.332 |
church | -3.215 |
Token | W |
Token ID | 54 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
advertising | +4.077 |
Dresden | +3.852 |
ary | +3.681 |
defense | +3.665 |
education | +3.606 |
Neg logit contributions | |
anonymously | -3.805 |
orr | -3.677 |
oux | -3.516 |
disse | -3.499 |
church | -3.451 |
Token | K |
Token ID | 42 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
advertising | +3.833 |
Dresden | +3.646 |
ary | +3.557 |
education | +3.426 |
defense | +3.420 |
Neg logit contributions | |
anonymously | -3.870 |
orr | -3.694 |
oux | -3.549 |
disse | -3.527 |
church | -3.487 |
Token | AND |
Token ID | 5357 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
advertising | +1.324 |
Dresden | +1.240 |
��� | +1.205 |
ary | +1.204 |
defense | +1.197 |
Neg logit contributions | |
anonymously | -1.251 |
orr | -1.197 |
oux | -1.156 |
disse | -1.131 |
church | -1.124 |
Token | AP |
Token ID | 3486 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
advertising | +2.596 |
Dresden | +2.454 |
ary | +2.355 |
��� | +2.343 |
defense | +2.339 |
Neg logit contributions | |
anonymously | -2.182 |
orr | -2.082 |
oux | -2.014 |
disse | -1.961 |
church | -1.960 |
Token | AC |
Token ID | 2246 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
anonymously | +1.566 |
orr | +1.498 |
oux | +1.415 |
church | +1.357 |
disse | +1.337 |
Neg logit contributions | |
advertising | -2.713 |
��� | -2.593 |
Dresden | -2.585 |
education | -2.537 |
defense | -2.517 |
Token | HE |
Token ID | 13909 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
HT | +4.438 |
orr | +3.472 |
anonymously | +3.400 |
church | +3.055 |
oux | +2.710 |
Neg logit contributions | |
��� | -21.970 |
advertising | -18.231 |
Dresden | -18.055 |
contestant | -17.838 |
defense | -17.819 |
Token | T |
Token ID | 309 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
anonymously | +3.361 |
orr | +3.153 |
oux | +3.053 |
disse | +2.959 |
church | +2.911 |
Neg logit contributions | |
advertising | -4.230 |
��� | -4.054 |
education | -3.943 |
Dresden | -3.941 |
peria | -3.904 |
Token | OC |
Token ID | 4503 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
advertising | +0.448 |
Dresden | +0.404 |
ary | +0.392 |
defense | +0.386 |
education | +0.385 |
Neg logit contributions | |
anonymously | -0.635 |
orr | -0.606 |
disse | -0.589 |
oux | -0.586 |
church | -0.579 |
Token | RE |
Token ID | 4526 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
anonymously | +2.525 |
orr | +2.355 |
oux | +2.245 |
disse | +2.199 |
church | +2.152 |
Neg logit contributions | |
advertising | -3.757 |
��� | -3.607 |
Dresden | -3.547 |
education | -3.523 |
peria | -3.476 |
Token | P |
Token ID | 47 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
advertising | +1.579 |
Dresden | +1.441 |
defense | +1.395 |
ary | +1.380 |
education | +1.379 |
Neg logit contributions | |
anonymously | -1.523 |
orr | -1.449 |
disse | -1.423 |
oux | -1.418 |
church | -1.360 |
Token | no |
Token ID | 645 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
anonymously | +3.690 |
orr | +3.497 |
oux | +3.362 |
disse | +3.321 |
church | +3.252 |
Neg logit contributions | |
advertising | -4.119 |
��� | -3.832 |
Dresden | -3.813 |
education | -3.716 |
defense | -3.713 |
Token | internet |
Token ID | 5230 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
advertising | +0.463 |
Dresden | +0.431 |
defense | +0.419 |
education | +0.419 |
��� | +0.418 |
Neg logit contributions | |
anonymously | -0.424 |
orr | -0.410 |
oux | -0.391 |
church | -0.382 |
disse | -0.380 |
Token | connection |
Token ID | 4637 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
anonymously | +1.118 |
orr | +1.068 |
oux | +1.022 |
disse | +0.988 |
church | +0.987 |
Neg logit contributions | |
advertising | -1.529 |
Dresden | -1.435 |
��� | -1.423 |
education | -1.401 |
defense | -1.397 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
anonymously | +0.978 |
orr | +0.938 |
oux | +0.902 |
disse | +0.876 |
church | +0.876 |
Neg logit contributions | |
advertising | -1.059 |
Dresden | -0.989 |
��� | -0.983 |
education | -0.961 |
defense | -0.959 |
Token | but |
Token ID | 475 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
anonymously | +1.577 |
orr | +1.499 |
oux | +1.438 |
disse | +1.397 |
church | +1.392 |
Neg logit contributions | |
advertising | -1.910 |
��� | -1.796 |
Dresden | -1.786 |
education | -1.741 |
defense | -1.738 |
Token | Broad |
Token ID | 9765 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
advertising | +0.382 |
Dresden | +0.359 |
ary | +0.347 |
��� | +0.347 |
education | +0.346 |
Neg logit contributions | |
anonymously | -0.393 |
orr | -0.383 |
oux | -0.367 |
church | -0.358 |
disse | -0.356 |
Token | band |
Token ID | 3903 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
church | +7.207 |
anonymously | +7.171 |
orr | +6.917 |
nect | +6.416 |
oux | +6.395 |
Neg logit contributions | |
��� | -16.654 |
Dresden | -15.689 |
advertising | -15.091 |
ebted | -14.796 |
defense | -14.791 |
Token | Connection |
Token ID | 26923 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
anonymously | +0.870 |
orr | +0.818 |
oux | +0.774 |
disse | +0.741 |
church | +0.740 |
Neg logit contributions | |
advertising | -1.689 |
Dresden | -1.603 |
��� | -1.598 |
education | -1.566 |
defense | -1.565 |
Token | ( |
Token ID | 357 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
advertising | +1.411 |
Dresden | +1.309 |
ary | +1.290 |
education | +1.279 |
defense | +1.266 |
Neg logit contributions | |
anonymously | -1.458 |
orr | -1.416 |
oux | -1.358 |
church | -1.327 |
disse | -1.308 |
Token | Co |
Token ID | 7222 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
anonymously | +0.132 |
orr | +0.127 |
oux | +0.123 |
disse | +0.120 |
church | +0.120 |
Neg logit contributions | |
advertising | -0.124 |
Dresden | -0.115 |
��� | -0.115 |
education | -0.112 |
defense | -0.112 |
Token | ax |
Token ID | 897 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
anonymously | +1.534 |
orr | +1.481 |
oux | +1.423 |
church | +1.381 |
disse | +1.362 |
Neg logit contributions | |
advertising | -1.659 |
��� | -1.590 |
Dresden | -1.558 |
defense | -1.502 |
education | -1.498 |
Token | The |
Token ID | 383 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
anonymously | +0.645 |
orr | +0.619 |
oux | +0.593 |
church | +0.575 |
disse | +0.572 |
Neg logit contributions | |
advertising | -0.757 |
��� | -0.711 |
Dresden | -0.705 |
education | -0.691 |
peria | -0.687 |
Token | property |
Token ID | 3119 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
advertising | +2.956 |
Dresden | +2.834 |
ary | +2.710 |
��� | +2.699 |
defense | +2.697 |
Neg logit contributions | |
anonymously | -3.133 |
orr | -3.026 |
oux | -2.977 |
church | -2.852 |
disse | -2.819 |
Token | now |
Token ID | 783 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
advertising | +1.364 |
Dresden | +1.290 |
ary | +1.254 |
��� | +1.254 |
defense | +1.245 |
Neg logit contributions | |
anonymously | -1.267 |
orr | -1.229 |
oux | -1.190 |
church | -1.157 |
disse | -1.139 |
Token | belongs |
Token ID | 14448 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
advertising | +1.556 |
Dresden | +1.469 |
ary | +1.425 |
��� | +1.421 |
defense | +1.413 |
Neg logit contributions | |
anonymously | -1.485 |
orr | -1.448 |
oux | -1.399 |
church | -1.358 |
disse | -1.337 |
Token | to |
Token ID | 284 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
advertising | +0.177 |
Dresden | +0.163 |
education | +0.158 |
defense | +0.157 |
��� | +0.157 |
Neg logit contributions | |
anonymously | -0.216 |
orr | -0.210 |
oux | -0.203 |
disse | -0.199 |
church | -0.198 |
Token | Cit |
Token ID | 15792 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
anonymously | +2.436 |
orr | +2.329 |
oux | +2.239 |
church | +2.192 |
disse | +2.191 |
Neg logit contributions | |
advertising | -2.267 |
��� | -2.111 |
Dresden | -2.076 |
education | -2.041 |
peria | -2.033 |
Token | ib |
Token ID | 571 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
oux | +8.030 |
orr | +7.631 |
anonymously | +7.406 |
ucci | +7.239 |
church | +6.826 |
Neg logit contributions | |
��� | -17.329 |
Dresden | -15.274 |
advertising | -14.663 |
contestant | -14.185 |
lance | -14.162 |
Token | ank |
Token ID | 962 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
advertising | +0.256 |
Dresden | +0.229 |
ary | +0.223 |
education | +0.222 |
defense | +0.221 |
Neg logit contributions | |
anonymously | -0.449 |
orr | -0.432 |
oux | -0.419 |
disse | -0.418 |
church | -0.411 |
Token | . |
Token ID | 13 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
anonymously | +5.673 |
orr | +5.454 |
oux | +5.198 |
disse | +4.923 |
church | +4.911 |
Neg logit contributions | |
advertising | -7.131 |
��� | -6.798 |
Dresden | -6.414 |
education | -6.406 |
defense | -6.359 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
anonymously | +0.184 |
orr | +0.177 |
oux | +0.169 |
church | +0.164 |
disse | +0.164 |
Neg logit contributions | |
advertising | -0.220 |
��� | -0.206 |
Dresden | -0.205 |
education | -0.200 |
defense | -0.199 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
advertising | +0.012 |
Dresden | +0.011 |
ary | +0.011 |
education | +0.011 |
defense | +0.011 |
Neg logit contributions | |
anonymously | -0.011 |
orr | -0.010 |
oux | -0.010 |
disse | -0.010 |
church | -0.009 |
Token | ( |
Token ID | 357 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
anonymously | +0.324 |
orr | +0.310 |
oux | +0.299 |
disse | +0.290 |
church | +0.290 |
Neg logit contributions | |
advertising | -0.357 |
Dresden | -0.333 |
��� | -0.332 |
education | -0.324 |
defense | -0.323 |
Token | which |
Token ID | 4758 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
advertising | +0.095 |
Dresden | +0.088 |
��� | +0.087 |
education | +0.086 |
defense | +0.086 |
Neg logit contributions | |
anonymously | -0.090 |
orr | -0.086 |
oux | -0.083 |
disse | -0.081 |
church | -0.080 |
Token | has |
Token ID | 468 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Dresden | +5.641 |
advertising | +5.445 |
ary | +5.325 |
��� | +5.098 |
education | +4.991 |
Neg logit contributions | |
orr | -7.902 |
anonymously | -7.745 |
oux | -7.668 |
church | -7.407 |
scribe | -7.251 |
Token | the |
Token ID | 262 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
anonymously | +0.997 |
orr | +0.960 |
oux | +0.926 |
church | +0.901 |
disse | +0.899 |
Neg logit contributions | |
advertising | -0.931 |
Dresden | -0.868 |
��� | -0.861 |
education | -0.839 |
defense | -0.838 |
Token | Hyp |
Token ID | 21209 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
anonymously | +2.978 |
orr | +2.818 |
oux | +2.735 |
disse | +2.696 |
church | +2.649 |
Neg logit contributions | |
advertising | -3.210 |
��� | -2.978 |
Dresden | -2.907 |
peria | -2.900 |
education | -2.876 |
Token | ac |
Token ID | 330 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
anonymously | +1.879 |
orr | +1.835 |
oux | +1.784 |
church | +1.702 |
disse | +1.655 |
Neg logit contributions | |
advertising | -2.091 |
��� | -1.990 |
Dresden | -1.981 |
peria | -1.884 |
education | -1.879 |
Token | ros |
Token ID | 4951 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
orr | +5.338 |
oux | +4.960 |
anonymously | +4.589 |
sters | +4.159 |
church | +4.108 |
Neg logit contributions | |
��� | -19.795 |
advertising | -17.777 |
Dresden | -17.175 |
ebted | -16.774 |
contestant | -16.746 |
Token | aurus |
Token ID | 22302 |
Feature activation | +2.77e-04 |
Pos logit contributions | |
anonymously | +1.869 |
orr | +1.799 |
oux | +1.731 |
church | +1.646 |
disse | +1.625 |
Neg logit contributions | |
advertising | -2.772 |
��� | -2.694 |
Dresden | -2.642 |
education | -2.559 |
defense | -2.542 |
Token | egg |
Token ID | 5935 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
advertising | +0.002 |
Dresden | +0.002 |
��� | +0.002 |
ary | +0.002 |
education | +0.002 |
Neg logit contributions | |
anonymously | -0.002 |
orr | -0.002 |
oux | -0.002 |
church | -0.002 |
disse | -0.002 |
Token | ) |
Token ID | 8 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
anonymously | +2.832 |
orr | +2.702 |
oux | +2.627 |
disse | +2.568 |
church | +2.552 |
Neg logit contributions | |
advertising | -2.636 |
��� | -2.472 |
Dresden | -2.412 |
peria | -2.357 |
defense | -2.349 |
Token | into |
Token ID | 656 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
advertising | +2.510 |
Dresden | +2.408 |
��� | +2.316 |
education | +2.311 |
ary | +2.302 |
Neg logit contributions | |
anonymously | -2.394 |
orr | -2.359 |
oux | -2.256 |
church | -2.197 |
disse | -2.167 |
Token | ag |
Token ID | 363 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
advertising | +0.987 |
Dresden | +0.906 |
��� | +0.894 |
education | +0.892 |
defense | +0.884 |
Neg logit contributions | |
anonymously | -1.057 |
orr | -1.009 |
oux | -0.975 |
disse | -0.962 |
church | -0.953 |
Token | ression |
Token ID | 2234 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
advertising | +0.413 |
Dresden | +0.384 |
education | +0.378 |
ary | +0.377 |
��� | +0.376 |
Neg logit contributions | |
anonymously | -0.365 |
orr | -0.343 |
oux | -0.329 |
disse | -0.325 |
church | -0.323 |
Token | de |
Token ID | 390 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
anonymously | +0.448 |
orr | +0.428 |
oux | +0.410 |
church | +0.399 |
disse | +0.398 |
Neg logit contributions | |
advertising | -0.538 |
Dresden | -0.505 |
��� | -0.501 |
education | -0.491 |
defense | -0.490 |
Token | t |
Token ID | 256 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
advertising | +0.179 |
Dresden | +0.169 |
��� | +0.167 |
education | +0.163 |
ary | +0.163 |
Neg logit contributions | |
anonymously | -0.156 |
orr | -0.149 |
oux | -0.143 |
church | -0.140 |
disse | -0.138 |
Token | out |
Token ID | 448 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
anonymously | +3.183 |
orr | +3.123 |
oux | +3.049 |
disse | +2.887 |
church | +2.885 |
Neg logit contributions | |
advertising | -3.673 |
��� | -3.517 |
Dresden | -3.483 |
defense | -3.345 |
education | -3.331 |
Token | cit |
Token ID | 15433 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
anonymously | +5.810 |
orr | +5.439 |
oux | +5.376 |
disse | +5.226 |
church | +4.959 |
Neg logit contributions | |
advertising | -6.699 |
��� | -6.406 |
Dresden | -6.353 |
defense | -6.212 |
peria | -6.133 |
Token | oy |
Token ID | 726 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
oux | +12.058 |
anonymously | +11.970 |
orr | +11.693 |
ucci | +10.996 |
disse | +10.952 |
Neg logit contributions | |
��� | -10.809 |
advertising | -10.730 |
Dresden | -10.193 |
defense | -9.592 |
eanor | -9.443 |
Token | en |
Token ID | 268 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
advertising | +0.172 |
Dresden | +0.161 |
��� | +0.159 |
education | +0.158 |
ary | +0.157 |
Neg logit contributions | |
anonymously | -0.144 |
orr | -0.137 |
oux | -0.131 |
church | -0.128 |
disse | -0.128 |
Token | Imp |
Token ID | 9855 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
anonymously | +3.762 |
orr | +3.591 |
oux | +3.495 |
disse | +3.388 |
church | +3.304 |
Neg logit contributions | |
advertising | -4.397 |
��� | -4.180 |
Dresden | -4.103 |
education | -4.019 |
defense | -4.017 |
Token | é |
Token ID | 2634 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
anonymously | +1.196 |
orr | +1.150 |
oux | +1.111 |
church | +1.069 |
disse | +1.069 |
Neg logit contributions | |
advertising | -1.370 |
Dresden | -1.286 |
��� | -1.284 |
education | -1.248 |
defense | -1.248 |
Token | rial |
Token ID | 4454 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
anonymously | +0.205 |
orr | +0.195 |
oux | +0.188 |
disse | +0.183 |
church | +0.183 |
Neg logit contributions | |
advertising | -0.228 |
Dresden | -0.213 |
��� | -0.211 |
defense | -0.207 |
education | -0.207 |
Token | h |
Token ID | 71 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
anonymously | +1.530 |
orr | +1.498 |
oux | +1.449 |
church | +1.427 |
disse | +1.403 |
Neg logit contributions | |
advertising | -0.893 |
��� | -0.836 |
Dresden | -0.834 |
peria | -0.789 |
defense | -0.770 |
Token | iking |
Token ID | 14132 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
anonymously | +2.696 |
orr | +2.669 |
oux | +2.573 |
church | +2.474 |
disse | +2.427 |
Neg logit contributions | |
advertising | -2.483 |
��� | -2.432 |
Dresden | -2.322 |
defense | -2.237 |
peria | -2.216 |
Token | � |
Token ID | 447 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
anonymously | +0.738 |
orr | +0.709 |
oux | +0.682 |
disse | +0.666 |
church | +0.665 |
Neg logit contributions | |
advertising | -0.732 |
Dresden | -0.684 |
��� | -0.672 |
education | -0.663 |
ary | -0.662 |
Token | � |
Token ID | 247 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
anonymously | +1.053 |
orr | +1.026 |
oux | +0.997 |
church | +0.980 |
disse | +0.978 |
Neg logit contributions | |
advertising | -0.410 |
Dresden | -0.360 |
��� | -0.355 |
education | -0.339 |
defense | -0.337 |
Token | s |
Token ID | 82 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
anonymously | +0.736 |
orr | +0.708 |
oux | +0.681 |
church | +0.662 |
disse | +0.660 |
Neg logit contributions | |
advertising | -0.748 |
��� | -0.697 |
Dresden | -0.696 |
education | -0.674 |
defense | -0.672 |
Token | holy |
Token ID | 11386 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
anonymously | +3.185 |
orr | +3.060 |
oux | +2.982 |
church | +2.871 |
disse | +2.856 |
Neg logit contributions | |
advertising | -3.265 |
��� | -3.064 |
Dresden | -3.012 |
education | -2.935 |
defense | -2.932 |
Token | gra |
Token ID | 7933 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
oux | +8.857 |
anonymously | +8.550 |
church | +8.401 |
orr | +8.213 |
disse | +7.475 |
Neg logit contributions | |
��� | -15.130 |
advertising | -13.512 |
peria | -12.922 |
ebted | -12.909 |
Morales | -12.825 |
Token | il |
Token ID | 346 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
advertising | +0.093 |
Dresden | +0.087 |
��� | +0.086 |
education | +0.084 |
defense | +0.084 |
Neg logit contributions | |
anonymously | -0.101 |
orr | -0.097 |
oux | -0.093 |
disse | -0.091 |
church | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
advertising | +2.178 |
Dresden | +2.044 |
ary | +1.997 |
education | +1.987 |
defense | +1.984 |
Neg logit contributions | |
anonymously | -2.066 |
orr | -1.996 |
oux | -1.914 |
disse | -1.877 |
church | -1.850 |
Token | In |
Token ID | 554 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
anonymously | +0.748 |
orr | +0.718 |
oux | +0.695 |
disse | +0.678 |
church | +0.676 |
Neg logit contributions | |
advertising | -0.678 |
Dresden | -0.632 |
��� | -0.621 |
education | -0.609 |
defense | -0.607 |
Token | Chicago |
Token ID | 4842 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
anonymously | +2.423 |
orr | +2.335 |
oux | +2.260 |
church | +2.204 |
disse | +2.198 |
Neg logit contributions | |
advertising | -2.025 |
��� | -1.886 |
Dresden | -1.832 |
defense | -1.803 |
education | -1.801 |
Token | with |
Token ID | 351 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
anonymously | +1.854 |
orr | +1.758 |
oux | +1.694 |
church | +1.640 |
disse | +1.637 |
Neg logit contributions | |
advertising | -2.128 |
��� | -2.009 |
Dresden | -2.000 |
education | -1.933 |
peria | -1.932 |
Token | him |
Token ID | 683 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
anonymously | +3.218 |
orr | +3.048 |
oux | +2.919 |
disse | +2.859 |
church | +2.828 |
Neg logit contributions | |
advertising | -3.814 |
��� | -3.585 |
Dresden | -3.577 |
education | -3.476 |
defense | -3.475 |
Token | . |
Token ID | 13 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
advertising | +0.709 |
Dresden | +0.662 |
��� | +0.649 |
education | +0.643 |
ary | +0.643 |
Neg logit contributions | |
anonymously | -0.664 |
orr | -0.644 |
oux | -0.619 |
church | -0.603 |
disse | -0.602 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
anonymously | +0.515 |
orr | +0.494 |
oux | +0.477 |
disse | +0.465 |
church | +0.463 |
Neg logit contributions | |
advertising | -0.530 |
Dresden | -0.495 |
��� | -0.487 |
education | -0.479 |
defense | -0.478 |
Token | S |
Token ID | 50 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
anonymously | +0.248 |
orr | +0.238 |
oux | +0.230 |
disse | +0.224 |
church | +0.224 |
Neg logit contributions | |
advertising | -0.235 |
Dresden | -0.219 |
��� | -0.217 |
education | -0.212 |
defense | -0.211 |
Token | AC |
Token ID | 2246 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
anonymously | +0.932 |
orr | +0.900 |
oux | +0.868 |
church | +0.841 |
disse | +0.840 |
Neg logit contributions | |
advertising | -0.909 |
��� | -0.847 |
Dresden | -0.847 |
education | -0.819 |
defense | -0.819 |
Token | RAM |
Token ID | 24115 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
anonymously | +10.717 |
orr | +10.408 |
oux | +9.901 |
church | +9.851 |
HT | +9.694 |
Neg logit contributions | |
advertising | -12.664 |
��� | -12.161 |
ebted | -11.895 |
defense | -11.490 |
Dresden | -11.292 |
Token | ENT |
Token ID | 3525 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
anonymously | +4.021 |
orr | +3.744 |
oux | +3.341 |
church | +3.240 |
disse | +3.103 |
Neg logit contributions | |
advertising | -11.831 |
��� | -11.586 |
education | -11.389 |
defense | -11.254 |
lance | -11.217 |
Token | O |
Token ID | 46 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
anonymously | +0.089 |
orr | +0.086 |
oux | +0.083 |
disse | +0.081 |
church | +0.081 |
Neg logit contributions | |
advertising | -0.072 |
Dresden | -0.066 |
��� | -0.065 |
ary | -0.064 |
education | -0.064 |
Token | — |
Token ID | 851 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
anonymously | +3.327 |
orr | +3.143 |
oux | +3.037 |
church | +2.997 |
disse | +2.938 |
Neg logit contributions | |
advertising | -3.294 |
��� | -3.089 |
Dresden | -3.051 |
education | -2.967 |
defense | -2.950 |
Token | Thousands |
Token ID | 30405 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
advertising | +1.581 |
Dresden | +1.466 |
defense | +1.404 |
education | +1.399 |
��� | +1.396 |
Neg logit contributions | |
anonymously | -1.842 |
orr | -1.794 |
oux | -1.736 |
disse | -1.702 |
church | -1.687 |
Token | :// |
Token ID | 1378 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
anonymously | +3.516 |
orr | +3.443 |
oux | +3.207 |
church | +3.076 |
nect | +2.887 |
Neg logit contributions | |
��� | -5.720 |
advertising | -5.197 |
Dresden | -5.088 |
peria | -4.984 |
ebted | -4.963 |
Token | t |
Token ID | 83 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
orr | +4.267 |
anonymously | +4.164 |
oux | +3.908 |
church | +3.725 |
nect | +3.465 |
Neg logit contributions | |
��� | -11.994 |
Dresden | -10.682 |
advertising | -10.424 |
peria | -10.205 |
ebted | -10.174 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
orr | +4.831 |
anonymously | +4.815 |
oux | +4.559 |
church | +4.348 |
ucci | +4.045 |
Neg logit contributions | |
��� | -9.342 |
advertising | -7.734 |
Dresden | -7.650 |
peria | -7.496 |
ebted | -7.384 |
Token | co |
Token ID | 1073 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
orr | +5.993 |
anonymously | +5.630 |
oux | +5.479 |
church | +5.295 |
ste | +5.034 |
Neg logit contributions | |
��� | -12.159 |
Dresden | -10.244 |
advertising | -10.043 |
amily | -9.855 |
ebted | -9.746 |
Token | / |
Token ID | 14 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
anonymously | +3.796 |
orr | +3.717 |
oux | +3.470 |
church | +3.372 |
nect | +3.154 |
Neg logit contributions | |
��� | -5.893 |
advertising | -5.339 |
Dresden | -5.122 |
peria | -5.059 |
amily | -5.045 |
Token | l |
Token ID | 75 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
orr | +6.806 |
anonymously | +6.546 |
oux | +6.534 |
church | +6.324 |
kef | +5.984 |
Neg logit contributions | |
��� | -6.997 |
advertising | -6.784 |
Dresden | -6.550 |
education | -6.150 |
peria | -6.126 |
Token | g |
Token ID | 70 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
orr | +10.961 |
oux | +10.586 |
church | +10.270 |
HT | +10.083 |
anonymously | +10.003 |
Neg logit contributions | |
��� | -12.379 |
advertising | -10.948 |
Dresden | -10.936 |
ebted | -10.313 |
education | -10.098 |
Token | S |
Token ID | 50 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
orr | +8.888 |
oux | +8.646 |
church | +8.317 |
anonymously | +8.315 |
HT | +8.002 |
Neg logit contributions | |
��� | -9.890 |
advertising | -9.119 |
Dresden | -8.930 |
ebted | -8.499 |
education | -8.402 |
Token | wh |
Token ID | 1929 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
orr | +5.126 |
anonymously | +5.031 |
oux | +4.973 |
church | +4.775 |
disse | +4.563 |
Neg logit contributions | |
��� | -5.319 |
advertising | -5.314 |
Dresden | -5.027 |
education | -4.786 |
ebted | -4.780 |
Token | X |
Token ID | 55 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
orr | +6.270 |
anonymously | +6.083 |
oux | +6.032 |
church | +5.842 |
kef | +5.511 |
Neg logit contributions | |
��� | -6.461 |
advertising | -6.321 |
Dresden | -6.075 |
education | -5.739 |
ebted | -5.719 |
Token | Um |
Token ID | 37280 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
anonymously | +2.308 |
orr | +2.258 |
oux | +2.177 |
church | +2.112 |
disse | +2.079 |
Neg logit contributions | |
advertising | -2.297 |
��� | -2.186 |
Dresden | -2.159 |
education | -2.077 |
defense | -2.071 |
Token | through |
Token ID | 832 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
anonymously | +6.034 |
orr | +5.873 |
church | +5.486 |
oux | +5.421 |
nect | +5.300 |
Neg logit contributions | |
advertising | -7.990 |
��� | -7.505 |
Dresden | -7.434 |
peria | -7.238 |
ebted | -7.196 |
Token | a |
Token ID | 257 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
anonymously | +7.306 |
orr | +6.863 |
disse | +6.596 |
oux | +6.560 |
church | +6.417 |
Neg logit contributions | |
advertising | -6.469 |
��� | -6.063 |
Dresden | -5.808 |
peria | -5.769 |
ebted | -5.690 |
Token | ridiculous |
Token ID | 11441 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
anonymously | +4.975 |
orr | +4.614 |
disse | +4.412 |
oux | +4.392 |
church | +4.292 |
Neg logit contributions | |
advertising | -6.076 |
��� | -5.659 |
Dresden | -5.493 |
peria | -5.437 |
education | -5.426 |
Token | and |
Token ID | 290 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
anonymously | +4.893 |
orr | +4.507 |
disse | +4.341 |
oux | +4.333 |
church | +4.220 |
Neg logit contributions | |
advertising | -5.941 |
��� | -5.664 |
Dresden | -5.424 |
peria | -5.384 |
ebted | -5.339 |
Token | unpopular |
Token ID | 24166 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
anonymously | +4.094 |
orr | +3.763 |
disse | +3.597 |
oux | +3.594 |
church | +3.471 |
Neg logit contributions | |
advertising | -4.982 |
��� | -4.666 |
Dresden | -4.597 |
peria | -4.585 |
defense | -4.533 |
Token | bill |
Token ID | 2855 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
anonymously | +7.141 |
orr | +6.375 |
disse | +6.356 |
oux | +6.213 |
church | +5.968 |
Neg logit contributions | |
advertising | -10.044 |
��� | -9.758 |
peria | -9.154 |
Dresden | -9.086 |
lance | -9.019 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
anonymously | +10.444 |
orr | +9.026 |
disse | +8.544 |
oux | +8.223 |
church | +8.148 |
Neg logit contributions | |
��� | -13.461 |
advertising | -13.144 |
peria | -12.528 |
eanor | -12.239 |
amily | -12.224 |
Token | just |
Token ID | 655 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
anonymously | +7.519 |
orr | +6.902 |
oux | +6.712 |
church | +6.605 |
disse | +6.534 |
Neg logit contributions | |
advertising | -7.524 |
��� | -7.289 |
peria | -6.652 |
education | -6.624 |
ebted | -6.622 |
Token | two |
Token ID | 734 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
anonymously | +6.293 |
orr | +5.808 |
oux | +5.518 |
disse | +5.448 |
church | +5.432 |
Neg logit contributions | |
advertising | -5.827 |
��� | -5.535 |
ebted | -5.240 |
Dresden | -5.230 |
education | -5.227 |
Token | weeks |
Token ID | 2745 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
anonymously | +1.661 |
orr | +1.580 |
oux | +1.518 |
disse | +1.487 |
church | +1.478 |
Neg logit contributions | |
advertising | -1.791 |
��� | -1.682 |
Dresden | -1.674 |
education | -1.631 |
defense | -1.622 |
Token | ? |
Token ID | 30 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
anonymously | +6.470 |
orr | +6.067 |
oux | +5.361 |
disse | +5.302 |
church | +5.174 |
Neg logit contributions | |
��� | -10.367 |
advertising | -10.137 |
peria | -9.734 |
Dresden | -9.691 |
amily | -9.434 |
Token | , |
Token ID | 11 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
anonymously | +1.317 |
orr | +1.259 |
oux | +1.210 |
disse | +1.177 |
church | +1.174 |
Neg logit contributions | |
advertising | -1.470 |
Dresden | -1.372 |
��� | -1.368 |
education | -1.336 |
defense | -1.333 |
Token | above |
Token ID | 2029 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
advertising | +2.900 |
Dresden | +2.742 |
ary | +2.676 |
defense | +2.610 |
education | +2.606 |
Neg logit contributions | |
anonymously | -3.127 |
orr | -3.102 |
oux | -3.069 |
church | -2.966 |
disse | -2.907 |
Token | all |
Token ID | 477 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
advertising | +2.925 |
Dresden | +2.636 |
education | +2.548 |
ary | +2.546 |
��� | +2.519 |
Neg logit contributions | |
anonymously | -4.707 |
orr | -4.567 |
oux | -4.533 |
disse | -4.382 |
church | -4.364 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
anonymously | +1.279 |
orr | +1.216 |
oux | +1.160 |
disse | +1.119 |
church | +1.118 |
Neg logit contributions | |
advertising | -1.899 |
Dresden | -1.791 |
��� | -1.785 |
education | -1.747 |
defense | -1.744 |
Token | an |
Token ID | 281 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
anonymously | +1.035 |
orr | +0.991 |
oux | +0.954 |
disse | +0.928 |
church | +0.926 |
Neg logit contributions | |
advertising | -1.098 |
Dresden | -1.024 |
��� | -1.020 |
education | -0.995 |
defense | -0.993 |
Token | uncons |
Token ID | 13962 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
anonymously | +1.832 |
orr | +1.742 |
oux | +1.681 |
disse | +1.632 |
church | +1.623 |
Neg logit contributions | |
advertising | -1.934 |
Dresden | -1.806 |
��� | -1.796 |
peria | -1.759 |
defense | -1.758 |
Token | c |
Token ID | 66 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
orr | +7.844 |
anonymously | +7.286 |
oux | +7.112 |
ucci | +6.891 |
nect | +6.887 |
Neg logit contributions | |
��� | -15.233 |
Dresden | -14.408 |
advertising | -14.098 |
peria | -13.957 |
lance | -13.572 |
Token | ion |
Token ID | 295 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
anonymously | +4.183 |
orr | +4.006 |
oux | +3.865 |
ococ | +3.547 |
church | +3.527 |
Neg logit contributions | |
��� | -9.165 |
advertising | -8.457 |
Dresden | -8.265 |
peria | -8.094 |
Morales | -8.013 |
Token | able |
Token ID | 540 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
anonymously | +3.639 |
orr | +3.550 |
oux | +3.408 |
church | +3.249 |
disse | +3.182 |
Neg logit contributions | |
advertising | -4.873 |
��� | -4.789 |
Dresden | -4.690 |
defense | -4.517 |
peria | -4.501 |
Token | gift |
Token ID | 6979 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
anonymously | +1.513 |
orr | +1.445 |
oux | +1.389 |
disse | +1.355 |
church | +1.349 |
Neg logit contributions | |
advertising | -1.672 |
��� | -1.562 |
Dresden | -1.559 |
education | -1.519 |
defense | -1.515 |
Token | to |
Token ID | 284 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
anonymously | +4.685 |
orr | +4.472 |
oux | +4.176 |
church | +4.133 |
disse | +4.095 |
Neg logit contributions | |
advertising | -5.221 |
��� | -4.974 |
Dresden | -4.869 |
peria | -4.815 |
education | -4.744 |
Token | flavor |
Token ID | 9565 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
anonymously | +1.585 |
orr | +1.519 |
oux | +1.462 |
church | +1.418 |
disse | +1.417 |
Neg logit contributions | |
advertising | -1.739 |
Dresden | -1.631 |
��� | -1.613 |
education | -1.580 |
defense | -1.579 |
Token | begins |
Token ID | 6140 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
anonymously | +2.093 |
orr | +2.001 |
oux | +1.923 |
disse | +1.873 |
church | +1.861 |
Neg logit contributions | |
advertising | -2.300 |
��� | -2.161 |
Dresden | -2.147 |
defense | -2.085 |
peria | -2.083 |
Token | with |
Token ID | 351 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
advertising | +2.464 |
Dresden | +2.339 |
ary | +2.284 |
��� | +2.265 |
defense | +2.254 |
Neg logit contributions | |
anonymously | -2.127 |
orr | -2.081 |
oux | -1.989 |
church | -1.945 |
disse | -1.922 |
Token | dried |
Token ID | 16577 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
advertising | +0.486 |
Dresden | +0.452 |
��� | +0.442 |
defense | +0.432 |
education | +0.432 |
Neg logit contributions | |
anonymously | -0.650 |
orr | -0.626 |
oux | -0.608 |
church | -0.592 |
disse | -0.591 |
Token | apr |
Token ID | 46593 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
advertising | +3.907 |
Dresden | +3.780 |
ary | +3.643 |
education | +3.551 |
defense | +3.534 |
Neg logit contributions | |
anonymously | -3.944 |
orr | -3.750 |
oux | -3.658 |
church | -3.487 |
disse | -3.465 |
Token | ic |
Token ID | 291 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
anonymously | +3.447 |
orr | +3.422 |
oux | +3.281 |
church | +3.118 |
disse | +3.079 |
Neg logit contributions | |
advertising | -2.667 |
��� | -2.557 |
Dresden | -2.508 |
education | -2.402 |
defense | -2.371 |
Token | ot |
Token ID | 313 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
oux | +5.248 |
orr | +5.246 |
anonymously | +4.873 |
church | +4.107 |
ococ | +4.064 |
Neg logit contributions | |
advertising | -17.759 |
Dresden | -17.272 |
lance | -16.791 |
eanor | -16.672 |
��� | -16.644 |
Token | , |
Token ID | 11 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
anonymously | +3.856 |
orr | +3.718 |
oux | +3.525 |
church | +3.424 |
disse | +3.411 |
Neg logit contributions | |
advertising | -4.988 |
��� | -4.760 |
Dresden | -4.646 |
peria | -4.601 |
defense | -4.567 |
Token | banana |
Token ID | 25996 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
anonymously | +2.507 |
orr | +2.388 |
oux | +2.289 |
disse | +2.229 |
church | +2.220 |
Neg logit contributions | |
advertising | -2.941 |
��� | -2.774 |
Dresden | -2.723 |
education | -2.671 |
peria | -2.670 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
anonymously | +4.428 |
orr | +4.402 |
oux | +4.023 |
disse | +3.957 |
church | +3.900 |
Neg logit contributions | |
advertising | -7.288 |
��� | -6.985 |
Dresden | -6.777 |
peria | -6.752 |
education | -6.737 |
Token | and |
Token ID | 290 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
anonymously | +1.146 |
orr | +1.099 |
oux | +1.052 |
church | +1.023 |
disse | +1.022 |
Neg logit contributions | |
advertising | -1.358 |
��� | -1.271 |
Dresden | -1.266 |
education | -1.235 |
defense | -1.234 |
Token | might |
Token ID | 1244 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
advertising | +2.970 |
ary | +2.770 |
Dresden | +2.764 |
education | +2.689 |
��� | +2.654 |
Neg logit contributions | |
anonymously | -2.733 |
orr | -2.696 |
oux | -2.606 |
church | -2.489 |
disse | -2.482 |
Token | become |
Token ID | 1716 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
advertising | +2.050 |
Dresden | +1.966 |
ary | +1.949 |
defense | +1.897 |
education | +1.890 |
Neg logit contributions | |
anonymously | -1.616 |
orr | -1.605 |
oux | -1.544 |
church | -1.541 |
disse | -1.462 |
Token | worthless |
Token ID | 28063 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
anonymously | +1.457 |
orr | +1.393 |
oux | +1.340 |
disse | +1.307 |
church | +1.300 |
Neg logit contributions | |
advertising | -1.488 |
Dresden | -1.383 |
��� | -1.383 |
education | -1.348 |
defense | -1.343 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
anonymously | +0.798 |
orr | +0.761 |
oux | +0.732 |
disse | +0.711 |
church | +0.709 |
Neg logit contributions | |
advertising | -0.896 |
��� | -0.841 |
Dresden | -0.838 |
education | -0.816 |
defense | -0.814 |
Token | The |
Token ID | 383 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
anonymously | +1.745 |
orr | +1.675 |
oux | +1.611 |
church | +1.569 |
disse | +1.562 |
Neg logit contributions | |
advertising | -1.689 |
��� | -1.593 |
Dresden | -1.568 |
education | -1.530 |
defense | -1.528 |
Token | gap |
Token ID | 7625 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
anonymously | +1.810 |
orr | +1.723 |
oux | +1.656 |
disse | +1.613 |
church | +1.609 |
Neg logit contributions | |
advertising | -2.059 |
��� | -1.926 |
Dresden | -1.912 |
education | -1.869 |
defense | -1.868 |
Token | was |
Token ID | 373 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
anonymously | +8.893 |
orr | +8.041 |
oux | +7.477 |
church | +7.329 |
disse | +7.328 |
Neg logit contributions | |
��� | -13.933 |
advertising | -13.818 |
amily | -12.782 |
defense | -12.766 |
peria | -12.742 |
Token | filled |
Token ID | 5901 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
anonymously | +5.624 |
orr | +5.182 |
oux | +4.989 |
disse | +4.869 |
church | +4.720 |
Neg logit contributions | |
advertising | -8.110 |
��� | -7.638 |
Dresden | -7.457 |
peria | -7.391 |
defense | -7.382 |
Token | by |
Token ID | 416 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
anonymously | +2.849 |
orr | +2.692 |
oux | +2.615 |
church | +2.538 |
disse | +2.537 |
Neg logit contributions | |
advertising | -2.645 |
��� | -2.482 |
Dresden | -2.433 |
defense | -2.383 |
education | -2.373 |
Token | , |
Token ID | 11 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
anonymously | +1.379 |
orr | +1.320 |
oux | +1.270 |
disse | +1.240 |
church | +1.236 |
Neg logit contributions | |
advertising | -1.307 |
��� | -1.218 |
Dresden | -1.209 |
education | -1.177 |
defense | -1.176 |
Token | among |
Token ID | 1871 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
anonymously | +2.940 |
orr | +2.749 |
oux | +2.604 |
disse | +2.526 |
church | +2.514 |
Neg logit contributions | |
advertising | -3.750 |
��� | -3.591 |
Dresden | -3.516 |
peria | -3.466 |
education | -3.428 |
Token |
|
Token ID | 198 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
advertising | +1.263 |
Dresden | +1.191 |
ary | +1.140 |
education | +1.137 |
defense | +1.133 |
Neg logit contributions | |
anonymously | -1.298 |
orr | -1.244 |
oux | -1.207 |
disse | -1.174 |
church | -1.169 |
Token |
|
Token ID | 198 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
advertising | +2.911 |
ary | +2.632 |
Dresden | +2.629 |
education | +2.541 |
defense | +2.536 |
Neg logit contributions | |
anonymously | -3.240 |
disse | -3.092 |
orr | -3.078 |
oux | -3.011 |
church | -2.923 |
Token | Be |
Token ID | 3856 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
advertising | +3.184 |
Dresden | +2.758 |
ary | +2.756 |
education | +2.748 |
defense | +2.728 |
Neg logit contributions | |
anonymously | -3.956 |
orr | -3.730 |
oux | -3.659 |
disse | -3.635 |
church | -3.482 |
Token | that |
Token ID | 326 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
advertising | +6.912 |
��� | +6.487 |
Dresden | +6.469 |
ary | +6.411 |
education | +6.354 |
Neg logit contributions | |
anonymously | -7.336 |
orr | -6.514 |
oux | -6.493 |
disse | -6.419 |
church | -6.382 |
Token | as |
Token ID | 355 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
anonymously | +1.116 |
orr | +1.077 |
oux | +1.044 |
disse | +1.020 |
church | +1.019 |
Neg logit contributions | |
advertising | -0.798 |
Dresden | -0.733 |
��� | -0.728 |
education | -0.706 |
defense | -0.704 |
Token | it |
Token ID | 340 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
anonymously | +6.106 |
orr | +5.693 |
oux | +5.036 |
church | +4.700 |
HT | +4.620 |
Neg logit contributions | |
��� | -13.025 |
ebted | -12.288 |
advertising | -12.253 |
amily | -12.009 |
Dresden | -11.689 |
Token | may |
Token ID | 743 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
anonymously | +8.137 |
orr | +7.112 |
oux | +6.261 |
ucci | +6.258 |
then | +6.104 |
Neg logit contributions | |
��� | -16.810 |
peria | -14.876 |
advertising | -14.648 |
ebted | -14.472 |
amily | -14.160 |
Token | , |
Token ID | 11 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
anonymously | +5.193 |
orr | +4.727 |
oux | +4.407 |
disse | +4.297 |
church | +4.090 |
Neg logit contributions | |
advertising | -10.586 |
peria | -9.943 |
��� | -9.916 |
Dresden | -9.904 |
defense | -9.892 |
Token | there |
Token ID | 612 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
advertising | +3.474 |
Dresden | +3.295 |
ary | +3.122 |
��� | +3.118 |
education | +3.110 |
Neg logit contributions | |
anonymously | -4.059 |
orr | -3.992 |
oux | -3.830 |
church | -3.753 |
nect | -3.627 |
Token | seems |
Token ID | 2331 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
advertising | +2.169 |
Dresden | +2.004 |
��� | +1.972 |
ary | +1.969 |
education | +1.958 |
Neg logit contributions | |
anonymously | -2.098 |
orr | -2.027 |
oux | -1.969 |
church | -1.909 |
disse | -1.897 |
Token | to |
Token ID | 284 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
advertising | +1.843 |
Dresden | +1.736 |
��� | +1.704 |
ary | +1.684 |
education | +1.676 |
Neg logit contributions | |
anonymously | -1.696 |
orr | -1.645 |
oux | -1.580 |
church | -1.536 |
disse | -1.528 |
Token |
|
Token ID | 198 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
anonymously | +1.182 |
orr | +1.137 |
oux | +1.096 |
disse | +1.066 |
church | +1.066 |
Neg logit contributions | |
advertising | -1.132 |
Dresden | -1.050 |
��� | -1.048 |
education | -1.020 |
defense | -1.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
advertising | +1.644 |
Dresden | +1.507 |
ary | +1.498 |
education | +1.464 |
defense | +1.463 |
Neg logit contributions | |
anonymously | -1.676 |
orr | -1.592 |
disse | -1.565 |
oux | -1.548 |
church | -1.504 |
Token | If |
Token ID | 1532 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
advertising | +1.219 |
Dresden | +1.108 |
ary | +1.089 |
defense | +1.087 |
education | +1.086 |
Neg logit contributions | |
anonymously | -1.385 |
orr | -1.313 |
oux | -1.280 |
disse | -1.257 |
church | -1.232 |
Token | we |
Token ID | 356 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
advertising | +4.844 |
Dresden | +4.691 |
ary | +4.582 |
defense | +4.397 |
��� | +4.388 |
Neg logit contributions | |
anonymously | -5.779 |
orr | -5.587 |
oux | -5.473 |
church | -5.321 |
disse | -5.297 |
Token | simply |
Token ID | 2391 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
advertising | +3.016 |
Dresden | +2.884 |
ary | +2.836 |
��� | +2.823 |
defense | +2.766 |
Neg logit contributions | |
anonymously | -2.627 |
orr | -2.499 |
oux | -2.487 |
church | -2.464 |
disse | -2.325 |
Token | want |
Token ID | 765 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
advertising | +1.663 |
Dresden | +1.600 |
ary | +1.560 |
��� | +1.548 |
defense | +1.525 |
Neg logit contributions | |
anonymously | -1.515 |
orr | -1.470 |
oux | -1.443 |
church | -1.415 |
disse | -1.356 |
Token | to |
Token ID | 284 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
ary | +6.856 |
advertising | +6.799 |
Dresden | +6.681 |
��� | +6.364 |
defense | +6.253 |
Neg logit contributions | |
anonymously | -9.588 |
oux | -9.392 |
orr | -9.360 |
church | -9.055 |
disse | -9.014 |
Token | write |
Token ID | 3551 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
advertising | +2.855 |
Dresden | +2.783 |
ary | +2.767 |
defense | +2.621 |
��� | +2.598 |
Neg logit contributions | |
anonymously | -3.127 |
orr | -3.113 |
oux | -3.095 |
church | -3.011 |
disse | -2.904 |
Token | an |
Token ID | 281 |
Feature activation | -8.78e-03 |
Pos logit contributions | |
advertising | +5.046 |
Dresden | +5.027 |
ary | +4.849 |
��� | +4.688 |
defense | +4.686 |
Neg logit contributions | |
orr | -6.380 |
anonymously | -6.347 |
oux | -6.327 |
church | -6.103 |
kef | -5.890 |
Token | Own |
Token ID | 11744 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
anonymously | +0.057 |
orr | +0.055 |
oux | +0.053 |
church | +0.051 |
disse | +0.051 |
Neg logit contributions | |
advertising | -0.063 |
Dresden | -0.059 |
��� | -0.058 |
education | -0.057 |
ary | -0.057 |
Token | ed |
Token ID | 276 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
anonymously | +1.516 |
orr | +1.457 |
oux | +1.411 |
disse | +1.382 |
church | +1.376 |
Neg logit contributions | |
advertising | -1.048 |
��� | -0.964 |
Dresden | -0.958 |
education | -0.924 |
defense | -0.922 |
Token | start |
Token ID | 923 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
anonymously | +1.837 |
orr | +1.740 |
oux | +1.646 |
disse | +1.601 |
church | +1.561 |
Neg logit contributions | |
advertising | -3.453 |
��� | -3.313 |
Dresden | -3.259 |
education | -3.197 |
peria | -3.196 |
Token | , |
Token ID | 11 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
anonymously | +1.138 |
orr | +1.091 |
oux | +1.050 |
disse | +1.019 |
church | +1.019 |
Neg logit contributions | |
advertising | -1.244 |
Dresden | -1.163 |
��� | -1.154 |
education | -1.129 |
defense | -1.127 |
Token | after |
Token ID | 706 |
Feature activation | +7.05e-02 |
Pos logit contributions | |
advertising | +2.418 |
Dresden | +2.302 |
defense | +2.215 |
ary | +2.208 |
education | +2.189 |
Neg logit contributions | |
anonymously | -1.958 |
orr | -1.928 |
oux | -1.865 |
church | -1.796 |
disse | -1.761 |
Token | Ibrahim |
Token ID | 30917 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
advertising | +0.476 |
Dresden | +0.446 |
��� | +0.436 |
defense | +0.431 |
education | +0.429 |
Neg logit contributions | |
anonymously | -0.482 |
orr | -0.468 |
oux | -0.450 |
church | -0.438 |
disse | -0.436 |
Token | 's |
Token ID | 338 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
advertising | +1.939 |
Dresden | +1.853 |
��� | +1.786 |
ary | +1.786 |
defense | +1.757 |
Neg logit contributions | |
anonymously | -1.948 |
orr | -1.929 |
oux | -1.855 |
church | -1.837 |
disse | -1.789 |
Token | lawyers |
Token ID | 9326 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
advertising | +1.165 |
Dresden | +1.096 |
��� | +1.063 |
defense | +1.061 |
education | +1.052 |
Neg logit contributions | |
anonymously | -1.114 |
orr | -1.090 |
oux | -1.047 |
church | -1.015 |
disse | -1.007 |
Token | informed |
Token ID | 7981 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
advertising | +7.190 |
Dresden | +7.173 |
ary | +6.827 |
defense | +6.592 |
Morales | +6.525 |
Neg logit contributions | |
orr | -7.810 |
church | -7.744 |
oux | -7.503 |
anonymously | -7.332 |
nect | -7.197 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
anonymously | +0.830 |
orr | +0.797 |
oux | +0.769 |
disse | +0.748 |
church | +0.747 |
Neg logit contributions | |
advertising | -0.806 |
Dresden | -0.750 |
��� | -0.746 |
education | -0.727 |
defense | -0.726 |
Token | DOJ |
Token ID | 27055 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
advertising | +0.827 |
Dresden | +0.786 |
��� | +0.760 |
defense | +0.754 |
education | +0.746 |
Neg logit contributions | |
anonymously | -0.884 |
orr | -0.861 |
oux | -0.827 |
disse | -0.803 |
church | -0.801 |
Token | that |
Token ID | 326 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
anonymously | +3.540 |
orr | +3.326 |
oux | +3.182 |
disse | +3.097 |
church | +3.059 |
Neg logit contributions | |
advertising | -4.273 |
��� | -4.012 |
Dresden | -3.953 |
education | -3.922 |
ebted | -3.867 |
Token | they |
Token ID | 484 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
anonymously | +1.337 |
orr | +1.279 |
oux | +1.230 |
disse | +1.195 |
church | +1.193 |
Neg logit contributions | |
advertising | -1.485 |
Dresden | -1.388 |
��� | -1.383 |
education | -1.351 |
defense | -1.346 |
Token | . |
Token ID | 13 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
advertising | +4.348 |
ary | +3.909 |
Dresden | +3.772 |
education | +3.720 |
defense | +3.690 |
Neg logit contributions | |
anonymously | -5.502 |
disse | -5.352 |
orr | -5.261 |
oux | -5.170 |
church | -5.052 |
Token | S |
Token ID | 50 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
advertising | +4.138 |
Dresden | +3.672 |
ary | +3.579 |
defense | +3.504 |
education | +3.464 |
Neg logit contributions | |
anonymously | -4.653 |
disse | -4.500 |
orr | -4.392 |
oux | -4.374 |
church | -4.219 |
Token | ., |
Token ID | 1539 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
anonymously | +0.409 |
orr | +0.391 |
oux | +0.377 |
disse | +0.364 |
church | +0.364 |
Neg logit contributions | |
advertising | -0.406 |
Dresden | -0.377 |
��� | -0.377 |
education | -0.365 |
defense | -0.365 |
Token | also |
Token ID | 635 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
advertising | +5.595 |
Dresden | +5.533 |
ary | +5.255 |
defense | +5.147 |
education | +5.060 |
Neg logit contributions | |
orr | -5.890 |
anonymously | -5.765 |
oux | -5.750 |
church | -5.644 |
disse | -5.491 |
Token | dropped |
Token ID | 5710 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
advertising | +4.061 |
Dresden | +3.936 |
ary | +3.887 |
defense | +3.718 |
��� | +3.703 |
Neg logit contributions | |
orr | -4.087 |
anonymously | -4.030 |
oux | -4.015 |
church | -3.981 |
ococ | -3.795 |
Token | nearly |
Token ID | 3016 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
advertising | +3.379 |
Dresden | +3.257 |
ary | +3.172 |
defense | +3.039 |
education | +2.969 |
Neg logit contributions | |
orr | -3.813 |
anonymously | -3.716 |
oux | -3.691 |
church | -3.579 |
disse | -3.543 |
Token | 3 |
Token ID | 513 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
advertising | +6.651 |
Dresden | +6.641 |
ary | +6.560 |
defense | +5.921 |
Morales | +5.915 |
Neg logit contributions | |
orr | -10.487 |
oux | -10.228 |
ucci | -10.040 |
church | -9.972 |
ococ | -9.947 |
Token | percent |
Token ID | 1411 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
advertising | +2.917 |
Dresden | +2.658 |
ary | +2.633 |
defense | +2.575 |
education | +2.530 |
Neg logit contributions | |
anonymously | -4.722 |
orr | -4.666 |
oux | -4.609 |
disse | -4.505 |
church | -4.497 |
Token | on |
Token ID | 319 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
advertising | +4.163 |
Dresden | +3.924 |
ary | +3.886 |
defense | +3.795 |
peria | +3.723 |
Neg logit contributions | |
orr | -4.610 |
anonymously | -4.591 |
oux | -4.467 |
disse | -4.376 |
church | -4.301 |
Token | the |
Token ID | 262 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
advertising | +0.347 |
Dresden | +0.325 |
��� | +0.319 |
defense | +0.314 |
education | +0.314 |
Neg logit contributions | |
anonymously | -0.329 |
orr | -0.317 |
oux | -0.306 |
church | -0.296 |
disse | -0.295 |
Token | news |
Token ID | 1705 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
anonymously | +0.434 |
orr | +0.417 |
oux | +0.402 |
church | +0.390 |
disse | +0.389 |
Neg logit contributions | |
advertising | -0.501 |
Dresden | -0.470 |
��� | -0.465 |
education | -0.456 |
defense | -0.455 |
Token | need |
Token ID | 761 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
anonymously | +3.192 |
orr | +3.037 |
oux | +2.912 |
disse | +2.854 |
church | +2.817 |
Neg logit contributions | |
advertising | -3.555 |
��� | -3.323 |
Dresden | -3.297 |
education | -3.226 |
defense | -3.210 |
Token | it |
Token ID | 340 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
advertising | +1.418 |
Dresden | +1.323 |
��� | +1.306 |
defense | +1.287 |
ary | +1.284 |
Neg logit contributions | |
anonymously | -1.382 |
orr | -1.327 |
oux | -1.275 |
church | -1.247 |
disse | -1.240 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
advertising | +0.920 |
Dresden | +0.861 |
��� | +0.843 |
ary | +0.834 |
education | +0.833 |
Neg logit contributions | |
anonymously | -0.905 |
orr | -0.871 |
oux | -0.841 |
church | -0.822 |
disse | -0.817 |
Token |
|
Token ID | 198 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
anonymously | +1.762 |
orr | +1.692 |
oux | +1.630 |
disse | +1.585 |
church | +1.584 |
Neg logit contributions | |
advertising | -1.770 |
Dresden | -1.648 |
��� | -1.641 |
education | -1.600 |
defense | -1.597 |
Token |
|
Token ID | 198 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
anonymously | +0.441 |
orr | +0.420 |
oux | +0.405 |
disse | +0.398 |
church | +0.393 |
Neg logit contributions | |
advertising | -0.499 |
Dresden | -0.465 |
education | -0.452 |
ary | -0.452 |
defense | -0.451 |
Token | RA |
Token ID | 3861 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
anonymously | +0.524 |
orr | +0.503 |
oux | +0.485 |
disse | +0.473 |
church | +0.471 |
Neg logit contributions | |
advertising | -0.509 |
Dresden | -0.472 |
��� | -0.468 |
education | -0.459 |
defense | -0.458 |
Token | ID |
Token ID | 2389 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
advertising | +6.558 |
defense | +6.003 |
Dresden | +5.975 |
education | +5.966 |
peria | +5.871 |
Neg logit contributions | |
anonymously | -7.417 |
orr | -7.255 |
oux | -6.846 |
disse | -6.802 |
church | -6.781 |
Token | 4 |
Token ID | 19 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
advertising | +2.477 |
Dresden | +2.334 |
��� | +2.277 |
defense | +2.273 |
education | +2.261 |
Neg logit contributions | |
anonymously | -2.328 |
orr | -2.216 |
oux | -2.135 |
church | -2.106 |
disse | -2.084 |
Token | on |
Token ID | 319 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
anonymously | +3.042 |
orr | +2.920 |
oux | +2.819 |
disse | +2.736 |
church | +2.721 |
Neg logit contributions | |
advertising | -3.132 |
��� | -2.926 |
Dresden | -2.904 |
education | -2.822 |
defense | -2.810 |
Token | tape |
Token ID | 9154 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
advertising | +0.606 |
Dresden | +0.572 |
��� | +0.560 |
education | +0.553 |
ary | +0.551 |
Neg logit contributions | |
anonymously | -0.583 |
orr | -0.561 |
oux | -0.539 |
church | -0.526 |
disse | -0.522 |
Token | . |
Token ID | 764 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
advertising | +0.420 |
Dresden | +0.391 |
��� | +0.386 |
education | +0.380 |
defense | +0.380 |
Neg logit contributions | |
anonymously | -0.420 |
orr | -0.403 |
oux | -0.388 |
church | -0.381 |
disse | -0.377 |
Token | The |
Token ID | 464 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
advertising | +2.065 |
Dresden | +1.843 |
education | +1.827 |
ary | +1.815 |
defense | +1.810 |
Neg logit contributions | |
anonymously | -2.334 |
orr | -2.235 |
oux | -2.180 |
disse | -2.173 |
church | -2.080 |
Token | flyer |
Token ID | 42464 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
advertising | +2.877 |
Dresden | +2.774 |
ary | +2.641 |
��� | +2.636 |
education | +2.626 |
Neg logit contributions | |
anonymously | -2.488 |
orr | -2.470 |
oux | -2.374 |
disse | -2.309 |
church | -2.291 |
Token | shows |
Token ID | 2523 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
advertising | +3.785 |
Dresden | +3.677 |
ary | +3.581 |
education | +3.461 |
defense | +3.407 |
Neg logit contributions | |
orr | -3.633 |
anonymously | -3.559 |
oux | -3.509 |
church | -3.429 |
disse | -3.345 |
Token | a |
Token ID | 257 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
advertising | +3.901 |
Dresden | +3.801 |
ary | +3.510 |
education | +3.486 |
��� | +3.450 |
Neg logit contributions | |
orr | -5.027 |
anonymously | -4.941 |
oux | -4.847 |
church | -4.623 |
disse | -4.598 |
Token | newspaper |
Token ID | 7533 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
advertising | +2.872 |
Dresden | +2.796 |
��� | +2.664 |
ary | +2.639 |
education | +2.614 |
Neg logit contributions | |
orr | -2.827 |
anonymously | -2.826 |
oux | -2.709 |
church | -2.585 |
disse | -2.585 |
Token | headline |
Token ID | 16534 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
advertising | +7.114 |
Dresden | +6.880 |
ary | +6.849 |
contestant | +6.649 |
education | +6.512 |
Neg logit contributions | |
orr | -8.057 |
oux | -7.915 |
anonymously | -7.543 |
kef | -7.467 |
church | -7.410 |
Token | taken |
Token ID | 2077 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
advertising | +7.244 |
Dresden | +7.242 |
ary | +7.183 |
Morales | +6.682 |
education | +6.600 |
Neg logit contributions | |
orr | -7.972 |
oux | -7.892 |
church | -7.442 |
nect | -7.435 |
anonymously | -7.393 |
Token | from |
Token ID | 422 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
advertising | +5.036 |
Dresden | +4.968 |
ary | +4.798 |
education | +4.547 |
defense | +4.531 |
Neg logit contributions | |
orr | -6.298 |
oux | -5.868 |
church | -5.856 |
nect | -5.782 |
anonymously | -5.732 |
Token | the |
Token ID | 262 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
advertising | +2.624 |
Dresden | +2.469 |
��� | +2.340 |
education | +2.326 |
ary | +2.304 |
Neg logit contributions | |
anonymously | -3.634 |
orr | -3.611 |
oux | -3.488 |
disse | -3.406 |
church | -3.391 |
Token | National |
Token ID | 2351 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
advertising | +2.478 |
Dresden | +2.383 |
��� | +2.259 |
education | +2.256 |
ary | +2.248 |
Neg logit contributions | |
anonymously | -2.469 |
orr | -2.462 |
oux | -2.358 |
disse | -2.305 |
church | -2.273 |
Token | Post |
Token ID | 2947 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
advertising | +1.798 |
Dresden | +1.730 |
ary | +1.683 |
education | +1.662 |
��� | +1.656 |
Neg logit contributions | |
anonymously | -1.359 |
orr | -1.334 |
oux | -1.287 |
disse | -1.256 |
church | -1.216 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
anonymously | +0.001 |
orr | +0.001 |
oux | +0.001 |
disse | +0.001 |
church | +0.001 |
Neg logit contributions | |
advertising | -0.002 |
Dresden | -0.002 |
��� | -0.002 |
ary | -0.002 |
education | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
anonymously | +1.289 |
orr | +1.234 |
oux | +1.182 |
church | +1.146 |
disse | +1.141 |
Neg logit contributions | |
advertising | -1.556 |
��� | -1.472 |
Dresden | -1.461 |
education | -1.421 |
defense | -1.419 |
Token | Materials |
Token ID | 41657 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
advertising | +0.774 |
Dresden | +0.705 |
education | +0.689 |
defense | +0.688 |
ary | +0.685 |
Neg logit contributions | |
anonymously | -0.857 |
orr | -0.818 |
oux | -0.793 |
disse | -0.783 |
church | -0.767 |
Token |
|
Token ID | 198 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
advertising | +3.184 |
Dresden | +3.003 |
education | +2.924 |
ary | +2.911 |
��� | +2.899 |
Neg logit contributions | |
anonymously | -2.879 |
orr | -2.779 |
oux | -2.659 |
church | -2.567 |
disse | -2.551 |
Token |
|
Token ID | 198 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
advertising | +2.686 |
Dresden | +2.442 |
ary | +2.438 |
education | +2.374 |
defense | +2.366 |
Neg logit contributions | |
anonymously | -2.938 |
disse | -2.809 |
orr | -2.797 |
oux | -2.735 |
church | -2.644 |
Token | . |
Token ID | 13 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
advertising | +4.748 |
education | +4.230 |
defense | +4.196 |
ary | +4.188 |
Dresden | +4.185 |
Neg logit contributions | |
anonymously | -5.472 |
orr | -5.144 |
disse | -5.067 |
oux | -5.009 |
church | -4.792 |
Token |
|
Token ID | 198 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
advertising | +5.118 |
Dresden | +4.853 |
defense | +4.714 |
ary | +4.706 |
��� | +4.702 |
Neg logit contributions | |
anonymously | -4.903 |
orr | -4.673 |
disse | -4.514 |
oux | -4.475 |
church | -4.356 |
Token |
|
Token ID | 198 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
advertising | +0.692 |
Dresden | +0.640 |
ary | +0.627 |
education | +0.622 |
defense | +0.620 |
Neg logit contributions | |
anonymously | -0.661 |
orr | -0.630 |
disse | -0.610 |
oux | -0.610 |
church | -0.592 |
Token | ( |
Token ID | 7 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
advertising | +4.852 |
Dresden | +4.439 |
education | +4.355 |
ary | +4.346 |
defense | +4.341 |
Neg logit contributions | |
anonymously | -5.291 |
orr | -5.005 |
disse | -4.861 |
oux | -4.842 |
church | -4.690 |
Token | Vis |
Token ID | 15854 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
advertising | +1.585 |
Dresden | +1.463 |
education | +1.429 |
��� | +1.426 |
ary | +1.423 |
Neg logit contributions | |
anonymously | -1.635 |
orr | -1.567 |
oux | -1.512 |
disse | -1.487 |
church | -1.464 |
Token | ited |
Token ID | 863 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
advertising | +0.914 |
Dresden | +0.834 |
��� | +0.827 |
ary | +0.812 |
peria | +0.809 |
Neg logit contributions | |
anonymously | -1.330 |
orr | -1.301 |
oux | -1.252 |
church | -1.240 |
disse | -1.231 |
Token | Y |
Token ID | 56 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
advertising | +0.143 |
Dresden | +0.133 |
��� | +0.132 |
education | +0.130 |
defense | +0.129 |
Neg logit contributions | |
anonymously | -0.147 |
orr | -0.141 |
oux | -0.136 |
disse | -0.133 |
church | -0.132 |
Token | alk |
Token ID | 971 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
advertising | +4.314 |
ary | +3.990 |
peria | +3.963 |
Dresden | +3.924 |
education | +3.917 |
Neg logit contributions | |
anonymously | -4.639 |
orr | -4.196 |
disse | -4.188 |
oux | -4.108 |
church | -4.054 |
Token | ut |
Token ID | 315 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
advertising | +2.062 |
Dresden | +1.914 |
ary | +1.889 |
education | +1.867 |
defense | +1.860 |
Neg logit contributions | |
anonymously | -2.635 |
orr | -2.483 |
oux | -2.407 |
disse | -2.398 |
church | -2.377 |
Token | Tal |
Token ID | 7193 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
advertising | +1.678 |
Dresden | +1.583 |
ary | +1.554 |
��� | +1.549 |
defense | +1.537 |
Neg logit contributions | |
anonymously | -1.624 |
orr | -1.538 |
oux | -1.486 |
church | -1.464 |
disse | -1.453 |
Token | mud |
Token ID | 41650 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
advertising | +1.404 |
Dresden | +1.318 |
ary | +1.295 |
��� | +1.294 |
defense | +1.290 |
Neg logit contributions | |
anonymously | -1.201 |
orr | -1.139 |
oux | -1.091 |
disse | -1.073 |
church | -1.058 |
Token | Torah |
Token ID | 33366 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
advertising | +3.067 |
Dresden | +2.965 |
ary | +2.929 |
��� | +2.886 |
defense | +2.847 |
Neg logit contributions | |
anonymously | -2.788 |
orr | -2.654 |
oux | -2.572 |
church | -2.510 |
disse | -2.481 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
advertising | +1.769 |
Dresden | +1.691 |
��� | +1.659 |
ary | +1.641 |
education | +1.629 |
Neg logit contributions | |
anonymously | -1.673 |
orr | -1.596 |
oux | -1.546 |
church | -1.503 |
disse | -1.493 |
Token | � |
Token ID | 447 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
advertising | +0.849 |
Dresden | +0.807 |
��� | +0.794 |
education | +0.776 |
defense | +0.774 |
Neg logit contributions | |
anonymously | -0.812 |
orr | -0.783 |
oux | -0.758 |
church | -0.735 |
disse | -0.732 |
Token | � |
Token ID | 251 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
anonymously | +3.556 |
orr | +3.458 |
oux | +3.301 |
church | +3.260 |
disse | +3.212 |
Neg logit contributions | |
advertising | -2.976 |
Dresden | -2.731 |
peria | -2.668 |
education | -2.660 |
defense | -2.635 |
Token | Genesis |
Token ID | 18993 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
anonymously | +0.314 |
orr | +0.301 |
oux | +0.290 |
disse | +0.282 |
church | +0.282 |
Neg logit contributions | |
advertising | -0.324 |
Dresden | -0.303 |
��� | -0.301 |
education | -0.294 |
defense | -0.293 |
Token | , |
Token ID | 11 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
advertising | +0.329 |
Dresden | +0.305 |
��� | +0.301 |
education | +0.293 |
defense | +0.292 |
Neg logit contributions | |
anonymously | -0.436 |
orr | -0.420 |
oux | -0.407 |
disse | -0.398 |
church | -0.397 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
advertising | +1.129 |
Dresden | +1.060 |
��� | +1.030 |
ary | +1.020 |
defense | +1.014 |
Neg logit contributions | |
anonymously | -1.379 |
orr | -1.327 |
oux | -1.283 |
church | -1.259 |
disse | -1.256 |
Token | point |
Token ID | 966 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
anonymously | +1.601 |
orr | +1.526 |
oux | +1.458 |
disse | +1.421 |
church | +1.415 |
Neg logit contributions | |
advertising | -2.026 |
��� | -1.895 |
Dresden | -1.887 |
education | -1.847 |
peria | -1.844 |
Token | where |
Token ID | 810 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
anonymously | +2.234 |
orr | +2.140 |
oux | +2.045 |
disse | +2.009 |
church | +2.006 |
Neg logit contributions | |
advertising | -2.060 |
��� | -1.918 |
Dresden | -1.896 |
peria | -1.853 |
education | -1.848 |
Token | this |
Token ID | 428 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
advertising | +1.629 |
Dresden | +1.537 |
ary | +1.483 |
education | +1.476 |
��� | +1.474 |
Neg logit contributions | |
anonymously | -1.663 |
orr | -1.618 |
oux | -1.574 |
church | -1.527 |
disse | -1.503 |
Token | sort |
Token ID | 3297 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
advertising | +0.186 |
Dresden | +0.174 |
��� | +0.171 |
education | +0.168 |
defense | +0.168 |
Neg logit contributions | |
anonymously | -0.188 |
orr | -0.182 |
oux | -0.176 |
church | -0.171 |
disse | -0.170 |
Token | of |
Token ID | 286 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
advertising | +2.178 |
Dresden | +1.967 |
ary | +1.934 |
education | +1.927 |
defense | +1.915 |
Neg logit contributions | |
anonymously | -2.717 |
orr | -2.618 |
oux | -2.539 |
disse | -2.511 |
church | -2.467 |
Token | comparison |
Token ID | 7208 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
advertising | +1.118 |
Dresden | +1.054 |
��� | +1.029 |
education | +1.016 |
ary | +1.015 |
Neg logit contributions | |
anonymously | -1.014 |
orr | -0.984 |
oux | -0.955 |
church | -0.922 |
disse | -0.909 |
Token | works |
Token ID | 2499 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
anonymously | +0.774 |
orr | +0.742 |
oux | +0.715 |
church | +0.694 |
disse | +0.693 |
Neg logit contributions | |
advertising | -0.833 |
Dresden | -0.778 |
��� | -0.773 |
education | -0.756 |
defense | -0.755 |
Token | more |
Token ID | 517 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
advertising | +0.819 |
Dresden | +0.771 |
ary | +0.751 |
education | +0.742 |
defense | +0.742 |
Neg logit contributions | |
anonymously | -0.772 |
orr | -0.757 |
oux | -0.735 |
church | -0.710 |
disse | -0.696 |
Token | as |
Token ID | 355 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
anonymously | +1.743 |
orr | +1.657 |
oux | +1.581 |
disse | +1.549 |
church | +1.541 |
Neg logit contributions | |
advertising | -1.985 |
��� | -1.857 |
Dresden | -1.853 |
education | -1.803 |
peria | -1.798 |
Token | a |
Token ID | 257 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
advertising | +3.625 |
Dresden | +3.264 |
ary | +3.181 |
education | +3.180 |
defense | +3.158 |
Neg logit contributions | |
anonymously | -5.933 |
orr | -5.897 |
oux | -5.717 |
church | -5.554 |
disse | -5.506 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
anonymously | +0.029 |
orr | +0.028 |
oux | +0.027 |
church | +0.026 |
disse | +0.026 |
Neg logit contributions | |
advertising | -0.032 |
Dresden | -0.030 |
��� | -0.029 |
ary | -0.029 |
education | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
advertising | +0.745 |
Dresden | +0.688 |
ary | +0.677 |
education | +0.670 |
defense | +0.669 |
Neg logit contributions | |
anonymously | -0.715 |
orr | -0.680 |
oux | -0.662 |
disse | -0.661 |
church | -0.641 |
Token | With |
Token ID | 3152 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
advertising | +0.894 |
Dresden | +0.808 |
education | +0.802 |
defense | +0.800 |
ary | +0.798 |
Neg logit contributions | |
anonymously | -0.945 |
orr | -0.898 |
oux | -0.875 |
disse | -0.859 |
church | -0.840 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
advertising | +0.904 |
Dresden | +0.849 |
��� | +0.833 |
ary | +0.824 |
education | +0.820 |
Neg logit contributions | |
anonymously | -0.931 |
orr | -0.899 |
oux | -0.862 |
church | -0.843 |
disse | -0.836 |
Token | console |
Token ID | 8624 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
advertising | +0.772 |
Dresden | +0.714 |
��� | +0.692 |
ary | +0.688 |
education | +0.684 |
Neg logit contributions | |
anonymously | -1.077 |
orr | -1.048 |
oux | -1.011 |
church | -0.990 |
disse | -0.979 |
Token | method |
Token ID | 2446 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
anonymously | +1.407 |
orr | +1.319 |
oux | +1.248 |
disse | +1.210 |
church | +1.192 |
Neg logit contributions | |
advertising | -2.505 |
Dresden | -2.377 |
��� | -2.376 |
education | -2.320 |
defense | -2.315 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
advertising | +2.662 |
Dresden | +2.512 |
ary | +2.478 |
��� | +2.452 |
defense | +2.442 |
Neg logit contributions | |
anonymously | -2.096 |
orr | -2.027 |
oux | -1.962 |
church | -1.915 |
disse | -1.872 |
Token | you |
Token ID | 345 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
advertising | +0.711 |
Dresden | +0.665 |
��� | +0.650 |
ary | +0.647 |
education | +0.644 |
Neg logit contributions | |
anonymously | -0.693 |
orr | -0.672 |
oux | -0.647 |
church | -0.632 |
disse | -0.626 |
Token | have |
Token ID | 423 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
anonymously | +1.799 |
orr | +1.712 |
oux | +1.634 |
disse | +1.583 |
church | +1.578 |
Neg logit contributions | |
advertising | -2.482 |
Dresden | -2.334 |
��� | -2.327 |
education | -2.276 |
defense | -2.271 |
Token | to |
Token ID | 284 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
advertising | +0.291 |
Dresden | +0.270 |
��� | +0.268 |
education | +0.261 |
defense | +0.261 |
Neg logit contributions | |
anonymously | -0.327 |
orr | -0.316 |
oux | -0.305 |
church | -0.297 |
disse | -0.297 |
Token | go |
Token ID | 467 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
advertising | +3.352 |
Dresden | +3.214 |
ary | +3.204 |
defense | +3.121 |
education | +3.092 |
Neg logit contributions | |
anonymously | -3.178 |
orr | -3.133 |
oux | -3.112 |
church | -3.039 |
disse | -2.921 |
Token | had |
Token ID | 550 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
anonymously | +1.289 |
orr | +1.233 |
oux | +1.185 |
disse | +1.149 |
church | +1.149 |
Neg logit contributions | |
advertising | -1.468 |
Dresden | -1.373 |
��� | -1.367 |
education | -1.335 |
defense | -1.333 |
Token | known |
Token ID | 1900 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
anonymously | +0.505 |
orr | +0.487 |
oux | +0.469 |
church | +0.454 |
disse | +0.453 |
Neg logit contributions | |
advertising | -0.576 |
Dresden | -0.542 |
��� | -0.536 |
education | -0.525 |
defense | -0.524 |
Token | about |
Token ID | 546 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
advertising | +0.187 |
Dresden | +0.176 |
��� | +0.173 |
ary | +0.171 |
education | +0.170 |
Neg logit contributions | |
anonymously | -0.151 |
orr | -0.146 |
oux | -0.140 |
disse | -0.135 |
church | -0.135 |
Token | his |
Token ID | 465 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
anonymously | +2.965 |
orr | +2.824 |
oux | +2.715 |
church | +2.648 |
disse | +2.637 |
Neg logit contributions | |
advertising | -3.346 |
��� | -3.142 |
Dresden | -3.114 |
defense | -3.060 |
peria | -3.048 |
Token | actions |
Token ID | 4028 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
anonymously | +1.189 |
orr | +1.140 |
oux | +1.097 |
disse | +1.065 |
church | +1.065 |
Neg logit contributions | |
advertising | -1.278 |
Dresden | -1.194 |
��� | -1.187 |
education | -1.160 |
defense | -1.158 |
Token | and |
Token ID | 290 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
anonymously | +2.269 |
orr | +2.132 |
oux | +2.048 |
disse | +1.991 |
church | +1.988 |
Neg logit contributions | |
advertising | -2.560 |
��� | -2.422 |
Dresden | -2.383 |
education | -2.327 |
defense | -2.324 |
Token | had |
Token ID | 550 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
advertising | +1.257 |
Dresden | +1.191 |
��� | +1.158 |
education | +1.155 |
ary | +1.154 |
Neg logit contributions | |
anonymously | -1.107 |
orr | -1.103 |
oux | -1.063 |
church | -1.016 |
disse | -1.002 |
Token | taken |
Token ID | 2077 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
anonymously | +0.373 |
orr | +0.364 |
oux | +0.351 |
church | +0.338 |
disse | +0.337 |
Neg logit contributions | |
advertising | -0.424 |
Dresden | -0.400 |
��� | -0.394 |
ary | -0.387 |
education | -0.387 |
Token | steps |
Token ID | 4831 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
advertising | +1.235 |
Dresden | +1.170 |
��� | +1.139 |
defense | +1.134 |
education | +1.133 |
Neg logit contributions | |
anonymously | -1.121 |
orr | -1.108 |
oux | -1.061 |
church | -1.025 |
disse | -1.024 |
Token | to |
Token ID | 284 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
anonymously | +1.378 |
orr | +1.311 |
oux | +1.264 |
church | +1.234 |
disse | +1.233 |
Neg logit contributions | |
advertising | -1.271 |
��� | -1.185 |
Dresden | -1.180 |
education | -1.145 |
defense | -1.140 |
Token | get |
Token ID | 651 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
anonymously | +1.250 |
orr | +1.202 |
oux | +1.159 |
church | +1.125 |
disse | +1.123 |
Neg logit contributions | |
advertising | -1.355 |
Dresden | -1.268 |
��� | -1.257 |
education | -1.232 |
defense | -1.230 |
Token |
|
Token ID | 198 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
advertising | +0.417 |
Dresden | +0.392 |
��� | +0.378 |
defense | +0.376 |
ary | +0.375 |
Neg logit contributions | |
anonymously | -0.430 |
orr | -0.414 |
oux | -0.398 |
disse | -0.392 |
church | -0.390 |
Token |
|
Token ID | 198 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
anonymously | +0.548 |
orr | +0.524 |
oux | +0.504 |
disse | +0.493 |
church | +0.488 |
Neg logit contributions | |
advertising | -0.632 |
Dresden | -0.590 |
��� | -0.575 |
education | -0.574 |
defense | -0.573 |
Token | Dead |
Token ID | 20489 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
advertising | +0.306 |
Dresden | +0.282 |
��� | +0.275 |
defense | +0.275 |
education | +0.274 |
Neg logit contributions | |
anonymously | -0.308 |
orr | -0.295 |
oux | -0.284 |
disse | -0.279 |
church | -0.276 |
Token | line |
Token ID | 1370 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
advertising | +2.939 |
Dresden | +2.688 |
ary | +2.673 |
defense | +2.625 |
��� | +2.609 |
Neg logit contributions | |
anonymously | -3.069 |
orr | -2.962 |
oux | -2.909 |
disse | -2.796 |
church | -2.767 |
Token | for |
Token ID | 329 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
anonymously | +0.537 |
orr | +0.513 |
oux | +0.491 |
church | +0.476 |
disse | +0.476 |
Neg logit contributions | |
advertising | -0.701 |
Dresden | -0.659 |
��� | -0.653 |
education | -0.641 |
defense | -0.640 |
Token | Clubs |
Token ID | 48901 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
advertising | +3.195 |
Dresden | +3.047 |
��� | +2.922 |
defense | +2.921 |
ary | +2.886 |
Neg logit contributions | |
anonymously | -3.049 |
orr | -3.007 |
oux | -2.874 |
church | -2.851 |
disse | -2.750 |
Token | to |
Token ID | 284 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
anonymously | +1.294 |
orr | +1.237 |
oux | +1.192 |
disse | +1.159 |
church | +1.155 |
Neg logit contributions | |
advertising | -1.315 |
��� | -1.226 |
Dresden | -1.223 |
education | -1.193 |
defense | -1.190 |
Token | ask |
Token ID | 1265 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
advertising | +3.063 |
Dresden | +2.995 |
��� | +2.877 |
ary | +2.858 |
defense | +2.829 |
Neg logit contributions | |
anonymously | -3.612 |
orr | -3.589 |
oux | -3.494 |
church | -3.492 |
disse | -3.342 |
Token | Players |
Token ID | 13094 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
advertising | +2.491 |
Dresden | +2.386 |
defense | +2.271 |
ary | +2.271 |
��� | +2.249 |
Neg logit contributions | |
anonymously | -2.423 |
orr | -2.408 |
oux | -2.292 |
church | -2.261 |
disse | -2.205 |
Token | with |
Token ID | 351 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
advertising | +0.795 |
Dresden | +0.742 |
��� | +0.728 |
ary | +0.714 |
defense | +0.713 |
Neg logit contributions | |
anonymously | -0.892 |
orr | -0.866 |
oux | -0.834 |
church | -0.815 |
disse | -0.810 |
Token | " |
Token ID | 366 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
advertising | +2.159 |
Dresden | +2.026 |
��� | +1.997 |
ary | +1.964 |
defense | +1.947 |
Neg logit contributions | |
anonymously | -2.394 |
orr | -2.316 |
oux | -2.236 |
church | -2.199 |
disse | -2.155 |
Token | , |
Token ID | 11 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
advertising | +1.138 |
Dresden | +1.077 |
��� | +1.063 |
education | +1.052 |
ary | +1.044 |
Neg logit contributions | |
anonymously | -0.859 |
orr | -0.826 |
oux | -0.785 |
disse | -0.763 |
church | -0.762 |
Token | Ground |
Token ID | 13706 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
advertising | +2.332 |
Dresden | +2.268 |
education | +2.178 |
��� | +2.154 |
ary | +2.145 |
Neg logit contributions | |
anonymously | -2.482 |
orr | -2.469 |
oux | -2.341 |
church | -2.293 |
disse | -2.255 |
Token | Zero |
Token ID | 12169 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
anonymously | +0.109 |
orr | +0.104 |
oux | +0.100 |
disse | +0.098 |
church | +0.097 |
Neg logit contributions | |
advertising | -0.111 |
Dresden | -0.104 |
��� | -0.103 |
education | -0.101 |
defense | -0.101 |
Token | for |
Token ID | 329 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
advertising | +0.774 |
Dresden | +0.732 |
education | +0.718 |
��� | +0.718 |
defense | +0.713 |
Neg logit contributions | |
anonymously | -0.719 |
orr | -0.702 |
oux | -0.670 |
disse | -0.647 |
church | -0.644 |
Token | social |
Token ID | 1919 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
advertising | +2.045 |
Dresden | +1.953 |
education | +1.912 |
��� | +1.903 |
defense | +1.876 |
Neg logit contributions | |
anonymously | -1.992 |
orr | -1.951 |
oux | -1.873 |
church | -1.812 |
disse | -1.800 |
Token | justice |
Token ID | 5316 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
anonymously | +4.974 |
orr | +4.584 |
disse | +4.399 |
oux | +4.344 |
church | +4.344 |
Neg logit contributions | |
advertising | -5.396 |
��� | -5.168 |
Dresden | -5.039 |
peria | -5.009 |
ebted | -4.812 |
Token | brain |
Token ID | 3632 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
anonymously | +0.902 |
orr | +0.866 |
oux | +0.833 |
church | +0.808 |
disse | +0.807 |
Neg logit contributions | |
advertising | -1.000 |
Dresden | -0.935 |
��� | -0.929 |
education | -0.911 |
defense | -0.908 |
Token | washing |
Token ID | 38524 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
anonymously | +5.900 |
orr | +5.692 |
disse | +5.312 |
oux | +5.263 |
church | +5.153 |
Neg logit contributions | |
advertising | -6.861 |
Dresden | -6.518 |
��� | -6.487 |
ebted | -6.232 |
peria | -6.186 |
Token | , |
Token ID | 11 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
advertising | +0.394 |
Dresden | +0.372 |
education | +0.363 |
��� | +0.362 |
ary | +0.359 |
Neg logit contributions | |
anonymously | -0.372 |
orr | -0.361 |
oux | -0.348 |
church | -0.338 |
disse | -0.334 |
Token | the |
Token ID | 262 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
anonymously | +0.350 |
orr | +0.339 |
oux | +0.326 |
church | +0.318 |
disse | +0.316 |
Neg logit contributions | |
advertising | -0.350 |
Dresden | -0.328 |
��� | -0.323 |
education | -0.319 |
defense | -0.317 |
Token | Social |
Token ID | 5483 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
advertising | +0.606 |
Dresden | +0.579 |
��� | +0.561 |
education | +0.558 |
ary | +0.553 |
Neg logit contributions | |
anonymously | -0.646 |
orr | -0.630 |
oux | -0.603 |
church | -0.588 |
disse | -0.585 |
Token | � |
Token ID | 447 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
advertising | +4.291 |
Dresden | +4.073 |
��� | +3.912 |
ary | +3.903 |
defense | +3.887 |
Neg logit contributions | |
anonymously | -3.672 |
orr | -3.491 |
oux | -3.393 |
church | -3.303 |
disse | -3.295 |
Token | � |
Token ID | 247 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
advertising | +0.944 |
Dresden | +0.801 |
��� | +0.751 |
defense | +0.746 |
education | +0.743 |
Neg logit contributions | |
anonymously | -3.304 |
orr | -3.203 |
oux | -3.166 |
disse | -3.118 |
church | -3.092 |
Token | s |
Token ID | 82 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
anonymously | +0.818 |
orr | +0.784 |
oux | +0.754 |
church | +0.732 |
disse | +0.732 |
Neg logit contributions | |
advertising | -0.892 |
��� | -0.832 |
Dresden | -0.832 |
education | -0.810 |
defense | -0.808 |
Token | Diary |
Token ID | 35911 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
anonymously | +0.072 |
orr | +0.068 |
oux | +0.064 |
disse | +0.062 |
church | +0.062 |
Neg logit contributions | |
advertising | -0.136 |
Dresden | -0.129 |
��� | -0.128 |
education | -0.126 |
defense | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
anonymously | +1.126 |
orr | +1.073 |
oux | +1.031 |
disse | +1.000 |
church | +0.996 |
Neg logit contributions | |
advertising | -1.321 |
��� | -1.238 |
Dresden | -1.235 |
education | -1.206 |
defense | -1.203 |
Token | � |
Token ID | 447 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
anonymously | +1.975 |
orr | +1.897 |
oux | +1.819 |
church | +1.761 |
disse | +1.753 |
Neg logit contributions | |
advertising | -2.205 |
��� | -2.084 |
Dresden | -2.055 |
education | -2.010 |
defense | -2.004 |
Token | � |
Token ID | 251 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
anonymously | +1.341 |
orr | +1.302 |
oux | +1.262 |
church | +1.237 |
disse | +1.232 |
Neg logit contributions | |
advertising | -0.790 |
Dresden | -0.716 |
��� | -0.708 |
education | -0.686 |
defense | -0.684 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
anonymously | +3.382 |
orr | +3.249 |
oux | +3.114 |
church | +3.017 |
disse | +2.983 |
Neg logit contributions | |
advertising | -3.733 |
��� | -3.583 |
Dresden | -3.457 |
education | -3.407 |
defense | -3.405 |
Token |
|
Token ID | 198 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
anonymously | +1.117 |
orr | +1.069 |
oux | +1.026 |
church | +0.994 |
disse | +0.992 |
Neg logit contributions | |
advertising | -1.337 |
��� | -1.257 |
Dresden | -1.254 |
education | -1.220 |
defense | -1.218 |
Token | I |
Token ID | 40 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
anonymously | +1.924 |
orr | +1.861 |
oux | +1.784 |
church | +1.739 |
disse | +1.711 |
Neg logit contributions | |
advertising | -2.031 |
��� | -1.956 |
Dresden | -1.923 |
education | -1.856 |
defense | -1.852 |
Token | think |
Token ID | 892 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
anonymously | +1.723 |
orr | +1.647 |
oux | +1.582 |
church | +1.533 |
disse | +1.532 |
Neg logit contributions | |
advertising | -2.103 |
Dresden | -1.974 |
��� | -1.961 |
education | -1.920 |
defense | -1.916 |
Token | like |
Token ID | 588 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
advertising | +1.884 |
Dresden | +1.775 |
ary | +1.737 |
��� | +1.713 |
education | +1.687 |
Neg logit contributions | |
anonymously | -2.075 |
orr | -2.026 |
oux | -1.971 |
church | -1.913 |
disse | -1.868 |
Token | your |
Token ID | 534 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
advertising | +1.163 |
Dresden | +1.089 |
ary | +1.066 |
��� | +1.056 |
education | +1.046 |
Neg logit contributions | |
anonymously | -1.246 |
orr | -1.206 |
oux | -1.162 |
church | -1.135 |
disse | -1.120 |
Token | looking |
Token ID | 2045 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
anonymously | +1.259 |
orr | +1.207 |
oux | +1.162 |
disse | +1.128 |
church | +1.127 |
Neg logit contributions | |
advertising | -1.362 |
Dresden | -1.273 |
��� | -1.266 |
education | -1.236 |
defense | -1.234 |
Token | at |
Token ID | 379 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
anonymously | +0.347 |
orr | +0.335 |
oux | +0.323 |
church | +0.314 |
disse | +0.313 |
Neg logit contributions | |
advertising | -0.336 |
Dresden | -0.313 |
��� | -0.311 |
education | -0.303 |
defense | -0.302 |
Token | the |
Token ID | 262 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
anonymously | +1.298 |
orr | +1.249 |
oux | +1.208 |
disse | +1.177 |
church | +1.176 |
Neg logit contributions | |
advertising | -1.120 |
Dresden | -1.037 |
��� | -1.031 |
education | -1.004 |
defense | -1.002 |
Token | image |
Token ID | 2939 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
anonymously | +0.456 |
orr | +0.439 |
oux | +0.423 |
church | +0.410 |
disse | +0.408 |
Neg logit contributions | |
advertising | -0.486 |
Dresden | -0.455 |
��� | -0.447 |
ary | -0.440 |
education | -0.440 |
Token | through |
Token ID | 832 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
anonymously | +0.821 |
orr | +0.789 |
oux | +0.760 |
church | +0.739 |
disse | +0.737 |
Neg logit contributions | |
advertising | -0.874 |
Dresden | -0.817 |
��� | -0.807 |
education | -0.794 |
defense | -0.792 |
Token | a |
Token ID | 257 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
anonymously | +0.588 |
orr | +0.566 |
oux | +0.548 |
disse | +0.534 |
church | +0.534 |
Neg logit contributions | |
advertising | -0.486 |
Dresden | -0.449 |
��� | -0.446 |
education | -0.434 |
defense | -0.433 |
Token | mesh |
Token ID | 19609 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
anonymously | +3.505 |
orr | +3.357 |
oux | +3.221 |
disse | +3.204 |
church | +3.115 |
Neg logit contributions | |
advertising | -4.034 |
��� | -3.809 |
Dresden | -3.725 |
education | -3.689 |
defense | -3.660 |
Token | ( |
Token ID | 357 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
anonymously | +1.703 |
orr | +1.632 |
oux | +1.570 |
disse | +1.531 |
church | +1.524 |
Neg logit contributions | |
advertising | -1.812 |
Dresden | -1.694 |
��� | -1.694 |
education | -1.647 |
defense | -1.640 |
Token | usually |
Token ID | 23073 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
anonymously | +2.065 |
orr | +1.999 |
oux | +1.922 |
church | +1.875 |
disse | +1.861 |
Neg logit contributions | |
advertising | -2.053 |
��� | -1.939 |
Dresden | -1.936 |
education | -1.860 |
defense | -1.855 |
Token | � |
Token ID | 447 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
advertising | +0.306 |
Dresden | +0.285 |
��� | +0.284 |
education | +0.277 |
defense | +0.276 |
Neg logit contributions | |
anonymously | -0.304 |
orr | -0.292 |
oux | -0.281 |
disse | -0.273 |
church | -0.273 |
Token | � |
Token ID | 247 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
anonymously | +0.687 |
orr | +0.662 |
oux | +0.642 |
disse | +0.627 |
church | +0.625 |
Neg logit contributions | |
advertising | -0.518 |
Dresden | -0.476 |
��� | -0.473 |
education | -0.460 |
defense | -0.458 |
Token | s |
Token ID | 82 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
advertising | +1.064 |
Dresden | +0.989 |
��� | +0.972 |
education | +0.968 |
defense | +0.966 |
Neg logit contributions | |
anonymously | -1.082 |
orr | -1.031 |
oux | -0.995 |
disse | -0.974 |
church | -0.968 |
Token | nervous |
Token ID | 10927 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
advertising | +1.423 |
Dresden | +1.348 |
��� | +1.304 |
ary | +1.301 |
education | +1.298 |
Neg logit contributions | |
anonymously | -1.414 |
orr | -1.363 |
oux | -1.309 |
church | -1.283 |
disse | -1.264 |
Token | ness |
Token ID | 1108 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
anonymously | +0.385 |
orr | +0.371 |
oux | +0.358 |
church | +0.349 |
disse | +0.349 |
Neg logit contributions | |
advertising | -0.320 |
Dresden | -0.296 |
��� | -0.293 |
education | -0.286 |
defense | -0.286 |
Token | about |
Token ID | 546 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
advertising | +1.847 |
Dresden | +1.741 |
ary | +1.704 |
��� | +1.700 |
defense | +1.684 |
Neg logit contributions | |
anonymously | -1.507 |
orr | -1.447 |
oux | -1.393 |
disse | -1.350 |
church | -1.350 |
Token | the |
Token ID | 262 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
anonymously | +2.229 |
orr | +2.120 |
oux | +2.038 |
disse | +2.002 |
church | +1.979 |
Neg logit contributions | |
advertising | -2.201 |
��� | -2.059 |
Dresden | -2.027 |
education | -1.989 |
peria | -1.985 |
Token | security |
Token ID | 2324 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
anonymously | +2.249 |
orr | +2.147 |
oux | +2.068 |
disse | +2.022 |
church | +2.011 |
Neg logit contributions | |
advertising | -2.240 |
��� | -2.088 |
Dresden | -2.061 |
peria | -2.016 |
defense | -2.015 |
Token | forces |
Token ID | 3386 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
advertising | +2.263 |
Dresden | +2.117 |
ary | +2.088 |
education | +2.042 |
defense | +2.012 |
Neg logit contributions | |
anonymously | -3.139 |
orr | -3.049 |
oux | -2.970 |
church | -2.901 |
disse | -2.868 |
Token | � |
Token ID | 447 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
advertising | +0.334 |
Dresden | +0.312 |
��� | +0.308 |
education | +0.302 |
defense | +0.302 |
Neg logit contributions | |
anonymously | -0.324 |
orr | -0.312 |
oux | -0.301 |
church | -0.293 |
disse | -0.292 |
Token | � |
Token ID | 247 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
advertising | +1.011 |
��� | +0.919 |
Dresden | +0.919 |
education | +0.881 |
defense | +0.880 |
Neg logit contributions | |
anonymously | -1.698 |
orr | -1.635 |
oux | -1.600 |
disse | -1.564 |
church | -1.561 |
Token | , |
Token ID | 11 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
anonymously | +1.788 |
orr | +1.686 |
oux | +1.617 |
disse | +1.567 |
church | +1.563 |
Neg logit contributions | |
advertising | -2.195 |
��� | -2.061 |
Dresden | -2.042 |
education | -2.002 |
defense | -1.994 |
Token | Robert |
Token ID | 5199 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
anonymously | +2.463 |
orr | +2.321 |
oux | +2.230 |
disse | +2.177 |
church | +2.173 |
Neg logit contributions | |
advertising | -2.906 |
��� | -2.724 |
Dresden | -2.690 |
education | -2.637 |
peria | -2.634 |
Token | Gibbs |
Token ID | 41071 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
advertising | +3.743 |
Dresden | +3.615 |
ary | +3.453 |
defense | +3.381 |
education | +3.368 |
Neg logit contributions | |
anonymously | -4.506 |
orr | -4.285 |
oux | -4.165 |
disse | -4.140 |
church | -4.056 |
Token | , |
Token ID | 11 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
anonymously | +3.659 |
orr | +3.416 |
oux | +3.274 |
church | +3.142 |
disse | +3.136 |
Neg logit contributions | |
advertising | -5.374 |
��� | -4.998 |
Dresden | -4.982 |
education | -4.950 |
peria | -4.918 |
Token | the |
Token ID | 262 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
anonymously | +2.844 |
orr | +2.697 |
oux | +2.612 |
church | +2.537 |
disse | +2.514 |
Neg logit contributions | |
advertising | -2.662 |
��� | -2.480 |
Dresden | -2.437 |
peria | -2.382 |
education | -2.372 |
Token | White |
Token ID | 2635 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
anonymously | +3.063 |
orr | +2.884 |
oux | +2.800 |
disse | +2.720 |
church | +2.720 |
Neg logit contributions | |
advertising | -3.241 |
��� | -3.021 |
Dresden | -2.970 |
peria | -2.920 |
education | -2.906 |
Token | House |
Token ID | 2097 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
anonymously | +6.010 |
orr | +5.707 |
oux | +5.555 |
church | +5.395 |
nect | +4.924 |
Neg logit contributions | |
��� | -10.892 |
advertising | -10.110 |
peria | -9.587 |
amily | -9.490 |
defense | -9.444 |
Token | press |
Token ID | 1803 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
anonymously | +3.222 |
orr | +3.033 |
oux | +2.909 |
disse | +2.841 |
church | +2.809 |
Neg logit contributions | |
advertising | -3.801 |
��� | -3.626 |
Dresden | -3.586 |
peria | -3.491 |
ebted | -3.460 |
Token | secretary |
Token ID | 7705 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
advertising | +2.842 |
ary | +2.707 |
Dresden | +2.522 |
education | +2.492 |
��� | +2.474 |
Neg logit contributions | |
anonymously | -5.623 |
orr | -5.540 |
church | -5.455 |
oux | -5.415 |
disse | -5.274 |
Token | , |
Token ID | 11 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
anonymously | +2.188 |
orr | +2.015 |
oux | +1.933 |
disse | +1.827 |
church | +1.811 |
Neg logit contributions | |
advertising | -3.579 |
��� | -3.374 |
Dresden | -3.341 |
education | -3.281 |
defense | -3.268 |
Token | made |
Token ID | 925 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
advertising | +1.633 |
Dresden | +1.553 |
��� | +1.522 |
ary | +1.510 |
education | +1.484 |
Neg logit contributions | |
anonymously | -1.599 |
orr | -1.584 |
oux | -1.528 |
church | -1.505 |
disse | -1.475 |
Token | deployed |
Token ID | 12380 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
advertising | +3.249 |
Dresden | +3.187 |
ary | +3.086 |
��� | +3.035 |
defense | +3.020 |
Neg logit contributions | |
anonymously | -3.435 |
orr | -3.425 |
oux | -3.301 |
church | -3.169 |
disse | -3.142 |
Token | with |
Token ID | 351 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
advertising | +3.747 |
Dresden | +3.575 |
ary | +3.526 |
defense | +3.460 |
education | +3.391 |
Neg logit contributions | |
anonymously | -4.090 |
orr | -4.080 |
oux | -3.889 |
disse | -3.880 |
church | -3.830 |
Token | maximum |
Token ID | 5415 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
advertising | +1.706 |
Dresden | +1.637 |
��� | +1.581 |
ary | +1.569 |
defense | +1.556 |
Neg logit contributions | |
anonymously | -1.857 |
orr | -1.808 |
oux | -1.732 |
disse | -1.697 |
church | -1.691 |
Token | deployment |
Token ID | 14833 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
anonymously | +0.199 |
orr | +0.192 |
oux | +0.185 |
disse | +0.181 |
church | +0.180 |
Neg logit contributions | |
advertising | -0.181 |
Dresden | -0.168 |
��� | -0.167 |
education | -0.163 |
defense | -0.163 |
Token | in |
Token ID | 287 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
advertising | +1.060 |
Dresden | +0.995 |
ary | +0.969 |
��� | +0.967 |
defense | +0.962 |
Neg logit contributions | |
anonymously | -1.124 |
orr | -1.086 |
oux | -1.046 |
disse | -1.028 |
church | -1.019 |
Token | Roh |
Token ID | 32694 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
advertising | +0.725 |
Dresden | +0.691 |
��� | +0.670 |
defense | +0.664 |
ary | +0.662 |
Neg logit contributions | |
anonymously | -0.767 |
orr | -0.743 |
oux | -0.718 |
church | -0.697 |
disse | -0.695 |
Token | t |
Token ID | 83 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
orr | +4.073 |
anonymously | +3.945 |
oux | +3.806 |
church | +3.568 |
ococ | +3.301 |
Neg logit contributions | |
��� | -11.739 |
advertising | -10.786 |
Dresden | -10.362 |
ebted | -10.179 |
eanor | -9.938 |
Token | ak |
Token ID | 461 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
anonymously | +2.008 |
orr | +1.944 |
oux | +1.880 |
church | +1.816 |
disse | +1.775 |
Neg logit contributions | |
advertising | -2.212 |
��� | -2.150 |
Dresden | -2.079 |
defense | -2.000 |
education | -1.999 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
anonymously | +1.213 |
orr | +1.161 |
oux | +1.115 |
church | +1.084 |
disse | +1.080 |
Neg logit contributions | |
advertising | -1.320 |
��� | -1.236 |
Dresden | -1.228 |
education | -1.196 |
defense | -1.190 |
Token | Additional |
Token ID | 15891 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
advertising | +0.213 |
Dresden | +0.199 |
��� | +0.194 |
education | +0.191 |
defense | +0.191 |
Neg logit contributions | |
anonymously | -0.233 |
orr | -0.224 |
oux | -0.216 |
disse | -0.212 |
church | -0.211 |
Token | columns |
Token ID | 15180 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
advertising | +1.835 |
Dresden | +1.741 |
ary | +1.689 |
defense | +1.675 |
education | +1.664 |
Neg logit contributions | |
anonymously | -2.113 |
orr | -2.037 |
oux | -1.978 |
disse | -1.939 |
church | -1.916 |
Token | room |
Token ID | 2119 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
anonymously | +1.670 |
orr | +1.590 |
oux | +1.525 |
disse | +1.478 |
church | +1.473 |
Neg logit contributions | |
advertising | -2.131 |
Dresden | -1.999 |
��� | -1.997 |
education | -1.949 |
defense | -1.945 |
Token | internet |
Token ID | 5230 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
advertising | +3.045 |
Dresden | +2.899 |
ary | +2.854 |
defense | +2.778 |
��� | +2.760 |
Neg logit contributions | |
anonymously | -2.690 |
orr | -2.633 |
oux | -2.526 |
church | -2.474 |
disse | -2.429 |
Token | at |
Token ID | 379 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
anonymously | +1.614 |
orr | +1.534 |
oux | +1.473 |
disse | +1.432 |
church | +1.426 |
Neg logit contributions | |
advertising | -1.998 |
Dresden | -1.873 |
��� | -1.873 |
education | -1.825 |
defense | -1.823 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
anonymously | +1.221 |
orr | +1.174 |
oux | +1.133 |
disse | +1.101 |
church | +1.098 |
Neg logit contributions | |
advertising | -1.221 |
��� | -1.131 |
Dresden | -1.130 |
education | -1.103 |
defense | -1.100 |
Token | West |
Token ID | 2688 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
anonymously | +1.271 |
orr | +1.221 |
oux | +1.177 |
disse | +1.146 |
church | +1.144 |
Neg logit contributions | |
advertising | -1.280 |
��� | -1.188 |
Dresden | -1.185 |
education | -1.157 |
defense | -1.153 |
Token | in |
Token ID | 259 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
anonymously | +0.870 |
orr | +0.835 |
oux | +0.804 |
church | +0.783 |
disse | +0.780 |
Neg logit contributions | |
advertising | -0.901 |
Dresden | -0.838 |
��� | -0.838 |
education | -0.816 |
defense | -0.815 |
Token | cut |
Token ID | 2005 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
anonymously | +7.102 |
orr | +6.930 |
oux | +6.753 |
church | +6.570 |
disse | +6.330 |
Neg logit contributions | |
advertising | -6.909 |
��� | -6.450 |
ebted | -6.375 |
peria | -6.295 |
education | -6.260 |
Token | out |
Token ID | 503 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
anonymously | +0.623 |
orr | +0.597 |
oux | +0.575 |
disse | +0.558 |
church | +0.558 |
Neg logit contributions | |
advertising | -0.674 |
Dresden | -0.630 |
��� | -0.626 |
education | -0.612 |
defense | -0.610 |
Token | ( |
Token ID | 357 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
anonymously | +2.391 |
orr | +2.262 |
oux | +2.192 |
disse | +2.125 |
church | +2.112 |
Neg logit contributions | |
advertising | -2.733 |
��� | -2.573 |
Dresden | -2.520 |
education | -2.490 |
peria | -2.482 |
Token | as |
Token ID | 292 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
anonymously | +1.268 |
orr | +1.220 |
oux | +1.177 |
church | +1.146 |
disse | +1.142 |
Neg logit contributions | |
advertising | -1.211 |
Dresden | -1.128 |
��� | -1.127 |
education | -1.093 |
defense | -1.090 |
Token | it |
Token ID | 340 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
advertising | +0.410 |
Dresden | +0.385 |
��� | +0.378 |
ary | +0.370 |
defense | +0.370 |
Neg logit contributions | |
anonymously | -0.421 |
orr | -0.406 |
oux | -0.389 |
church | -0.381 |
disse | -0.381 |
Token | and |
Token ID | 290 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
anonymously | +3.072 |
orr | +2.923 |
oux | +2.794 |
church | +2.695 |
disse | +2.693 |
Neg logit contributions | |
advertising | -3.796 |
��� | -3.653 |
Dresden | -3.551 |
education | -3.458 |
defense | -3.456 |
Token | touched |
Token ID | 12615 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
anonymously | +2.006 |
orr | +1.916 |
oux | +1.845 |
disse | +1.801 |
church | +1.793 |
Neg logit contributions | |
advertising | -2.070 |
��� | -1.926 |
Dresden | -1.921 |
education | -1.872 |
defense | -1.861 |
Token | off |
Token ID | 572 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
anonymously | +2.492 |
orr | +2.364 |
oux | +2.274 |
disse | +2.215 |
church | +2.202 |
Neg logit contributions | |
advertising | -2.972 |
��� | -2.796 |
Dresden | -2.756 |
education | -2.708 |
defense | -2.686 |
Token | the |
Token ID | 262 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
advertising | +0.985 |
Dresden | +0.916 |
��� | +0.892 |
defense | +0.879 |
ary | +0.876 |
Neg logit contributions | |
anonymously | -1.341 |
orr | -1.301 |
oux | -1.262 |
church | -1.230 |
disse | -1.220 |
Token | political |
Token ID | 1964 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
advertising | +1.437 |
Dresden | +1.380 |
ary | +1.325 |
��� | +1.325 |
education | +1.317 |
Neg logit contributions | |
anonymously | -1.406 |
orr | -1.351 |
oux | -1.309 |
church | -1.274 |
disse | -1.246 |
Token | rift |
Token ID | 36788 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
anonymously | +0.179 |
orr | +0.172 |
oux | +0.165 |
church | +0.160 |
disse | +0.159 |
Neg logit contributions | |
advertising | -0.198 |
Dresden | -0.186 |
��� | -0.183 |
education | -0.181 |
ary | -0.180 |
Token | that |
Token ID | 326 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
anonymously | +6.207 |
orr | +5.864 |
oux | +5.615 |
disse | +5.315 |
church | +5.304 |
Neg logit contributions | |
advertising | -8.441 |
��� | -8.264 |
education | -7.649 |
Dresden | -7.631 |
peria | -7.617 |
Token | paraly |
Token ID | 26901 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
advertising | +0.406 |
Dresden | +0.387 |
ary | +0.374 |
��� | +0.372 |
defense | +0.370 |
Neg logit contributions | |
anonymously | -0.404 |
orr | -0.392 |
oux | -0.377 |
church | -0.371 |
disse | -0.362 |
Token | zes |
Token ID | 12271 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
anonymously | +1.793 |
orr | +1.721 |
oux | +1.656 |
disse | +1.602 |
church | +1.599 |
Neg logit contributions | |
advertising | -2.175 |
��� | -2.039 |
Dresden | -2.034 |
education | -1.977 |
peria | -1.973 |
Token | Palestinian |
Token ID | 8501 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
anonymously | +0.196 |
orr | +0.189 |
oux | +0.184 |
church | +0.178 |
disse | +0.176 |
Neg logit contributions | |
advertising | -0.173 |
Dresden | -0.163 |
��� | -0.157 |
defense | -0.156 |
ary | -0.156 |
Token | politics |
Token ID | 4819 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
anonymously | +2.964 |
orr | +2.837 |
oux | +2.707 |
disse | +2.669 |
church | +2.627 |
Neg logit contributions | |
advertising | -3.513 |
��� | -3.332 |
Dresden | -3.284 |
peria | -3.187 |
education | -3.184 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
anonymously | +0.886 |
orr | +0.846 |
oux | +0.814 |
disse | +0.793 |
church | +0.789 |
Neg logit contributions | |
advertising | -1.030 |
Dresden | -0.963 |
��� | -0.947 |
education | -0.937 |
defense | -0.935 |
Token | The |
Token ID | 464 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
anonymously | +1.070 |
orr | +1.033 |
oux | +0.994 |
church | +0.971 |
disse | +0.964 |
Neg logit contributions | |
advertising | -0.972 |
��� | -0.914 |
Dresden | -0.911 |
education | -0.877 |
defense | -0.875 |
Token | statement |
Token ID | 2643 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
anonymously | +1.579 |
orr | +1.511 |
oux | +1.454 |
disse | +1.414 |
church | +1.413 |
Neg logit contributions | |
advertising | -1.666 |
Dresden | -1.552 |
��� | -1.549 |
education | -1.509 |
defense | -1.507 |
Token | by |
Token ID | 416 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
advertising | +1.019 |
Dresden | +0.966 |
ary | +0.953 |
defense | +0.926 |
��� | +0.924 |
Neg logit contributions | |
anonymously | -1.015 |
orr | -1.002 |
oux | -0.964 |
church | -0.937 |
disse | -0.930 |
Token | the |
Token ID | 262 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
anonymously | +3.117 |
orr | +2.959 |
oux | +2.812 |
church | +2.732 |
disse | +2.726 |
Neg logit contributions | |
advertising | -3.597 |
��� | -3.376 |
Dresden | -3.331 |
peria | -3.266 |
education | -3.264 |
Token | FDA |
Token ID | 14672 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
anonymously | +1.860 |
orr | +1.779 |
oux | +1.712 |
disse | +1.667 |
church | +1.665 |
Neg logit contributions | |
advertising | -1.821 |
��� | -1.690 |
Dresden | -1.688 |
education | -1.640 |
defense | -1.637 |
Token | largely |
Token ID | 5688 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
anonymously | +9.586 |
disse | +8.315 |
orr | +8.209 |
oux | +8.105 |
church | +7.689 |
Neg logit contributions | |
��� | -10.641 |
advertising | -10.613 |
ebted | -9.898 |
Dresden | -9.603 |
education | -9.585 |
Token | came |
Token ID | 1625 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
anonymously | +3.179 |
orr | +2.984 |
oux | +2.876 |
disse | +2.839 |
church | +2.793 |
Neg logit contributions | |
advertising | -3.419 |
��� | -3.207 |
Dresden | -3.160 |
education | -3.115 |
peria | -3.090 |
Token | as |
Token ID | 355 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
anonymously | +0.019 |
orr | +0.018 |
oux | +0.018 |
disse | +0.017 |
church | +0.017 |
Neg logit contributions | |
advertising | -0.016 |
Dresden | -0.015 |
��� | -0.015 |
education | -0.014 |
defense | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
advertising | +0.866 |
Dresden | +0.807 |
��� | +0.790 |
education | +0.780 |
defense | +0.779 |
Neg logit contributions | |
anonymously | -0.919 |
orr | -0.894 |
oux | -0.865 |
disse | -0.837 |
church | -0.836 |
Token | surprise |
Token ID | 5975 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
advertising | +1.687 |
Dresden | +1.597 |
ary | +1.544 |
defense | +1.535 |
��� | +1.527 |
Neg logit contributions | |
anonymously | -1.939 |
orr | -1.931 |
oux | -1.868 |
church | -1.784 |
disse | -1.777 |