Token | its |
Token ID | 663 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
�� | +0.841 |
izoph | +0.823 |
="# | +0.762 |
arte | +0.729 |
ム | +0.718 |
Neg logit contributions | |
ocument | -0.783 |
"]," | -0.717 |
outp | -0.688 |
Extrem | -0.657 |
cial | -0.636 |
Token | sovereign |
Token ID | 18901 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
ocument | +0.335 |
"]," | +0.309 |
outp | +0.297 |
Extrem | +0.286 |
cult | +0.275 |
Neg logit contributions | |
�� | -0.349 |
izoph | -0.341 |
="# | -0.313 |
arte | -0.301 |
ム | -0.297 |
Token | territory |
Token ID | 7674 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
�� | +3.284 |
izoph | +3.232 |
="# | +3.039 |
arte | +2.851 |
ム | +2.797 |
Neg logit contributions | |
ocument | -3.472 |
"]," | -3.174 |
outp | -3.069 |
Extrem | -2.965 |
Exhibit | -2.845 |
Token | and |
Token ID | 290 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
�� | +2.486 |
izoph | +2.420 |
="# | +2.240 |
arte | +2.158 |
ム | +2.127 |
Neg logit contributions | |
ocument | -2.508 |
"]," | -2.340 |
outp | -2.253 |
Extrem | -2.171 |
cult | -2.090 |
Token | the |
Token ID | 262 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
�� | +2.164 |
izoph | +2.104 |
="# | +1.960 |
arte | +1.854 |
ム | +1.837 |
Neg logit contributions | |
ocument | -2.134 |
"]," | -1.947 |
outp | -1.879 |
Extrem | -1.793 |
cial | -1.748 |
Token | West |
Token ID | 2688 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
�� | +3.681 |
izoph | +3.611 |
="# | +3.367 |
arte | +3.178 |
ム | +3.141 |
Neg logit contributions | |
ocument | -3.841 |
"]," | -3.458 |
outp | -3.299 |
Extrem | -3.168 |
cial | -3.163 |
Token | Bank |
Token ID | 5018 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
izoph | +5.318 |
="# | +4.992 |
�� | +4.300 |
Bowen | +4.280 |
Boe | +4.175 |
Neg logit contributions | |
ocument | -18.275 |
ormons | -16.558 |
cial | -16.382 |
outp | -16.290 |
Reviewer | -16.210 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
�� | +3.260 |
izoph | +3.175 |
="# | +2.944 |
arte | +2.838 |
ム | +2.796 |
Neg logit contributions | |
ocument | -3.189 |
"]," | -2.980 |
outp | -2.841 |
Extrem | -2.696 |
cult | -2.635 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
�� | +1.758 |
izoph | +1.691 |
="# | +1.605 |
arte | +1.524 |
ム | +1.518 |
Neg logit contributions | |
ocument | -2.062 |
"]," | -1.885 |
outp | -1.875 |
cult | -1.726 |
cial | -1.703 |
Token |
|
Token ID | 198 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
�� | +1.411 |
izoph | +1.395 |
="# | +1.356 |
arte | +1.278 |
ム | +1.248 |
Neg logit contributions | |
ocument | -1.967 |
"]," | -1.756 |
outp | -1.751 |
Extrem | -1.683 |
cult | -1.621 |
Token | The |
Token ID | 464 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
�� | +0.661 |
izoph | +0.639 |
="# | +0.595 |
arte | +0.566 |
ム | +0.563 |
Neg logit contributions | |
ocument | -0.783 |
"]," | -0.726 |
outp | -0.716 |
Extrem | -0.684 |
cult | -0.655 |
Token | separation |
Token ID | 14139 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
�� | +3.031 |
izoph | +2.948 |
="# | +2.857 |
ム | +2.487 |
ENN | +2.464 |
Neg logit contributions | |
ocument | -5.329 |
"]," | -4.869 |
outp | -4.623 |
cial | -4.450 |
ormons | -4.449 |
Token | between |
Token ID | 1022 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ocument | +0.249 |
"]," | +0.231 |
outp | +0.223 |
Extrem | +0.214 |
cult | +0.206 |
Neg logit contributions | |
�� | -0.268 |
izoph | -0.262 |
="# | -0.240 |
arte | -0.232 |
ム | -0.229 |
Token | Gaza |
Token ID | 11010 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ocument | +1.417 |
"]," | +1.312 |
outp | +1.265 |
Extrem | +1.216 |
cult | +1.165 |
Neg logit contributions | |
�� | -1.691 |
izoph | -1.652 |
="# | -1.515 |
arte | -1.468 |
ム | -1.452 |
Token | and |
Token ID | 290 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
�� | +2.610 |
izoph | +2.561 |
="# | +2.357 |
arte | +2.248 |
ム | +2.202 |
Neg logit contributions | |
ocument | -2.936 |
"]," | -2.733 |
outp | -2.619 |
Extrem | -2.534 |
cult | -2.439 |
Token | the |
Token ID | 262 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
�� | +0.643 |
izoph | +0.623 |
="# | +0.582 |
arte | +0.552 |
ム | +0.545 |
Neg logit contributions | |
ocument | -0.644 |
"]," | -0.595 |
outp | -0.572 |
Extrem | -0.545 |
cult | -0.532 |
Token | West |
Token ID | 2688 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ocument | +0.784 |
"]," | +0.728 |
outp | +0.703 |
Extrem | +0.676 |
cult | +0.649 |
Neg logit contributions | |
�� | -0.823 |
izoph | -0.804 |
="# | -0.735 |
arte | -0.709 |
ム | -0.700 |
Token | Bank |
Token ID | 5018 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
izoph | +4.456 |
="# | +3.948 |
Bowen | +3.299 |
�� | +3.180 |
Boe | +2.903 |
Neg logit contributions | |
ocument | -18.567 |
ormons | -17.209 |
outp | -17.004 |
cial | -16.800 |
cult | -16.736 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
�� | +0.313 |
izoph | +0.305 |
="# | +0.281 |
arte | +0.272 |
ム | +0.268 |
Neg logit contributions | |
ocument | -0.270 |
"]," | -0.249 |
outp | -0.240 |
Extrem | -0.230 |
cult | -0.221 |
Token | The |
Token ID | 383 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
�� | +1.222 |
izoph | +1.178 |
="# | +1.117 |
arte | +1.055 |
ム | +1.051 |
Neg logit contributions | |
ocument | -1.449 |
"]," | -1.319 |
outp | -1.311 |
cult | -1.211 |
Extrem | -1.198 |
Token | hope |
Token ID | 2911 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
�� | +2.491 |
izoph | +2.434 |
="# | +2.260 |
arte | +2.161 |
ム | +2.118 |
Neg logit contributions | |
ocument | -2.431 |
"]," | -2.225 |
outp | -2.082 |
Extrem | -2.006 |
cial | -1.990 |
Token | was |
Token ID | 373 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ocument | +0.979 |
"]," | +0.907 |
outp | +0.880 |
Extrem | +0.840 |
cult | +0.809 |
Neg logit contributions | |
�� | -1.070 |
izoph | -1.048 |
="# | -0.957 |
arte | -0.925 |
ム | -0.914 |
Token | region |
Token ID | 3814 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ocument | +0.922 |
"]," | +0.849 |
outp | +0.819 |
Extrem | +0.786 |
cult | +0.755 |
Neg logit contributions | |
�� | -1.065 |
izoph | -1.043 |
="# | -0.955 |
arte | -0.925 |
ム | -0.912 |
Token | would |
Token ID | 561 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
�� | +0.963 |
izoph | +0.929 |
="# | +0.865 |
arte | +0.830 |
ム | +0.823 |
Neg logit contributions | |
ocument | -0.893 |
"]," | -0.831 |
outp | -0.790 |
Extrem | -0.767 |
cult | -0.740 |
Token | bis |
Token ID | 47457 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ocument | +0.666 |
"]," | +0.617 |
outp | +0.594 |
Extrem | +0.574 |
cult | +0.551 |
Neg logit contributions | |
�� | -0.690 |
izoph | -0.672 |
="# | -0.620 |
arte | -0.598 |
ム | -0.589 |
Token | ect |
Token ID | 478 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
ocument | +3.119 |
"]," | +2.843 |
outp | +2.701 |
Extrem | +2.597 |
cult | +2.524 |
Neg logit contributions | |
�� | -4.595 |
izoph | -4.475 |
="# | -4.089 |
arte | -4.010 |
ENN | -3.925 |
Token | the |
Token ID | 262 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ocument | +0.485 |
"]," | +0.452 |
outp | +0.437 |
Extrem | +0.421 |
cult | +0.407 |
Neg logit contributions | |
�� | -0.443 |
izoph | -0.432 |
="# | -0.393 |
arte | -0.378 |
ム | -0.373 |
Token | West |
Token ID | 2688 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
�� | +2.234 |
izoph | +2.181 |
="# | +2.010 |
arte | +1.913 |
ム | +1.901 |
Neg logit contributions | |
ocument | -2.408 |
"]," | -2.210 |
outp | -2.122 |
Extrem | -2.038 |
cult | -2.000 |
Token | Bank |
Token ID | 5018 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
izoph | +4.789 |
�� | +4.168 |
Bowen | +4.036 |
="# | +4.015 |
arte | +3.593 |
Neg logit contributions | |
ocument | -17.840 |
cial | -16.263 |
ormons | -16.124 |
cult | -16.000 |
Reviewer | -15.986 |
Token | later |
Token ID | 1568 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
�� | +2.690 |
izoph | +2.622 |
="# | +2.443 |
arte | +2.349 |
ム | +2.323 |
Neg logit contributions | |
ocument | -2.581 |
"]," | -2.427 |
outp | -2.284 |
Extrem | -2.195 |
cult | -2.141 |
Token | ally |
Token ID | 453 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ocument | +1.017 |
"]," | +0.938 |
outp | +0.905 |
Extrem | +0.867 |
cult | +0.832 |
Neg logit contributions | |
�� | -1.193 |
izoph | -1.167 |
="# | -1.072 |
arte | -1.036 |
ム | -1.022 |
Token | , |
Token ID | 11 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
ocument | +2.598 |
"]," | +2.374 |
outp | +2.336 |
Extrem | +2.198 |
cult | +2.110 |
Neg logit contributions | |
�� | -3.320 |
izoph | -3.255 |
="# | -2.964 |
arte | -2.873 |
ム | -2.832 |
Token | though |
Token ID | 996 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ocument | +0.236 |
"]," | +0.219 |
outp | +0.209 |
Extrem | +0.202 |
cult | +0.195 |
Neg logit contributions | |
�� | -0.249 |
izoph | -0.243 |
="# | -0.223 |
arte | -0.216 |
ム | -0.213 |
Token | nurt |
Token ID | 23868 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
ocument | +1.803 |
"]," | +1.674 |
outp | +1.617 |
Extrem | +1.554 |
cult | +1.495 |
Neg logit contributions | |
�� | -1.873 |
izoph | -1.829 |
="# | -1.671 |
arte | -1.612 |
ム | -1.591 |
Token | ures |
Token ID | 942 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
izoph | +1.841 |
�� | +1.820 |
="# | +1.702 |
arte | +1.652 |
aster | +1.608 |
Neg logit contributions | |
ocument | -2.023 |
"]," | -1.921 |
outp | -1.823 |
Extrem | -1.821 |
Exhibit | -1.738 |
Token | separation |
Token ID | 14139 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
�� | +2.290 |
izoph | +2.221 |
="# | +2.072 |
arte | +1.953 |
ム | +1.919 |
Neg logit contributions | |
ocument | -2.328 |
"]," | -2.137 |
outp | -2.027 |
Extrem | -1.929 |
cult | -1.898 |
Token | within |
Token ID | 1626 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
�� | +1.215 |
izoph | +1.188 |
="# | +1.109 |
arte | +1.062 |
ム | +1.049 |
Neg logit contributions | |
ocument | -1.123 |
"]," | -1.042 |
outp | -0.985 |
Extrem | -0.952 |
cial | -0.913 |
Token | the |
Token ID | 262 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
�� | +4.127 |
izoph | +3.983 |
="# | +3.787 |
arte | +3.501 |
ム | +3.452 |
Neg logit contributions | |
ocument | -4.504 |
"]," | -4.144 |
outp | -3.960 |
cial | -3.719 |
Extrem | -3.697 |
Token | West |
Token ID | 2688 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
�� | +1.468 |
izoph | +1.436 |
="# | +1.325 |
arte | +1.266 |
ム | +1.244 |
Neg logit contributions | |
ocument | -1.570 |
"]," | -1.446 |
outp | -1.382 |
Extrem | -1.325 |
cial | -1.299 |
Token | Bank |
Token ID | 5018 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
izoph | +4.752 |
="# | +4.359 |
�� | +3.827 |
Bowen | +3.781 |
arte | +3.461 |
Neg logit contributions | |
ocument | -17.058 |
ormons | -15.453 |
cial | -15.335 |
"]," | -15.320 |
cult | -15.288 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
�� | +2.216 |
izoph | +2.157 |
="# | +2.013 |
arte | +1.938 |
ム | +1.907 |
Neg logit contributions | |
ocument | -2.083 |
"]," | -1.950 |
outp | -1.843 |
Extrem | -1.762 |
cult | -1.713 |
Token | Flying |
Token ID | 19903 |
Feature activation | +4.62e-03 |
Pos logit contributions | |
�� | +1.487 |
izoph | +1.431 |
="# | +1.364 |
arte | +1.283 |
ム | +1.275 |
Neg logit contributions | |
ocument | -1.739 |
"]," | -1.594 |
outp | -1.581 |
cult | -1.458 |
cial | -1.440 |
Token | checkpoints |
Token ID | 36628 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
�� | +0.045 |
izoph | +0.044 |
="# | +0.041 |
arte | +0.039 |
ム | +0.039 |
Neg logit contributions | |
ocument | -0.040 |
"]," | -0.037 |
outp | -0.036 |
Extrem | -0.034 |
cult | -0.033 |
Token | shift |
Token ID | 6482 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
�� | +1.800 |
izoph | +1.748 |
="# | +1.673 |
arte | +1.595 |
ム | +1.549 |
Neg logit contributions | |
ocument | -1.765 |
"]," | -1.637 |
outp | -1.541 |
Extrem | -1.501 |
cult | -1.439 |
Token | what |
Token ID | 644 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
�� | +0.175 |
izoph | +0.171 |
="# | +0.157 |
arte | +0.152 |
ム | +0.148 |
Neg logit contributions | |
ocument | -0.174 |
"]," | -0.163 |
outp | -0.156 |
Extrem | -0.150 |
cult | -0.146 |
Token | the |
Token ID | 262 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
�� | +0.131 |
izoph | +0.129 |
="# | +0.119 |
arte | +0.114 |
ム | +0.111 |
Neg logit contributions | |
ocument | -0.128 |
"]," | -0.120 |
outp | -0.114 |
Extrem | -0.109 |
cult | -0.107 |
Token | Ubuntu |
Token ID | 14949 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
ocument | +4.289 |
"]," | +3.978 |
outp | +3.952 |
Extrem | +3.714 |
Exhibit | +3.548 |
Neg logit contributions | |
�� | -5.333 |
izoph | -5.156 |
="# | -4.763 |
ム | -4.593 |
arte | -4.569 |
Token | website |
Token ID | 3052 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
�� | +0.553 |
izoph | +0.550 |
="# | +0.499 |
arte | +0.487 |
aster | +0.473 |
Neg logit contributions | |
ocument | -0.533 |
"]," | -0.486 |
outp | -0.462 |
Extrem | -0.448 |
cult | -0.435 |
Token | has |
Token ID | 468 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
�� | +5.641 |
izoph | +5.630 |
="# | +5.263 |
aster | +5.144 |
arte | +5.006 |
Neg logit contributions | |
ocument | -7.473 |
"]," | -6.957 |
Extrem | -6.363 |
outp | -6.362 |
cial | -6.311 |
Token | to |
Token ID | 284 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
izoph | +4.112 |
�� | +4.097 |
="# | +3.735 |
aster | +3.583 |
arte | +3.540 |
Neg logit contributions | |
ocument | -5.686 |
"]," | -5.445 |
Extrem | -5.067 |
outp | -5.049 |
cult | -4.991 |
Token | say |
Token ID | 910 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
�� | +5.967 |
aster | +5.890 |
="# | +5.866 |
izoph | +5.768 |
arte | +5.404 |
Neg logit contributions | |
ocument | -14.797 |
"]," | -14.178 |
Extrem | -13.599 |
cult | -13.547 |
outp | -13.492 |
Token | about |
Token ID | 546 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
�� | +0.060 |
izoph | +0.059 |
="# | +0.053 |
arte | +0.051 |
ム | +0.050 |
Neg logit contributions | |
ocument | -0.069 |
"]," | -0.065 |
outp | -0.063 |
Extrem | -0.061 |
cult | -0.059 |
Token | their |
Token ID | 511 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ocument | +2.532 |
"]," | +2.356 |
outp | +2.296 |
Extrem | +2.206 |
Exhibit | +2.108 |
Neg logit contributions | |
�� | -2.575 |
izoph | -2.494 |
="# | -2.278 |
arte | -2.198 |
ム | -2.185 |
Token | Snap |
Token ID | 16026 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
ocument | +1.791 |
"]," | +1.662 |
outp | +1.604 |
Extrem | +1.543 |
cult | +1.485 |
Neg logit contributions | |
�� | -1.849 |
izoph | -1.806 |
="# | -1.651 |
arte | -1.592 |
ム | -1.571 |
Token | technology |
Token ID | 3037 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ocument | +5.220 |
"]," | +4.822 |
outp | +4.765 |
Extrem | +4.436 |
cult | +4.208 |
Neg logit contributions | |
�� | -7.364 |
izoph | -7.044 |
="# | -6.568 |
ム | -6.403 |
arte | -6.323 |
Token | that |
Token ID | 326 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
�� | +0.145 |
izoph | +0.141 |
="# | +0.129 |
arte | +0.125 |
ム | +0.123 |
Neg logit contributions | |
ocument | -0.137 |
"]," | -0.128 |
outp | -0.123 |
Extrem | -0.118 |
cult | -0.114 |
Token | Israel |
Token ID | 2692 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
�� | +0.947 |
izoph | +0.923 |
="# | +0.853 |
arte | +0.811 |
ム | +0.806 |
Neg logit contributions | |
ocument | -0.944 |
"]," | -0.876 |
outp | -0.845 |
Extrem | -0.810 |
cult | -0.785 |
Token | controls |
Token ID | 6973 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
ocument | +1.571 |
"]," | +1.454 |
outp | +1.408 |
Extrem | +1.350 |
cult | +1.299 |
Neg logit contributions | |
�� | -1.687 |
izoph | -1.648 |
="# | -1.499 |
arte | -1.450 |
ム | -1.431 |
Token | both |
Token ID | 1111 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ocument | +0.296 |
"]," | +0.275 |
outp | +0.265 |
Extrem | +0.255 |
cult | +0.246 |
Neg logit contributions | |
�� | -0.305 |
izoph | -0.298 |
="# | -0.273 |
arte | -0.263 |
ム | -0.260 |
Token | the |
Token ID | 262 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
�� | +1.320 |
izoph | +1.294 |
="# | +1.195 |
arte | +1.138 |
ム | +1.124 |
Neg logit contributions | |
ocument | -1.309 |
"]," | -1.209 |
outp | -1.173 |
Extrem | -1.112 |
cult | -1.084 |
Token | West |
Token ID | 2688 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
�� | +2.003 |
izoph | +1.964 |
="# | +1.801 |
arte | +1.720 |
ム | +1.713 |
Neg logit contributions | |
ocument | -2.053 |
"]," | -1.873 |
outp | -1.812 |
Extrem | -1.731 |
cult | -1.697 |
Token | Bank |
Token ID | 5018 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
izoph | +5.295 |
="# | +4.857 |
�� | +4.599 |
Bowen | +4.537 |
arte | +4.527 |
Neg logit contributions | |
ocument | -15.431 |
outp | -13.686 |
cial | -13.686 |
Reviewer | -13.635 |
ormons | -13.473 |
Token | and |
Token ID | 290 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
�� | +2.520 |
izoph | +2.457 |
="# | +2.262 |
arte | +2.173 |
ム | +2.155 |
Neg logit contributions | |
ocument | -2.578 |
"]," | -2.388 |
outp | -2.311 |
Extrem | -2.204 |
cult | -2.148 |
Token | has |
Token ID | 468 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
�� | +0.310 |
izoph | +0.302 |
="# | +0.275 |
arte | +0.264 |
ム | +0.261 |
Neg logit contributions | |
ocument | -0.337 |
"]," | -0.313 |
outp | -0.303 |
Extrem | -0.292 |
cult | -0.282 |
Token | effective |
Token ID | 4050 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
�� | +1.282 |
izoph | +1.249 |
="# | +1.150 |
arte | +1.104 |
ム | +1.095 |
Neg logit contributions | |
ocument | -1.264 |
"]," | -1.163 |
outp | -1.123 |
Extrem | -1.078 |
cult | -1.040 |
Token | control |
Token ID | 1630 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
�� | +2.254 |
izoph | +2.212 |
="# | +2.073 |
arte | +1.969 |
ム | +1.939 |
Neg logit contributions | |
ocument | -1.880 |
"]," | -1.684 |
outp | -1.618 |
Extrem | -1.543 |
cult | -1.493 |
Token | decade |
Token ID | 5707 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
�� | +0.373 |
izoph | +0.363 |
="# | +0.331 |
arte | +0.320 |
ム | +0.315 |
Neg logit contributions | |
ocument | -0.403 |
"]," | -0.377 |
outp | -0.361 |
Extrem | -0.350 |
cult | -0.336 |
Token | - |
Token ID | 12 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
�� | +2.426 |
izoph | +2.382 |
="# | +2.222 |
arte | +2.171 |
ENN | +2.141 |
Neg logit contributions | |
ocument | -1.598 |
"]," | -1.474 |
outp | -1.345 |
Extrem | -1.325 |
cult | -1.249 |
Token | long |
Token ID | 6511 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
ocument | +5.111 |
"]," | +4.779 |
outp | +4.697 |
cult | +4.563 |
Extrem | +4.343 |
Neg logit contributions | |
�� | -5.663 |
izoph | -5.544 |
="# | -5.061 |
ム | -4.793 |
ENN | -4.702 |
Token | roller |
Token ID | 24471 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
ocument | +0.671 |
"]," | +0.616 |
outp | +0.590 |
Extrem | +0.568 |
cult | +0.546 |
Neg logit contributions | |
�� | -0.789 |
izoph | -0.770 |
="# | -0.710 |
arte | -0.688 |
ム | -0.677 |
Token | - |
Token ID | 12 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
�� | +2.319 |
izoph | +2.263 |
="# | +2.088 |
arte | +1.992 |
ム | +1.991 |
Neg logit contributions | |
ocument | -2.417 |
"]," | -2.237 |
outp | -2.115 |
Extrem | -2.085 |
Exhibit | -1.963 |
Token | co |
Token ID | 1073 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
�� | +4.508 |
aster | +4.217 |
izoph | +4.153 |
="# | +4.027 |
gold | +3.845 |
Neg logit contributions | |
ocument | -10.748 |
"]," | -9.873 |
Extrem | -9.787 |
outp | -9.655 |
Exhibit | -9.074 |
Token | aster |
Token ID | 1603 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
aster | +1.462 |
asters | +0.044 |
izoph | -0.859 |
arte | -1.368 |
uph | -1.378 |
Neg logit contributions | |
ocument | -21.345 |
Extrem | -20.475 |
"]," | -19.747 |
outp | -19.739 |
イト | -19.633 |
Token | ride |
Token ID | 6594 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
�� | +0.704 |
izoph | +0.687 |
="# | +0.638 |
arte | +0.618 |
ム | +0.613 |
Neg logit contributions | |
ocument | -0.558 |
"]," | -0.512 |
outp | -0.479 |
Extrem | -0.471 |
cult | -0.446 |
Token | followed |
Token ID | 3940 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ocument | +1.702 |
"]," | +1.575 |
outp | +1.519 |
Extrem | +1.458 |
cult | +1.400 |
Neg logit contributions | |
�� | -1.904 |
izoph | -1.861 |
="# | -1.707 |
arte | -1.649 |
ム | -1.628 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ocument | +1.979 |
"]," | +1.809 |
outp | +1.767 |
Extrem | +1.683 |
Exhibit | +1.605 |
Neg logit contributions | |
�� | -2.574 |
izoph | -2.521 |
="# | -2.326 |
arte | -2.251 |
ム | -2.220 |
Token | as |
Token ID | 355 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
�� | +1.500 |
izoph | +1.459 |
="# | +1.329 |
arte | +1.289 |
ム | +1.270 |
Neg logit contributions | |
ocument | -1.539 |
"]," | -1.425 |
outp | -1.322 |
Extrem | -1.310 |
cult | -1.261 |
Token | time |
Token ID | 640 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
�� | +1.417 |
izoph | +1.378 |
="# | +1.254 |
arte | +1.209 |
ム | +1.200 |
Neg logit contributions | |
ocument | -1.467 |
"]," | -1.369 |
outp | -1.279 |
Extrem | -1.250 |
cial | -1.210 |
Token | he |
Token ID | 339 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
�� | +4.507 |
izoph | +4.351 |
ム | +3.937 |
="# | +3.893 |
aster | +3.815 |
Neg logit contributions | |
ocument | -4.685 |
"]," | -4.355 |
outp | -3.978 |
cial | -3.863 |
Extrem | -3.859 |
Token | tracked |
Token ID | 18283 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
�� | +1.641 |
izoph | +1.599 |
="# | +1.468 |
arte | +1.453 |
ム | +1.410 |
Neg logit contributions | |
ocument | -1.851 |
"]," | -1.697 |
outp | -1.589 |
Extrem | -1.577 |
cial | -1.528 |
Token | Yoshi |
Token ID | 38936 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
�� | +2.484 |
izoph | +2.432 |
="# | +2.231 |
ム | +2.165 |
arte | +2.137 |
Neg logit contributions | |
ocument | -2.613 |
"]," | -2.398 |
outp | -2.267 |
Extrem | -2.157 |
cial | -2.155 |
Token | and |
Token ID | 290 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
�� | +2.047 |
izoph | +1.992 |
="# | +1.836 |
ム | +1.779 |
arte | +1.768 |
Neg logit contributions | |
ocument | -2.127 |
"]," | -2.002 |
outp | -1.891 |
Extrem | -1.832 |
cial | -1.773 |
Token | Tang |
Token ID | 18816 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ocument | +0.460 |
"]," | +0.427 |
outp | +0.410 |
Extrem | +0.394 |
cult | +0.381 |
Neg logit contributions | |
�� | -0.464 |
izoph | -0.452 |
="# | -0.414 |
arte | -0.399 |
ム | -0.395 |
Token | down |
Token ID | 866 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
�� | +7.471 |
izoph | +7.362 |
arte | +6.722 |
ム | +6.708 |
ENN | +6.600 |
Neg logit contributions | |
ocument | -11.391 |
"]," | -10.980 |
outp | -10.198 |
cial | -10.080 |
Extrem | -10.031 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
�� | +1.912 |
izoph | +1.858 |
="# | +1.716 |
arte | +1.661 |
ム | +1.650 |
Neg logit contributions | |
ocument | -1.941 |
"]," | -1.825 |
outp | -1.731 |
Extrem | -1.666 |
cult | -1.604 |
Token | and |
Token ID | 290 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
�� | +1.462 |
izoph | +1.421 |
="# | +1.309 |
arte | +1.276 |
ム | +1.261 |
Neg logit contributions | |
ocument | -1.484 |
"]," | -1.382 |
outp | -1.301 |
Extrem | -1.263 |
cial | -1.232 |
Token | set |
Token ID | 900 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ocument | +0.218 |
"]," | +0.201 |
outp | +0.192 |
Extrem | +0.185 |
cult | +0.179 |
Neg logit contributions | |
�� | -0.230 |
izoph | -0.224 |
="# | -0.206 |
arte | -0.200 |
ム | -0.198 |
Token | his |
Token ID | 465 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ocument | +1.177 |
"]," | +1.090 |
outp | +1.052 |
Extrem | +1.010 |
cult | +0.971 |
Neg logit contributions | |
�� | -1.279 |
izoph | -1.249 |
="# | -1.145 |
arte | -1.105 |
ム | -1.091 |
Token | officers |
Token ID | 3790 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
�� | +0.049 |
izoph | +0.048 |
="# | +0.044 |
arte | +0.043 |
ム | +0.042 |
Neg logit contributions | |
ocument | -0.044 |
"]," | -0.041 |
outp | -0.039 |
Extrem | -0.038 |
cult | -0.036 |
Token | have |
Token ID | 423 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ocument | +0.427 |
"]," | +0.395 |
outp | +0.380 |
Extrem | +0.367 |
cult | +0.354 |
Neg logit contributions | |
�� | -0.425 |
izoph | -0.414 |
="# | -0.382 |
arte | -0.370 |
ム | -0.361 |
Token | a |
Token ID | 257 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
�� | +1.769 |
izoph | +1.746 |
="# | +1.615 |
arte | +1.555 |
ム | +1.535 |
Neg logit contributions | |
ocument | -1.845 |
"]," | -1.692 |
outp | -1.594 |
Extrem | -1.551 |
cult | -1.526 |
Token | personal |
Token ID | 2614 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
�� | +2.366 |
izoph | +2.322 |
="# | +2.165 |
arte | +2.063 |
ム | +2.036 |
Neg logit contributions | |
ocument | -2.246 |
"]," | -2.087 |
outp | -1.965 |
Extrem | -1.895 |
cult | -1.839 |
Token | relationship |
Token ID | 2776 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
izoph | +2.333 |
�� | +2.327 |
="# | +2.160 |
arte | +2.047 |
wagen | +2.027 |
Neg logit contributions | |
ocument | -2.584 |
"]," | -2.347 |
outp | -2.193 |
Extrem | -2.170 |
cult | -2.135 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
�� | +3.974 |
izoph | +3.908 |
="# | +3.611 |
arte | +3.492 |
ム | +3.419 |
Neg logit contributions | |
ocument | -4.429 |
"]," | -4.109 |
outp | -3.876 |
Extrem | -3.816 |
cult | -3.687 |
Token | some |
Token ID | 617 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
izoph | +8.621 |
�� | +8.410 |
="# | +8.378 |
wagen | +7.846 |
Bowen | +7.759 |
Neg logit contributions | |
ocument | -10.717 |
"]," | -9.618 |
cult | -8.880 |
ocks | -8.804 |
Reviewer | -8.785 |
Token | kind |
Token ID | 1611 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
izoph | +4.604 |
�� | +4.560 |
="# | +4.279 |
arte | +4.004 |
wagen | +4.002 |
Neg logit contributions | |
ocument | -8.411 |
"]," | -7.811 |
outp | -7.282 |
Extrem | -7.280 |
cult | -7.155 |
Token | and |
Token ID | 290 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
�� | +1.891 |
izoph | +1.850 |
="# | +1.709 |
arte | +1.650 |
ム | +1.615 |
Neg logit contributions | |
ocument | -1.887 |
"]," | -1.756 |
outp | -1.672 |
Extrem | -1.625 |
cult | -1.563 |
Token | knew |
Token ID | 2993 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
�� | +2.746 |
izoph | +2.696 |
="# | +2.527 |
arte | +2.447 |
wagen | +2.364 |
Neg logit contributions | |
ocument | -3.005 |
"]," | -2.781 |
outp | -2.639 |
Extrem | -2.567 |
cult | -2.508 |
Token | each |
Token ID | 1123 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
izoph | +4.998 |
�� | +4.961 |
="# | +4.688 |
arte | +4.455 |
Bowen | +4.399 |
Neg logit contributions | |
ocument | -6.489 |
"]," | -6.075 |
outp | -5.756 |
cial | -5.503 |
Extrem | -5.489 |
Token | 104 |
Token ID | 13464 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
�� | +1.695 |
izoph | +1.655 |
="# | +1.558 |
ム | +1.480 |
arte | +1.475 |
Neg logit contributions | |
ocument | -2.006 |
outp | -1.848 |
"]," | -1.845 |
Extrem | -1.760 |
cult | -1.705 |
Token | x |
Token ID | 2124 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
ocument | +1.857 |
"]," | +1.714 |
outp | +1.651 |
Extrem | +1.584 |
cult | +1.522 |
Neg logit contributions | |
�� | -2.129 |
izoph | -2.081 |
="# | -1.915 |
arte | -1.850 |
ム | -1.827 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
�� | +0.202 |
izoph | +0.200 |
="# | +0.189 |
arte | +0.180 |
ム | +0.178 |
Neg logit contributions | |
ocument | -0.201 |
"]," | -0.183 |
outp | -0.179 |
Extrem | -0.172 |
cult | -0.165 |
Token | x |
Token ID | 87 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
�� | +1.086 |
izoph | +1.065 |
="# | +1.006 |
arte | +0.953 |
ム | +0.937 |
Neg logit contributions | |
ocument | -1.480 |
"]," | -1.353 |
outp | -1.342 |
Extrem | -1.301 |
cult | -1.236 |
Token | . |
Token ID | 13 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
="# | +3.784 |
izoph | +3.715 |
�� | +3.524 |
arte | +3.443 |
aster | +3.437 |
Neg logit contributions | |
ocument | -5.431 |
outp | -4.871 |
"]," | -4.737 |
Extrem | -4.631 |
tarians | -4.532 |
Token | x |
Token ID | 87 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
="# | +3.707 |
�� | +3.699 |
izoph | +3.695 |
arte | +3.410 |
aster | +3.408 |
Neg logit contributions | |
ocument | -6.927 |
outp | -6.249 |
"]," | -6.120 |
Extrem | -6.101 |
disclaimer | -5.923 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
="# | +6.998 |
izoph | +6.294 |
ム | +6.151 |
aster | +6.129 |
ENN | +5.901 |
Neg logit contributions | |
ocument | -12.595 |
outp | -11.193 |
tarians | -10.811 |
"]," | -10.724 |
Extrem | -10.623 |
Token | 129 |
Token ID | 18741 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
="# | +4.311 |
izoph | +4.091 |
�� | +4.070 |
aster | +3.706 |
ム | +3.695 |
Neg logit contributions | |
ocument | -13.060 |
outp | -11.582 |
"]," | -11.522 |
Extrem | -11.394 |
Ov | -11.197 |
Token | 144 |
Token ID | 20224 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
izoph | +3.939 |
�� | +3.890 |
="# | +3.735 |
arte | +3.514 |
ENN | +3.513 |
Neg logit contributions | |
ocument | -5.534 |
"]," | -5.020 |
outp | -5.016 |
tarians | -4.789 |
cult | -4.696 |
Token | 23 |
Token ID | 1954 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
�� | +1.659 |
izoph | +1.627 |
="# | +1.541 |
ム | +1.468 |
arte | +1.453 |
Neg logit contributions | |
ocument | -2.165 |
outp | -1.980 |
"]," | -1.951 |
Extrem | -1.883 |
cult | -1.825 |
Token | 15 |
Token ID | 1314 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
ocument | +0.176 |
"]," | +0.161 |
outp | +0.157 |
Extrem | +0.151 |
cult | +0.146 |
Neg logit contributions | |
�� | -0.159 |
izoph | -0.155 |
="# | -0.144 |
arte | -0.138 |
ム | -0.136 |
Token | � |
Token ID | 247 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
�� | +0.178 |
izoph | +0.166 |
="# | +0.141 |
arte | +0.131 |
ム | +0.129 |
Neg logit contributions | |
ocument | -0.477 |
"]," | -0.452 |
outp | -0.442 |
Extrem | -0.433 |
cult | -0.420 |
Token | s |
Token ID | 82 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
�� | +2.337 |
izoph | +2.288 |
="# | +2.136 |
arte | +2.048 |
ム | +2.026 |
Neg logit contributions | |
ocument | -2.782 |
"]," | -2.598 |
outp | -2.448 |
Extrem | -2.433 |
Exhibit | -2.300 |
Token | almost |
Token ID | 2048 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
�� | +2.760 |
izoph | +2.729 |
="# | +2.485 |
arte | +2.371 |
ム | +2.353 |
Neg logit contributions | |
ocument | -3.148 |
"]," | -2.902 |
outp | -2.756 |
Extrem | -2.733 |
cult | -2.622 |
Token | a |
Token ID | 257 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
ocument | +2.915 |
"]," | +2.708 |
outp | +2.630 |
Extrem | +2.480 |
Exhibit | +2.404 |
Neg logit contributions | |
�� | -3.545 |
izoph | -3.443 |
="# | -3.152 |
arte | -3.057 |
ム | -3.050 |
Token | tick |
Token ID | 4378 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ocument | +3.240 |
"]," | +3.017 |
outp | +2.908 |
Extrem | +2.793 |
cult | +2.723 |
Neg logit contributions | |
�� | -3.644 |
izoph | -3.612 |
="# | -3.248 |
arte | -3.179 |
ム | -3.143 |
Token | - |
Token ID | 12 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
�� | +1.884 |
izoph | +1.843 |
="# | +1.704 |
arte | +1.653 |
ム | +1.607 |
Neg logit contributions | |
ocument | -2.152 |
"]," | -2.041 |
outp | -1.935 |
Extrem | -1.899 |
cial | -1.793 |
Token | box |
Token ID | 3524 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
�� | +7.652 |
arte | +7.405 |
izoph | +7.222 |
="# | +7.214 |
aster | +7.118 |
Neg logit contributions | |
ocument | -10.874 |
"]," | -10.444 |
Extrem | -10.362 |
outp | -10.081 |
Ov | -9.671 |
Token | : |
Token ID | 25 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
�� | +0.231 |
izoph | +0.226 |
="# | +0.208 |
arte | +0.201 |
ム | +0.197 |
Neg logit contributions | |
ocument | -0.212 |
"]," | -0.197 |
outp | -0.189 |
Extrem | -0.182 |
cult | -0.175 |
Token | after |
Token ID | 706 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
�� | +0.684 |
izoph | +0.672 |
="# | +0.620 |
arte | +0.593 |
ム | +0.586 |
Neg logit contributions | |
ocument | -0.650 |
"]," | -0.599 |
outp | -0.574 |
Extrem | -0.553 |
cult | -0.537 |
Token | every |
Token ID | 790 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
ocument | +2.411 |
"]," | +2.227 |
outp | +2.161 |
Extrem | +2.062 |
cult | +1.974 |
Neg logit contributions | |
�� | -2.651 |
izoph | -2.585 |
="# | -2.366 |
arte | -2.290 |
ム | -2.252 |
Token | oil |
Token ID | 3056 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ocument | +0.187 |
"]," | +0.172 |
outp | +0.164 |
Extrem | +0.158 |
cult | +0.152 |
Neg logit contributions | |
�� | -0.237 |
izoph | -0.232 |
="# | -0.214 |
arte | -0.207 |
ム | -0.205 |
Token | million |
Token ID | 1510 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ocument | +0.080 |
"]," | +0.074 |
outp | +0.071 |
Extrem | +0.068 |
cult | +0.066 |
Neg logit contributions | |
�� | -0.086 |
izoph | -0.084 |
="# | -0.077 |
arte | -0.074 |
ム | -0.073 |
Token | citizens |
Token ID | 4290 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ocument | +1.728 |
"]," | +1.595 |
outp | +1.541 |
Extrem | +1.474 |
cult | +1.403 |
Neg logit contributions | |
�� | -2.129 |
izoph | -2.080 |
="# | -1.908 |
arte | -1.846 |
ム | -1.827 |
Token | , |
Token ID | 11 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ocument | +2.364 |
"]," | +2.213 |
outp | +2.143 |
Extrem | +2.057 |
cult | +1.984 |
Neg logit contributions | |
�� | -2.220 |
izoph | -2.158 |
="# | -1.953 |
arte | -1.877 |
ム | -1.862 |
Token | five |
Token ID | 1936 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ocument | +2.523 |
"]," | +2.338 |
outp | +2.277 |
Extrem | +2.166 |
cult | +2.075 |
Neg logit contributions | |
�� | -3.003 |
izoph | -2.921 |
="# | -2.684 |
arte | -2.580 |
ム | -2.557 |
Token | out |
Token ID | 503 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ocument | +1.803 |
"]," | +1.670 |
outp | +1.626 |
Extrem | +1.560 |
cult | +1.497 |
Neg logit contributions | |
�� | -1.936 |
izoph | -1.888 |
="# | -1.723 |
arte | -1.660 |
ム | -1.639 |
Token | of |
Token ID | 286 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
�� | +1.796 |
izoph | +1.774 |
="# | +1.704 |
arte | +1.602 |
ム | +1.566 |
Neg logit contributions | |
ocument | -2.148 |
"]," | -1.967 |
outp | -1.904 |
Extrem | -1.865 |
Exhibit | -1.763 |
Token | every |
Token ID | 790 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
�� | +6.545 |
="# | +6.522 |
izoph | +6.508 |
arte | +6.179 |
aster | +6.018 |
Neg logit contributions | |
ocument | -12.293 |
"]," | -11.229 |
outp | -10.647 |
Extrem | -10.614 |
cult | -10.371 |
Token | six |
Token ID | 2237 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
izoph | +5.073 |
�� | +4.937 |
="# | +4.669 |
aster | +4.302 |
arte | +4.289 |
Neg logit contributions | |
ocument | -10.264 |
"]," | -9.414 |
Extrem | -9.071 |
outp | -9.036 |
cult | -8.776 |
Token | of |
Token ID | 286 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
ocument | +1.770 |
"]," | +1.625 |
outp | +1.564 |
Extrem | +1.493 |
cult | +1.419 |
Neg logit contributions | |
�� | -2.398 |
izoph | -2.347 |
="# | -2.164 |
arte | -2.098 |
ム | -2.077 |
Token | the |
Token ID | 262 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
�� | +3.729 |
izoph | +3.648 |
="# | +3.445 |
arte | +3.297 |
aster | +3.237 |
Neg logit contributions | |
ocument | -3.555 |
"]," | -3.294 |
outp | -3.111 |
Extrem | -2.994 |
cult | -2.940 |
Token | roughly |
Token ID | 7323 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
�� | +2.326 |
izoph | +2.316 |
="# | +2.119 |
arte | +2.027 |
ENN | +2.021 |
Neg logit contributions | |
ocument | -2.684 |
"]," | -2.471 |
outp | -2.328 |
Extrem | -2.289 |
cult | -2.235 |
Token | Here |
Token ID | 4342 |
Feature activation | +7.89e-04 |
Pos logit contributions | |
ocument | +0.036 |
"]," | +0.034 |
outp | +0.033 |
Extrem | +0.032 |
cult | +0.030 |
Neg logit contributions | |
�� | -0.031 |
izoph | -0.030 |
="# | -0.028 |
arte | -0.027 |
ム | -0.026 |
Token | 's |
Token ID | 338 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
�� | +0.007 |
izoph | +0.007 |
="# | +0.007 |
arte | +0.006 |
ム | +0.006 |
Neg logit contributions | |
ocument | -0.007 |
"]," | -0.007 |
outp | -0.006 |
Extrem | -0.006 |
cult | -0.006 |
Token | what |
Token ID | 644 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
ocument | +0.936 |
"]," | +0.868 |
outp | +0.839 |
Extrem | +0.807 |
cult | +0.775 |
Neg logit contributions | |
�� | -0.973 |
izoph | -0.949 |
="# | -0.867 |
arte | -0.837 |
ム | -0.826 |
Token | Gunn |
Token ID | 40837 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
izoph | +4.379 |
�� | +4.354 |
="# | +4.053 |
arte | +3.885 |
ENN | +3.806 |
Neg logit contributions | |
ocument | -5.005 |
"]," | -4.817 |
outp | -4.430 |
Extrem | -4.222 |
cult | -4.208 |
Token | had |
Token ID | 550 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
�� | +1.120 |
izoph | +1.094 |
="# | +0.998 |
arte | +0.967 |
ム | +0.938 |
Neg logit contributions | |
ocument | -1.304 |
"]," | -1.222 |
outp | -1.159 |
Extrem | -1.133 |
cial | -1.091 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
izoph | +5.740 |
�� | +5.586 |
="# | +5.096 |
aster | +5.053 |
skinned | +5.006 |
Neg logit contributions | |
ocument | -9.917 |
"]," | -9.573 |
Extrem | -8.786 |
outp | -8.726 |
cult | -8.674 |
Token | say |
Token ID | 910 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
aster | +4.694 |
�� | +4.678 |
izoph | +4.646 |
="# | +4.629 |
arte | +4.399 |
Neg logit contributions | |
ocument | -13.959 |
"]," | -13.375 |
Extrem | -12.943 |
outp | -12.659 |
cult | -12.648 |
Token | in |
Token ID | 287 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
�� | +2.587 |
izoph | +2.573 |
="# | +2.341 |
arte | +2.240 |
aster | +2.205 |
Neg logit contributions | |
ocument | -2.999 |
"]," | -2.832 |
outp | -2.680 |
Extrem | -2.612 |
cult | -2.543 |
Token | his |
Token ID | 465 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
�� | +0.729 |
izoph | +0.713 |
="# | +0.661 |
arte | +0.643 |
ム | +0.632 |
Neg logit contributions | |
ocument | -0.576 |
"]," | -0.526 |
outp | -0.503 |
Extrem | -0.479 |
cult | -0.465 |
Token | post |
Token ID | 1281 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ocument | +1.414 |
"]," | +1.295 |
outp | +1.230 |
Extrem | +1.183 |
cult | +1.135 |
Neg logit contributions | |
�� | -1.847 |
izoph | -1.814 |
="# | -1.673 |
arte | -1.622 |
ム | -1.598 |
Token | : |
Token ID | 25 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ocument | +0.109 |
"]," | +0.101 |
outp | +0.097 |
Extrem | +0.093 |
cult | +0.090 |
Neg logit contributions | |
�� | -0.123 |
izoph | -0.121 |
="# | -0.111 |
arte | -0.107 |
ム | -0.106 |
Token | directing |
Token ID | 21024 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
�� | +1.331 |
izoph | +1.301 |
="# | +1.205 |
arte | +1.164 |
ム | +1.149 |
Neg logit contributions | |
ocument | -1.342 |
"]," | -1.243 |
outp | -1.178 |
Extrem | -1.143 |
cult | -1.109 |
Token | terrorist |
Token ID | 7417 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
�� | +1.013 |
izoph | +0.990 |
="# | +0.918 |
arte | +0.869 |
ム | +0.863 |
Neg logit contributions | |
ocument | -1.018 |
"]," | -0.942 |
outp | -0.894 |
Extrem | -0.853 |
cult | -0.839 |
Token | operatives |
Token ID | 27269 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
ocument | +0.448 |
"]," | +0.412 |
outp | +0.395 |
Extrem | +0.378 |
cult | +0.364 |
Neg logit contributions | |
�� | -0.520 |
izoph | -0.509 |
="# | -0.470 |
arte | -0.452 |
ム | -0.447 |
Token | in |
Token ID | 287 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ocument | +0.442 |
"]," | +0.410 |
outp | +0.395 |
Extrem | +0.379 |
cult | +0.365 |
Neg logit contributions | |
�� | -0.480 |
izoph | -0.469 |
="# | -0.431 |
arte | -0.416 |
ム | -0.410 |
Token | the |
Token ID | 262 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
�� | +1.848 |
izoph | +1.787 |
="# | +1.656 |
ム | +1.562 |
arte | +1.561 |
Neg logit contributions | |
ocument | -2.160 |
"]," | -2.006 |
outp | -1.927 |
Extrem | -1.835 |
cult | -1.810 |
Token | West |
Token ID | 2688 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
�� | +0.145 |
izoph | +0.141 |
="# | +0.127 |
arte | +0.121 |
ム | +0.119 |
Neg logit contributions | |
ocument | -0.197 |
"]," | -0.185 |
outp | -0.179 |
Extrem | -0.173 |
cult | -0.168 |
Token | Bank |
Token ID | 5018 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
izoph | +5.642 |
�� | +4.978 |
="# | +4.778 |
arte | +4.238 |
ム | +4.098 |
Neg logit contributions | |
ocument | -13.519 |
"]," | -12.602 |
outp | -12.389 |
ormons | -12.302 |
tarians | -12.015 |
Token | from |
Token ID | 422 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
�� | +1.586 |
izoph | +1.545 |
="# | +1.433 |
arte | +1.377 |
ム | +1.363 |
Neg logit contributions | |
ocument | -1.464 |
"]," | -1.360 |
outp | -1.302 |
Extrem | -1.246 |
cult | -1.206 |
Token | there |
Token ID | 612 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
�� | +1.286 |
izoph | +1.257 |
="# | +1.156 |
ム | +1.098 |
arte | +1.094 |
Neg logit contributions | |
ocument | -1.360 |
"]," | -1.263 |
outp | -1.207 |
Extrem | -1.155 |
cult | -1.130 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
�� | +3.950 |
izoph | +3.875 |
="# | +3.650 |
arte | +3.499 |
ム | +3.449 |
Neg logit contributions | |
ocument | -3.951 |
"]," | -3.709 |
outp | -3.530 |
Extrem | -3.391 |
cult | -3.273 |
Token | In |
Token ID | 554 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
�� | +2.802 |
izoph | +2.725 |
="# | +2.560 |
arte | +2.450 |
ム | +2.442 |
Neg logit contributions | |
ocument | -3.117 |
"]," | -2.843 |
outp | -2.807 |
Extrem | -2.595 |
cult | -2.589 |
Token | ad |
Token ID | 324 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
�� | +1.922 |
izoph | +1.884 |
arte | +1.637 |
="# | +1.630 |
aster | +1.535 |
Neg logit contributions | |
ocument | -3.775 |
"]," | -3.564 |
outp | -3.460 |
Extrem | -3.405 |
Exhibit | -3.284 |
Token | , |
Token ID | 11 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
�� | +2.863 |
izoph | +2.829 |
="# | +2.606 |
arte | +2.519 |
ENN | +2.471 |
Neg logit contributions | |
ocument | -2.816 |
"]," | -2.611 |
outp | -2.464 |
Extrem | -2.389 |
Exhibit | -2.303 |
Token | this |
Token ID | 428 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
�� | +2.724 |
izoph | +2.668 |
="# | +2.456 |
arte | +2.412 |
ENN | +2.329 |
Neg logit contributions | |
ocument | -2.557 |
"]," | -2.364 |
outp | -2.222 |
Extrem | -2.136 |
cial | -2.064 |
Token | has |
Token ID | 468 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
�� | +1.097 |
izoph | +1.084 |
="# | +0.991 |
arte | +0.957 |
ム | +0.935 |
Neg logit contributions | |
ocument | -1.095 |
"]," | -1.013 |
outp | -0.957 |
Extrem | -0.934 |
cult | -0.902 |
Token | nothing |
Token ID | 2147 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
ocument | +1.190 |
"]," | +1.108 |
outp | +1.072 |
Extrem | +1.031 |
cult | +0.993 |
Neg logit contributions | |
�� | -1.171 |
izoph | -1.143 |
="# | -1.042 |
arte | -1.003 |
ム | -0.990 |
Token | to |
Token ID | 284 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
�� | +5.719 |
izoph | +5.520 |
="# | +5.161 |
arte | +4.971 |
ム | +4.868 |
Neg logit contributions | |
ocument | -7.280 |
"]," | -6.752 |
outp | -6.501 |
Extrem | -6.300 |
cult | -6.046 |
Token | do |
Token ID | 466 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
izoph | +6.307 |
�� | +6.080 |
="# | +5.987 |
arte | +5.702 |
aster | +5.242 |
Neg logit contributions | |
ocument | -13.113 |
outp | -12.003 |
"]," | -11.956 |
Extrem | -11.519 |
ocks | -11.431 |
Token | with |
Token ID | 351 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
�� | +1.221 |
izoph | +1.219 |
="# | +1.160 |
arte | +1.091 |
ム | +1.088 |
Neg logit contributions | |
ocument | -1.384 |
"]," | -1.240 |
outp | -1.220 |
Extrem | -1.169 |
cult | -1.124 |
Token | him |
Token ID | 683 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
�� | +3.007 |
izoph | +2.978 |
="# | +2.703 |
arte | +2.646 |
ENN | +2.572 |
Neg logit contributions | |
ocument | -3.306 |
"]," | -3.028 |
outp | -2.856 |
Extrem | -2.775 |
cult | -2.692 |
Token | . |
Token ID | 13 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
�� | +1.146 |
izoph | +1.121 |
="# | +1.034 |
arte | +0.999 |
ム | +0.984 |
Neg logit contributions | |
ocument | -1.036 |
"]," | -0.962 |
outp | -0.908 |
Extrem | -0.883 |
cult | -0.846 |
Token | He |
Token ID | 679 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
�� | +2.175 |
izoph | +2.127 |
="# | +1.968 |
arte | +1.928 |
ム | +1.859 |
Neg logit contributions | |
ocument | -2.396 |
"]," | -2.196 |
outp | -2.149 |
Extrem | -2.005 |
cult | -1.988 |
Token | fact |
Token ID | 1109 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
�� | +0.354 |
izoph | +0.346 |
="# | +0.319 |
arte | +0.308 |
ム | +0.303 |
Neg logit contributions | |
ocument | -0.318 |
"]," | -0.292 |
outp | -0.274 |
Extrem | -0.265 |
cult | -0.259 |
Token | that |
Token ID | 326 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
�� | +0.169 |
izoph | +0.165 |
="# | +0.151 |
arte | +0.146 |
ム | +0.144 |
Neg logit contributions | |
ocument | -0.155 |
"]," | -0.144 |
outp | -0.139 |
Extrem | -0.133 |
cult | -0.128 |
Token | roughly |
Token ID | 7323 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
ocument | +1.041 |
"]," | +0.962 |
outp | +0.921 |
Extrem | +0.885 |
cult | +0.857 |
Neg logit contributions | |
�� | -1.131 |
izoph | -1.107 |
="# | -1.017 |
arte | -0.978 |
ム | -0.967 |
Token | two |
Token ID | 734 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
ocument | +5.267 |
"]," | +5.015 |
outp | +4.950 |
Extrem | +4.659 |
Exhibit | +4.482 |
Neg logit contributions | |
�� | -6.418 |
izoph | -6.172 |
="# | -5.574 |
arte | -5.477 |
ム | -5.418 |
Token | out |
Token ID | 503 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
ocument | +0.286 |
"]," | +0.266 |
outp | +0.257 |
Extrem | +0.246 |
cult | +0.236 |
Neg logit contributions | |
�� | -0.328 |
izoph | -0.321 |
="# | -0.294 |
arte | -0.285 |
ム | -0.281 |
Token | of |
Token ID | 286 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
�� | +1.969 |
izoph | +1.937 |
="# | +1.891 |
arte | +1.755 |
ム | +1.731 |
Neg logit contributions | |
ocument | -2.457 |
"]," | -2.222 |
outp | -2.166 |
Extrem | -2.127 |
disclaimer | -2.008 |
Token | every |
Token ID | 790 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
�� | +6.905 |
="# | +6.842 |
izoph | +6.726 |
arte | +6.095 |
aster | +6.091 |
Neg logit contributions | |
ocument | -12.126 |
"]," | -10.935 |
ionics | -10.191 |
Extrem | -10.116 |
outp | -10.106 |
Token | five |
Token ID | 1936 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
izoph | +6.063 |
�� | +6.010 |
="# | +5.928 |
aster | +5.382 |
ENN | +5.249 |
Neg logit contributions | |
ocument | -9.681 |
"]," | -8.682 |
Extrem | -8.126 |
cult | -8.046 |
ionics | -8.035 |
Token | Americans |
Token ID | 3399 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
�� | +2.239 |
izoph | +2.189 |
="# | +2.040 |
arte | +1.951 |
ム | +1.937 |
Neg logit contributions | |
ocument | -1.916 |
"]," | -1.747 |
outp | -1.634 |
Extrem | -1.560 |
cult | -1.555 |
Token | knows |
Token ID | 4206 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ocument | +1.226 |
"]," | +1.135 |
outp | +1.092 |
Extrem | +1.055 |
cult | +1.014 |
Neg logit contributions | |
�� | -1.253 |
izoph | -1.224 |
="# | -1.126 |
arte | -1.082 |
ム | -1.066 |
Token | about |
Token ID | 546 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
�� | +2.281 |
izoph | +2.237 |
="# | +2.090 |
arte | +1.980 |
ム | +1.957 |
Neg logit contributions | |
ocument | -2.435 |
"]," | -2.252 |
outp | -2.149 |
Extrem | -2.038 |
cult | -2.019 |
Token | t |
Token ID | 83 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ocument | +0.981 |
"]," | +0.909 |
outp | +0.876 |
Extrem | +0.842 |
cult | +0.809 |
Neg logit contributions | |
�� | -1.056 |
izoph | -1.032 |
="# | -0.946 |
arte | -0.913 |
ム | -0.901 |
Token | be |
Token ID | 307 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
ocument | +2.835 |
"]," | +2.638 |
outp | +2.556 |
Extrem | +2.442 |
cult | +2.333 |
Neg logit contributions | |
�� | -3.121 |
izoph | -3.049 |
="# | -2.768 |
arte | -2.676 |
ム | -2.647 |
Token | spent |
Token ID | 3377 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
ocument | +0.564 |
"]," | +0.522 |
outp | +0.502 |
Extrem | +0.484 |
cult | +0.466 |
Neg logit contributions | |
�� | -0.605 |
izoph | -0.590 |
="# | -0.542 |
arte | -0.523 |
ム | -0.517 |
Token | with |
Token ID | 351 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ocument | +0.036 |
"]," | +0.033 |
outp | +0.032 |
Extrem | +0.031 |
cult | +0.030 |
Neg logit contributions | |
�� | -0.036 |
izoph | -0.035 |
="# | -0.032 |
arte | -0.031 |
ム | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ocument | +2.471 |
"]," | +2.304 |
outp | +2.235 |
Extrem | +2.151 |
cult | +2.049 |
Neg logit contributions | |
�� | -2.603 |
izoph | -2.538 |
="# | -2.310 |
arte | -2.229 |
ム | -2.206 |
Token | warm |
Token ID | 5814 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ocument | +3.794 |
"]," | +3.528 |
outp | +3.451 |
Extrem | +3.288 |
cult | +3.167 |
Neg logit contributions | |
�� | -4.372 |
izoph | -4.261 |
="# | -3.874 |
arte | -3.773 |
ム | -3.728 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
�� | +9.706 |
izoph | +8.995 |
aster | +8.701 |
="# | +8.642 |
arte | +8.494 |
Neg logit contributions | |
ocument | -9.405 |
"]," | -8.478 |
Exhibit | -8.045 |
tarians | -7.992 |
Extrem | -7.916 |
Token | engaging |
Token ID | 11932 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
�� | +1.673 |
izoph | +1.634 |
="# | +1.473 |
arte | +1.411 |
ム | +1.406 |
Neg logit contributions | |
ocument | -1.882 |
"]," | -1.744 |
outp | -1.656 |
Extrem | -1.631 |
cult | -1.579 |
Token | brilliant |
Token ID | 10457 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
ocument | +1.440 |
"]," | +1.326 |
outp | +1.272 |
Extrem | +1.225 |
cult | +1.178 |
Neg logit contributions | |
�� | -1.641 |
izoph | -1.604 |
="# | -1.477 |
arte | -1.424 |
ム | -1.404 |
Token | young |
Token ID | 1862 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ocument | +0.730 |
"]," | +0.674 |
outp | +0.647 |
Extrem | +0.623 |
cult | +0.601 |
Neg logit contributions | |
�� | -0.799 |
izoph | -0.782 |
="# | -0.718 |
arte | -0.693 |
ム | -0.682 |
Token | man |
Token ID | 582 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ocument | +1.071 |
"]," | +0.988 |
outp | +0.949 |
Extrem | +0.910 |
cult | +0.873 |
Neg logit contributions | |
�� | -1.278 |
izoph | -1.251 |
="# | -1.151 |
arte | -1.114 |
ム | -1.099 |
Token | make |
Token ID | 787 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ocument | +0.839 |
"]," | +0.781 |
outp | +0.749 |
Extrem | +0.716 |
cult | +0.695 |
Neg logit contributions | |
�� | -0.886 |
izoph | -0.872 |
="# | -0.797 |
arte | -0.769 |
ム | -0.758 |
Token | US |
Token ID | 1294 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
izoph | +1.468 |
�� | +1.467 |
="# | +1.334 |
arte | +1.292 |
ム | +1.262 |
Neg logit contributions | |
ocument | -1.402 |
"]," | -1.311 |
outp | -1.226 |
Extrem | -1.173 |
cult | -1.153 |
Token | generals |
Token ID | 26770 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ocument | +2.887 |
"]," | +2.625 |
outp | +2.552 |
Extrem | +2.445 |
cial | +2.319 |
Neg logit contributions | |
�� | -3.874 |
izoph | -3.768 |
="# | -3.478 |
arte | -3.402 |
ム | -3.364 |
Token | sit |
Token ID | 1650 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ocument | +1.973 |
"]," | +1.830 |
outp | +1.767 |
Extrem | +1.688 |
cult | +1.620 |
Neg logit contributions | |
�� | -2.380 |
izoph | -2.320 |
="# | -2.121 |
arte | -2.055 |
ム | -2.043 |
Token | up |
Token ID | 510 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
�� | +1.574 |
izoph | +1.562 |
="# | +1.424 |
arte | +1.364 |
wagen | +1.331 |
Neg logit contributions | |
ocument | -1.886 |
"]," | -1.767 |
outp | -1.709 |
Extrem | -1.647 |
cial | -1.605 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
�� | +5.479 |
izoph | +5.358 |
="# | +4.743 |
skinned | +4.662 |
robe | +4.624 |
Neg logit contributions | |
ocument | -7.383 |
"]," | -7.080 |
outp | -6.592 |
Extrem | -6.496 |
cult | -6.282 |
Token | listen |
Token ID | 6004 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
izoph | +8.224 |
="# | +7.739 |
�� | +7.654 |
arte | +7.338 |
robe | +7.336 |
Neg logit contributions | |
ocument | -10.423 |
"]," | -9.391 |
Extrem | -9.006 |
Reviewer | -8.770 |
outp | -8.742 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
�� | +2.239 |
izoph | +2.202 |
="# | +2.023 |
arte | +1.929 |
ム | +1.905 |
Neg logit contributions | |
ocument | -2.306 |
"]," | -2.190 |
outp | -2.084 |
Extrem | -2.015 |
cial | -1.932 |
Token | The |
Token ID | 383 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
ocument | +1.654 |
"]," | +1.536 |
outp | +1.486 |
Extrem | +1.425 |
cult | +1.376 |
Neg logit contributions | |
�� | -1.662 |
izoph | -1.623 |
="# | -1.485 |
arte | -1.430 |
ム | -1.413 |
Token | stakes |
Token ID | 21147 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
ocument | +0.742 |
"]," | +0.687 |
outp | +0.655 |
Extrem | +0.629 |
cult | +0.606 |
Neg logit contributions | |
�� | -0.875 |
izoph | -0.859 |
="# | -0.788 |
arte | -0.762 |
ム | -0.752 |
Token | for |
Token ID | 329 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ocument | +0.520 |
"]," | +0.483 |
outp | +0.466 |
Extrem | +0.450 |
cult | +0.434 |
Neg logit contributions | |
�� | -0.493 |
izoph | -0.481 |
="# | -0.439 |
arte | -0.423 |
ム | -0.416 |
Token | c |
Token ID | 66 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
�� | +4.877 |
izoph | +4.729 |
="# | +4.340 |
arte | +4.146 |
ム | +4.087 |
Neg logit contributions | |
ocument | -6.629 |
"]," | -6.230 |
outp | -5.902 |
Extrem | -5.824 |
Exhibit | -5.569 |
Token | is |
Token ID | 318 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ocument | +0.051 |
"]," | +0.047 |
outp | +0.045 |
Extrem | +0.044 |
cult | +0.042 |
Neg logit contributions | |
�� | -0.052 |
izoph | -0.050 |
="# | -0.046 |
arte | -0.045 |
ム | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
�� | +3.093 |
izoph | +3.045 |
="# | +2.808 |
arte | +2.695 |
aster | +2.656 |
Neg logit contributions | |
ocument | -3.077 |
"]," | -2.836 |
outp | -2.620 |
Extrem | -2.563 |
cult | -2.522 |
Token | mega |
Token ID | 23465 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
�� | +5.950 |
izoph | +5.775 |
="# | +5.432 |
arte | +5.200 |
aster | +5.108 |
Neg logit contributions | |
ocument | -5.929 |
"]," | -5.477 |
outp | -5.099 |
Extrem | -4.821 |
cult | -4.782 |
Token | - |
Token ID | 12 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
�� | +4.011 |
izoph | +3.897 |
="# | +3.607 |
arte | +3.511 |
ム | +3.425 |
Neg logit contributions | |
ocument | -4.249 |
"]," | -3.954 |
outp | -3.742 |
Extrem | -3.604 |
cult | -3.514 |
Token | Earth |
Token ID | 22840 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
�� | +3.341 |
izoph | +3.182 |
="# | +2.899 |
arte | +2.881 |
aster | +2.766 |
Neg logit contributions | |
ocument | -5.239 |
"]," | -4.916 |
outp | -4.795 |
Extrem | -4.622 |
Exhibit | -4.495 |
Token | also |
Token ID | 635 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
�� | +8.718 |
izoph | +8.459 |
="# | +8.027 |
wagen | +7.815 |
aster | +7.754 |
Neg logit contributions | |
ocument | -9.929 |
"]," | -9.048 |
Extrem | -8.173 |
cult | -8.111 |
Fla | -8.055 |
Token | has |
Token ID | 468 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ocument | +2.000 |
"]," | +1.860 |
outp | +1.802 |
Extrem | +1.726 |
cult | +1.659 |
Neg logit contributions | |
�� | -2.081 |
izoph | -2.034 |
="# | -1.853 |
arte | -1.790 |
ム | -1.765 |
Token | profound |
Token ID | 11982 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
�� | +1.881 |
izoph | +1.863 |
="# | +1.722 |
ム | +1.647 |
arte | +1.642 |
Neg logit contributions | |
ocument | -1.746 |
"]," | -1.590 |
outp | -1.509 |
Extrem | -1.468 |
cult | -1.438 |
Token | implications |
Token ID | 10939 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
�� | +1.422 |
izoph | +1.408 |
="# | +1.298 |
arte | +1.249 |
ム | +1.242 |
Neg logit contributions | |
ocument | -1.299 |
"]," | -1.176 |
outp | -1.120 |
Extrem | -1.092 |
cult | -1.055 |
Token | for |
Token ID | 329 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
ocument | +0.732 |
"]," | +0.677 |
outp | +0.654 |
Extrem | +0.626 |
cult | +0.601 |
Neg logit contributions | |
�� | -0.857 |
izoph | -0.837 |
="# | -0.767 |
arte | -0.742 |
ム | -0.733 |
Token | and |
Token ID | 290 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
ocument | +2.255 |
"]," | +2.045 |
outp | +2.037 |
Extrem | +1.850 |
cult | +1.814 |
Neg logit contributions | |
�� | -3.243 |
izoph | -3.219 |
="# | -2.925 |
arte | -2.813 |
ム | -2.795 |
Token | elected |
Token ID | 7018 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
ocument | +0.542 |
"]," | +0.495 |
outp | +0.473 |
Extrem | +0.455 |
cult | +0.436 |
Neg logit contributions | |
�� | -0.672 |
izoph | -0.658 |
="# | -0.608 |
arte | -0.588 |
ム | -0.579 |
Token | officials |
Token ID | 2828 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
�� | +0.787 |
izoph | +0.773 |
="# | +0.726 |
arte | +0.702 |
ム | +0.686 |
Neg logit contributions | |
ocument | -0.602 |
"]," | -0.556 |
outp | -0.522 |
Extrem | -0.506 |
cult | -0.484 |
Token | are |
Token ID | 389 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ocument | +0.416 |
"]," | +0.385 |
outp | +0.370 |
Extrem | +0.359 |
cult | +0.345 |
Neg logit contributions | |
�� | -0.401 |
izoph | -0.391 |
="# | -0.361 |
arte | -0.348 |
ム | -0.340 |
Token | up |
Token ID | 510 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
�� | +1.139 |
izoph | +1.113 |
="# | +1.037 |
arte | +0.985 |
ム | +0.972 |
Neg logit contributions | |
ocument | -1.221 |
"]," | -1.122 |
Extrem | -1.046 |
outp | -1.038 |
cult | -1.007 |
Token | in |
Token ID | 287 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
�� | +1.368 |
izoph | +1.332 |
="# | +1.220 |
arte | +1.180 |
ム | +1.155 |
Neg logit contributions | |
ocument | -1.424 |
"]," | -1.327 |
outp | -1.270 |
Extrem | -1.227 |
cult | -1.181 |
Token | arms |
Token ID | 5101 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
�� | +9.508 |
izoph | +8.727 |
="# | +8.147 |
arte | +8.143 |
yden | +8.057 |
Neg logit contributions | |
ocument | -9.815 |
"]," | -8.602 |
cult | -8.137 |
iquette | -8.080 |
Reviewer | -7.942 |
Token | again |
Token ID | 757 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ocument | +1.766 |
"]," | +1.635 |
outp | +1.586 |
Extrem | +1.513 |
cult | +1.451 |
Neg logit contributions | |
�� | -2.025 |
izoph | -1.978 |
="# | -1.813 |
arte | -1.752 |
ム | -1.732 |
Token | over |
Token ID | 625 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
ocument | +1.172 |
"]," | +1.081 |
outp | +1.042 |
Extrem | +0.997 |
cult | +0.956 |
Neg logit contributions | |
�� | -1.396 |
izoph | -1.366 |
="# | -1.255 |
arte | -1.214 |
ム | -1.199 |
Token | a |
Token ID | 257 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
�� | +0.185 |
izoph | +0.181 |
="# | +0.165 |
arte | +0.159 |
ム | +0.157 |
Neg logit contributions | |
ocument | -0.183 |
"]," | -0.169 |
outp | -0.162 |
Extrem | -0.157 |
cult | -0.152 |
Token | health |
Token ID | 1535 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ocument | +1.174 |
"]," | +1.091 |
outp | +1.056 |
Extrem | +1.014 |
cult | +0.973 |
Neg logit contributions | |
�� | -1.249 |
izoph | -1.220 |
="# | -1.114 |
arte | -1.076 |
ム | -1.062 |
Token | We |
Token ID | 1135 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
�� | +0.529 |
izoph | +0.512 |
="# | +0.475 |
arte | +0.451 |
ム | +0.447 |
Neg logit contributions | |
ocument | -0.631 |
"]," | -0.587 |
outp | -0.575 |
Extrem | -0.552 |
cult | -0.530 |
Token | need |
Token ID | 761 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
�� | +1.146 |
izoph | +1.127 |
="# | +1.027 |
arte | +0.982 |
ム | +0.970 |
Neg logit contributions | |
ocument | -1.299 |
"]," | -1.215 |
outp | -1.172 |
Extrem | -1.123 |
cult | -1.092 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ocument | +1.467 |
"]," | +1.358 |
outp | +1.311 |
Extrem | +1.264 |
cult | +1.219 |
Neg logit contributions | |
�� | -1.388 |
izoph | -1.358 |
="# | -1.251 |
arte | -1.196 |
ム | -1.181 |
Token | be |
Token ID | 307 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ocument | +0.994 |
"]," | +0.911 |
outp | +0.881 |
Extrem | +0.850 |
cult | +0.817 |
Neg logit contributions | |
�� | -0.976 |
izoph | -0.957 |
="# | -0.885 |
arte | -0.848 |
ム | -0.835 |
Token | smart |
Token ID | 4451 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ocument | +5.679 |
"]," | +5.423 |
outp | +5.322 |
Extrem | +4.937 |
cial | +4.750 |
Neg logit contributions | |
�� | -12.666 |
izoph | -11.999 |
arte | -11.101 |
ム | -11.002 |
artney | -10.941 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ocument | +4.454 |
"]," | +4.186 |
outp | +4.021 |
Extrem | +3.800 |
cult | +3.584 |
Neg logit contributions | |
�� | -8.045 |
izoph | -7.870 |
="# | -7.090 |
ム | -7.042 |
arte | -6.933 |
Token | vigilant |
Token ID | 30257 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
ocument | +4.011 |
"]," | +3.596 |
outp | +3.193 |
Extrem | +3.135 |
naturally | +2.416 |
Neg logit contributions | |
�� | -23.912 |
izoph | -22.701 |
ム | -21.796 |
�� | -21.038 |
arte | -20.987 |
Token | and |
Token ID | 290 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
ocument | +4.621 |
"]," | +4.436 |
outp | +4.271 |
Extrem | +4.044 |
cult | +3.881 |
Neg logit contributions | |
�� | -6.638 |
izoph | -6.380 |
="# | -5.641 |
ム | -5.545 |
arte | -5.491 |
Token | tough |
Token ID | 5802 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
ocument | +3.025 |
"]," | +2.899 |
outp | +2.824 |
Extrem | +2.656 |
cult | +2.478 |
Neg logit contributions | |
�� | -4.735 |
izoph | -4.576 |
="# | -4.177 |
arte | -4.157 |
ム | -4.099 |
Token | . |
Token ID | 13 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
ocument | +2.807 |
"]," | +2.582 |
outp | +2.460 |
Extrem | +2.455 |
cial | +2.245 |
Neg logit contributions | |
�� | -4.181 |
izoph | -4.015 |
="# | -3.668 |
arte | -3.611 |
ム | -3.557 |
Token | We |
Token ID | 775 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ocument | +4.614 |
"]," | +4.428 |
Extrem | +4.353 |
outp | +4.169 |
Exhibit | +3.929 |
Neg logit contributions | |
�� | -5.768 |
izoph | -5.682 |
="# | -4.989 |
arte | -4.959 |
ム | -4.824 |
Token | and |
Token ID | 290 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
ocument | +0.983 |
"]," | +0.911 |
outp | +0.879 |
Extrem | +0.846 |
cult | +0.813 |
Neg logit contributions | |
�� | -1.038 |
izoph | -1.014 |
="# | -0.929 |
arte | -0.897 |
ム | -0.885 |
Token | explore |
Token ID | 7301 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ocument | +2.471 |
"]," | +2.280 |
outp | +2.147 |
Extrem | +2.006 |
cult | +1.950 |
Neg logit contributions | |
�� | -4.358 |
izoph | -4.195 |
="# | -3.919 |
arte | -3.787 |
ム | -3.776 |
Token | the |
Token ID | 262 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ocument | +1.049 |
"]," | +0.971 |
outp | +0.940 |
Extrem | +0.905 |
cult | +0.871 |
Neg logit contributions | |
�� | -1.031 |
izoph | -1.009 |
="# | -0.927 |
arte | -0.892 |
ム | -0.879 |
Token | world |
Token ID | 995 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
ocument | +1.931 |
"]," | +1.776 |
outp | +1.705 |
Extrem | +1.595 |
cult | +1.522 |
Neg logit contributions | |
�� | -3.349 |
izoph | -3.264 |
="# | -3.023 |
arte | -2.943 |
ム | -2.921 |
Token | with |
Token ID | 351 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
ocument | +3.620 |
"]," | +3.434 |
outp | +3.264 |
Extrem | +3.095 |
Exhibit | +2.991 |
Neg logit contributions | |
�� | -5.191 |
izoph | -4.994 |
="# | -4.508 |
arte | -4.386 |
wagen | -4.361 |
Token | kindred |
Token ID | 46449 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ocument | +3.417 |
"]," | +3.097 |
outp | +2.984 |
Extrem | +2.816 |
cult | +2.635 |
Neg logit contributions | |
�� | -6.650 |
izoph | -6.488 |
="# | -5.943 |
arte | -5.809 |
ム | -5.791 |
Token | spirits |
Token ID | 13747 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
outp | +2.613 |
"]," | +2.202 |
ocument | +1.681 |
cult | +1.536 |
Extrem | +1.395 |
Neg logit contributions | |
�� | -24.236 |
izoph | -22.820 |
�� | -21.536 |
arte | -21.478 |
wagen | -21.286 |
Token | . |
Token ID | 13 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
izoph | +1.096 |
�� | +1.093 |
="# | +1.044 |
arte | +0.993 |
ム | +0.986 |
Neg logit contributions | |
ocument | -1.216 |
"]," | -1.096 |
outp | -1.095 |
Extrem | -1.040 |
cult | -0.996 |
Token |
|
Token ID | 198 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
�� | +2.226 |
izoph | +2.148 |
="# | +2.116 |
arte | +1.986 |
ム | +1.966 |
Neg logit contributions | |
ocument | -3.162 |
outp | -2.849 |
"]," | -2.823 |
Extrem | -2.668 |
tarians | -2.655 |
Token |
|
Token ID | 198 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
�� | +0.580 |
izoph | +0.569 |
="# | +0.540 |
arte | +0.511 |
ム | +0.505 |
Neg logit contributions | |
ocument | -0.719 |
"]," | -0.648 |
outp | -0.645 |
Extrem | -0.617 |
cult | -0.596 |
Token | Sign |
Token ID | 11712 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ocument | +0.392 |
"]," | +0.352 |
outp | +0.350 |
Extrem | +0.327 |
cult | +0.313 |
Neg logit contributions | |
�� | -0.470 |
izoph | -0.458 |
="# | -0.428 |
arte | -0.421 |
ム | -0.413 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
izoph | +1.177 |
�� | +1.165 |
="# | +1.120 |
arte | +1.037 |
ム | +1.031 |
Neg logit contributions | |
ocument | -1.562 |
"]," | -1.410 |
outp | -1.365 |
Extrem | -1.327 |
cult | -1.296 |
Token | j |
Token ID | 474 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
izoph | +1.142 |
�� | +1.121 |
="# | +1.081 |
arte | +0.976 |
wagen | +0.970 |
Neg logit contributions | |
ocument | -1.626 |
"]," | -1.486 |
outp | -1.422 |
Extrem | -1.408 |
cult | -1.365 |
Token | agg |
Token ID | 9460 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ocument | +0.941 |
"]," | +0.878 |
outp | +0.855 |
Extrem | +0.836 |
cult | +0.803 |
Neg logit contributions | |
�� | -0.676 |
izoph | -0.668 |
="# | -0.605 |
arte | -0.576 |
ム | -0.562 |
Token | ies |
Token ID | 444 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
ocument | +3.066 |
"]," | +2.855 |
outp | +2.703 |
Extrem | +2.516 |
cial | +2.497 |
Neg logit contributions | |
�� | -4.692 |
izoph | -4.518 |
="# | -4.108 |
arte | -4.049 |
ム | -3.987 |
Token | since |
Token ID | 1201 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
"]," | +3.356 |
ocument | +3.285 |
outp | +3.230 |
Extrem | +2.758 |
Exhibit | +2.563 |
Neg logit contributions | |
�� | -10.480 |
izoph | -10.384 |
="# | -9.297 |
ム | -9.168 |
arte | -9.138 |
Token | even |
Token ID | 772 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ocument | +3.974 |
"]," | +3.801 |
outp | +3.733 |
Extrem | +3.585 |
cult | +3.478 |
Neg logit contributions | |
�� | -2.296 |
izoph | -2.195 |
="# | -1.911 |
arte | -1.805 |
ム | -1.783 |
Token | though |
Token ID | 996 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
outp | +5.612 |
ocument | +4.611 |
"]," | +4.592 |
Exhibit | +4.236 |
Extrem | +4.231 |
Neg logit contributions | |
�� | -19.634 |
izoph | -18.711 |
ム | -17.587 |
arte | -17.315 |
="# | -17.271 |
Token | they |
Token ID | 484 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
ocument | +3.571 |
"]," | +3.330 |
outp | +3.184 |
Extrem | +2.986 |
cult | +2.856 |
Neg logit contributions | |
�� | -5.919 |
izoph | -5.748 |
="# | -5.192 |
arte | -5.176 |
ム | -5.091 |
Token | are |
Token ID | 389 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ocument | +0.677 |
"]," | +0.628 |
outp | +0.608 |
Extrem | +0.592 |
cult | +0.571 |
Neg logit contributions | |
�� | -0.555 |
izoph | -0.543 |
="# | -0.500 |
arte | -0.478 |
ム | -0.469 |
Token | there |
Token ID | 612 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ocument | +1.621 |
"]," | +1.526 |
outp | +1.481 |
Extrem | +1.445 |
cult | +1.403 |
Neg logit contributions | |
�� | -0.915 |
izoph | -0.887 |
="# | -0.793 |
arte | -0.746 |
ム | -0.732 |
Token | at |
Token ID | 379 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
ocument | +1.431 |
"]," | +1.313 |
outp | +1.261 |
Extrem | +1.217 |
cult | +1.169 |
Neg logit contributions | |
�� | -1.593 |
izoph | -1.565 |
="# | -1.448 |
arte | -1.395 |
ム | -1.370 |
Token | young |
Token ID | 1862 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ocument | +0.633 |
"]," | +0.582 |
outp | +0.554 |
Extrem | +0.532 |
cult | +0.511 |
Neg logit contributions | |
�� | -0.760 |
izoph | -0.745 |
="# | -0.689 |
arte | -0.664 |
ム | -0.656 |
Token | voters |
Token ID | 4446 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ocument | +1.099 |
"]," | +1.014 |
outp | +0.973 |
Extrem | +0.934 |
cult | +0.897 |
Neg logit contributions | |
�� | -1.293 |
izoph | -1.265 |
="# | -1.165 |
arte | -1.127 |
ム | -1.112 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ocument | +1.194 |
"]," | +1.102 |
outp | +1.062 |
Extrem | +1.018 |
cult | +0.976 |
Neg logit contributions | |
�� | -1.408 |
izoph | -1.376 |
="# | -1.265 |
arte | -1.223 |
ム | -1.208 |
Token | says |
Token ID | 1139 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
ocument | +2.117 |
"]," | +1.967 |
outp | +1.908 |
Extrem | +1.830 |
cult | +1.751 |
Neg logit contributions | |
�� | -2.318 |
izoph | -2.266 |
="# | -2.070 |
arte | -1.999 |
ム | -1.974 |
Token | D |
Token ID | 360 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ocument | +4.987 |
"]," | +4.739 |
outp | +4.597 |
Extrem | +4.435 |
Exhibit | +4.269 |
Neg logit contributions | |
�� | -5.452 |
izoph | -5.314 |
="# | -4.791 |
wagen | -4.591 |
arte | -4.590 |
Token | ella |
Token ID | 12627 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ocument | +2.484 |
"]," | +2.327 |
outp | +2.241 |
Extrem | +2.151 |
cult | +2.102 |
Neg logit contributions | |
�� | -2.147 |
izoph | -2.078 |
="# | -1.871 |
ム | -1.785 |
arte | -1.781 |
Token | Vol |
Token ID | 4709 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
"]," | +4.282 |
Extrem | +3.661 |
ocument | +3.479 |
Ov | +3.348 |
Exhibit | +2.970 |
Neg logit contributions | |
�� | -21.020 |
izoph | -19.838 |
�� | -18.494 |
artney | -17.924 |
skinned | -17.795 |
Token | pe |
Token ID | 431 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
ocument | +3.058 |
"]," | +2.895 |
outp | +2.798 |
Extrem | +2.660 |
cult | +2.633 |
Neg logit contributions | |
�� | -2.640 |
izoph | -2.556 |
="# | -2.253 |
ム | -2.162 |
ENN | -2.141 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ocument | +2.354 |
"]," | +2.129 |
outp | +2.104 |
Extrem | +1.969 |
Exhibit | +1.897 |
Neg logit contributions | |
�� | -3.521 |
izoph | -3.462 |
="# | -3.190 |
arte | -3.087 |
ム | -3.083 |
Token | At |
Token ID | 1629 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
ocument | +1.179 |
"]," | +1.090 |
outp | +1.057 |
Extrem | +1.008 |
cult | +0.979 |
Neg logit contributions | |
�� | -1.169 |
izoph | -1.139 |
="# | -1.048 |
arte | -1.008 |
ム | -0.993 |
Token | worse |
Token ID | 4785 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
�� | +0.416 |
izoph | +0.405 |
="# | +0.374 |
arte | +0.364 |
ム | +0.355 |
Neg logit contributions | |
ocument | -0.384 |
"]," | -0.353 |
outp | -0.338 |
Extrem | -0.325 |
cult | -0.315 |
Token | how |
Token ID | 703 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ocument | +4.046 |
"]," | +3.818 |
outp | +3.678 |
Extrem | +3.512 |
cult | +3.339 |
Neg logit contributions | |
�� | -5.082 |
izoph | -4.946 |
="# | -4.451 |
ム | -4.417 |
arte | -4.342 |
Token | easy |
Token ID | 2562 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
ocument | +3.148 |
"]," | +2.977 |
outp | +2.901 |
Extrem | +2.776 |
cult | +2.680 |
Neg logit contributions | |
�� | -2.805 |
izoph | -2.715 |
="# | -2.445 |
arte | -2.338 |
ム | -2.335 |
Token | it |
Token ID | 340 |
Feature activation | -8.71e-03 |
Pos logit contributions | |
ocument | +3.533 |
"]," | +3.333 |
outp | +3.221 |
Extrem | +3.093 |
cult | +2.993 |
Neg logit contributions | |
�� | -3.566 |
izoph | -3.438 |
="# | -3.094 |
arte | -3.000 |
ム | -2.982 |
Token | is |
Token ID | 318 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
ocument | +0.084 |
"]," | +0.077 |
outp | +0.074 |
Extrem | +0.072 |
cult | +0.070 |
Neg logit contributions | |
�� | -0.076 |
izoph | -0.075 |
="# | -0.070 |
arte | -0.067 |
ム | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -8.50e-03 |
Pos logit contributions | |
ocument | +0.352 |
"]," | +0.324 |
outp | +0.313 |
Extrem | +0.304 |
cult | +0.292 |
Neg logit contributions | |
�� | -0.309 |
izoph | -0.306 |
="# | -0.283 |
arte | -0.271 |
ム | -0.266 |
Token | game |
Token ID | 983 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ocument | +0.075 |
"]," | +0.068 |
outp | +0.066 |
Extrem | +0.064 |
cult | +0.061 |
Neg logit contributions | |
�� | -0.082 |
izoph | -0.081 |
="# | -0.075 |
arte | -0.072 |
ム | -0.071 |
Token | Amazon |
Token ID | 6186 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
"]," | +5.465 |
ocument | +4.975 |
outp | +4.824 |
Extrem | +4.339 |
Exhibit | +4.159 |
Neg logit contributions | |
�� | -17.312 |
izoph | -16.986 |
�� | -15.210 |
="# | -15.103 |
ム | -15.056 |
Token | , |
Token ID | 11 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ocument | +3.912 |
"]," | +3.785 |
outp | +3.490 |
Extrem | +3.331 |
cial | +3.165 |
Neg logit contributions | |
�� | -6.982 |
izoph | -6.717 |
="# | -6.023 |
arte | -5.968 |
wagen | -5.943 |
Token | we |
Token ID | 356 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ocument | +2.345 |
"]," | +2.173 |
outp | +2.093 |
Extrem | +2.002 |
cult | +1.917 |
Neg logit contributions | |
�� | -2.957 |
izoph | -2.881 |
="# | -2.637 |
arte | -2.556 |
ム | -2.534 |
Token | spent |
Token ID | 3377 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
�� | +1.538 |
izoph | +1.524 |
="# | +1.393 |
arte | +1.355 |
ム | +1.341 |
Neg logit contributions | |
ocument | -1.220 |
"]," | -1.133 |
outp | -1.081 |
Extrem | -1.039 |
Exhibit | -0.988 |
Token | a |
Token ID | 257 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ocument | +0.250 |
"]," | +0.228 |
outp | +0.221 |
Extrem | +0.214 |
cult | +0.207 |
Neg logit contributions | |
�� | -0.229 |
izoph | -0.226 |
="# | -0.208 |
arte | -0.200 |
ム | -0.197 |
Token | to |
Token ID | 284 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ocument | +2.778 |
"]," | +2.544 |
outp | +2.498 |
Extrem | +2.350 |
cult | +2.301 |
Neg logit contributions | |
�� | -3.450 |
izoph | -3.391 |
="# | -2.987 |
arte | -2.955 |
ム | -2.909 |
Token | get |
Token ID | 651 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ocument | +1.142 |
"]," | +1.069 |
outp | +1.036 |
Extrem | +1.000 |
cult | +0.966 |
Neg logit contributions | |
�� | -0.974 |
izoph | -0.947 |
="# | -0.855 |
arte | -0.822 |
ム | -0.810 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ocument | +2.172 |
"]," | +2.004 |
outp | +1.989 |
Extrem | +1.875 |
cult | +1.793 |
Neg logit contributions | |
�� | -2.696 |
izoph | -2.628 |
="# | -2.359 |
arte | -2.331 |
ム | -2.322 |
Token | best |
Token ID | 1266 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
�� | +0.130 |
izoph | +0.126 |
="# | +0.115 |
arte | +0.111 |
ム | +0.110 |
Neg logit contributions | |
ocument | -0.131 |
"]," | -0.122 |
outp | -0.117 |
Extrem | -0.113 |
cult | -0.109 |
Token | education |
Token ID | 3707 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
ocument | +3.200 |
"]," | +2.947 |
outp | +2.911 |
Extrem | +2.568 |
cult | +2.371 |
Neg logit contributions | |
�� | -8.049 |
izoph | -7.832 |
="# | -7.195 |
arte | -7.101 |
ム | -7.096 |
Token | they |
Token ID | 484 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ocument | +5.068 |
"]," | +4.440 |
outp | +4.279 |
Extrem | +3.994 |
cult | +3.781 |
Neg logit contributions | |
�� | -11.147 |
izoph | -11.095 |
="# | -10.053 |
arte | -10.045 |
ム | -9.924 |
Token | can |
Token ID | 460 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
"]," | +5.374 |
ocument | +5.124 |
outp | +4.421 |
naturally | +4.222 |
cult | +3.995 |
Neg logit contributions | |
�� | -17.042 |
izoph | -16.793 |
�� | -14.984 |
="# | -14.962 |
ム | -14.918 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ocument | +3.274 |
"]," | +3.004 |
outp | +2.925 |
Extrem | +2.800 |
cult | +2.681 |
Neg logit contributions | |
�� | -4.126 |
izoph | -4.032 |
="# | -3.631 |
ム | -3.511 |
arte | -3.487 |
Token | then |
Token ID | 788 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ocument | +1.260 |
"]," | +1.157 |
outp | +1.109 |
Extrem | +1.056 |
cult | +1.012 |
Neg logit contributions | |
�� | -1.837 |
izoph | -1.796 |
="# | -1.655 |
arte | -1.599 |
ム | -1.587 |
Token | use |
Token ID | 779 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
ocument | +1.780 |
"]," | +1.600 |
outp | +1.539 |
Extrem | +1.406 |
cult | +1.351 |
Neg logit contributions | |
�� | -3.759 |
izoph | -3.656 |
="# | -3.397 |
arte | -3.337 |
ム | -3.287 |
Token | it |
Token ID | 340 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
�� | +0.757 |
izoph | +0.741 |
="# | +0.694 |
arte | +0.649 |
ム | +0.634 |
Neg logit contributions | |
ocument | -1.054 |
"]," | -0.972 |
outp | -0.931 |
Extrem | -0.909 |
cult | -0.886 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ocument | +0.161 |
"]," | +0.149 |
outp | +0.143 |
Extrem | +0.138 |
cult | +0.132 |
Neg logit contributions | |
�� | -0.183 |
izoph | -0.178 |
="# | -0.164 |
arte | -0.159 |
ム | -0.157 |
Token | � |
Token ID | 447 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
ocument | +1.570 |
"]," | +1.459 |
outp | +1.407 |
Extrem | +1.356 |
cult | +1.302 |
Neg logit contributions | |
�� | -1.641 |
izoph | -1.602 |
="# | -1.461 |
arte | -1.411 |
ム | -1.391 |
Token | � |
Token ID | 251 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ocument | +0.341 |
"]," | +0.321 |
outp | +0.311 |
Extrem | +0.301 |
cult | +0.291 |
Neg logit contributions | |
�� | -0.257 |
izoph | -0.253 |
="# | -0.227 |
arte | -0.217 |
ム | -0.212 |
Token | See |
Token ID | 4091 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
ocument | +2.535 |
"]," | +2.363 |
outp | +2.276 |
Extrem | +2.208 |
Exhibit | +2.118 |
Neg logit contributions | |
�� | -2.606 |
izoph | -2.549 |
="# | -2.293 |
arte | -2.222 |
ム | -2.190 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ocument | +5.818 |
"]," | +5.396 |
outp | +5.278 |
Extrem | +5.177 |
Exhibit | +5.030 |
Neg logit contributions | |
�� | -6.554 |
izoph | -6.401 |
="# | -5.606 |
arte | -5.497 |
wagen | -5.445 |
Token | Louis |
Token ID | 5593 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ocument | +0.856 |
"]," | +0.790 |
outp | +0.760 |
Extrem | +0.729 |
cult | +0.699 |
Neg logit contributions | |
�� | -1.011 |
izoph | -0.989 |
="# | -0.909 |
arte | -0.879 |
ム | -0.869 |
Token | H |
Token ID | 367 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
ocument | +8.230 |
"]," | +7.397 |
outp | +7.164 |
Extrem | +7.045 |
Exhibit | +6.931 |
Neg logit contributions | |
�� | -13.462 |
izoph | -12.902 |
="# | -11.319 |
skinned | -11.302 |
wagen | -11.266 |
Token | . |
Token ID | 13 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
ocument | +4.139 |
"]," | +3.776 |
outp | +3.631 |
Extrem | +3.518 |
ocks | +3.390 |
Neg logit contributions | |
�� | -4.559 |
izoph | -4.343 |
="# | -4.064 |
ム | -3.892 |
wagen | -3.791 |
Token | Feldman |
Token ID | 45498 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ocument | +6.608 |
"]," | +6.118 |
Extrem | +5.807 |
outp | +5.662 |
Exhibit | +5.548 |
Neg logit contributions | |
�� | -10.953 |
izoph | -10.636 |
wagen | -9.355 |
="# | -9.344 |
skinned | -9.285 |
Token | , |
Token ID | 11 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ocument | +1.653 |
"]," | +1.512 |
outp | +1.454 |
Extrem | +1.394 |
Exhibit | +1.326 |
Neg logit contributions | |
�� | -2.167 |
izoph | -2.114 |
="# | -1.938 |
arte | -1.880 |
ム | -1.863 |
Token | James |
Token ID | 3700 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ocument | +3.005 |
"]," | +2.781 |
outp | +2.687 |
Extrem | +2.613 |
Exhibit | +2.497 |
Neg logit contributions | |
�� | -3.154 |
izoph | -3.053 |
="# | -2.744 |
arte | -2.673 |
wagen | -2.626 |
Token | Parser |
Token ID | 46677 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
ocument | +2.598 |
"]," | +2.469 |
outp | +2.408 |
Extrem | +2.346 |
cult | +2.287 |
Neg logit contributions | |
�� | -1.109 |
izoph | -1.062 |
="# | -0.902 |
arte | -0.843 |
ム | -0.823 |
Token | () |
Token ID | 3419 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ocument | +0.710 |
"]," | +0.666 |
outp | +0.652 |
Extrem | +0.634 |
cult | +0.616 |
Neg logit contributions | |
�� | -0.381 |
izoph | -0.373 |
="# | -0.339 |
arte | -0.317 |
ム | -0.309 |
Token | ap |
Token ID | 2471 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
ocument | +2.516 |
"]," | +2.320 |
outp | +2.235 |
Extrem | +2.137 |
cult | +2.045 |
Neg logit contributions | |
�� | -3.103 |
izoph | -3.028 |
="# | -2.785 |
arte | -2.698 |
ム | -2.669 |
Token | . |
Token ID | 13 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
ocument | +0.220 |
"]," | +0.202 |
outp | +0.196 |
Extrem | +0.188 |
cult | +0.180 |
Neg logit contributions | |
�� | -0.221 |
izoph | -0.219 |
="# | -0.207 |
arte | -0.197 |
ム | -0.195 |
Token | add |
Token ID | 2860 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
ocument | +1.195 |
"]," | +1.138 |
outp | +1.112 |
Extrem | +1.086 |
cult | +1.052 |
Neg logit contributions | |
�� | -0.444 |
izoph | -0.428 |
="# | -0.362 |
arte | -0.336 |
ム | -0.325 |
Token | _ |
Token ID | 62 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ocument | +0.996 |
"]," | +0.926 |
outp | +0.903 |
Extrem | +0.871 |
cult | +0.840 |
Neg logit contributions | |
�� | -0.793 |
izoph | -0.781 |
="# | -0.716 |
arte | -0.682 |
ム | -0.675 |
Token | argument |
Token ID | 49140 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
ocument | +6.956 |
"]," | +6.631 |
cult | +6.009 |
outp | +5.917 |
cial | +5.901 |
Neg logit contributions | |
�� | -15.412 |
izoph | -14.288 |
�� | -13.298 |
� | -12.654 |
ENN | -12.529 |
Token | (" |
Token ID | 7203 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
ocument | +0.957 |
"]," | +0.898 |
outp | +0.878 |
Extrem | +0.849 |
cult | +0.820 |
Neg logit contributions | |
�� | -0.659 |
izoph | -0.642 |
="# | -0.591 |
arte | -0.551 |
ム | -0.549 |
Token | - |
Token ID | 12 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
�� | +0.212 |
izoph | +0.209 |
="# | +0.197 |
arte | +0.188 |
ム | +0.184 |
Neg logit contributions | |
ocument | -0.221 |
"]," | -0.201 |
outp | -0.197 |
Extrem | -0.192 |
Exhibit | -0.181 |
Token | i |
Token ID | 72 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
�� | +0.557 |
izoph | +0.554 |
="# | +0.521 |
arte | +0.502 |
ム | +0.487 |
Neg logit contributions | |
ocument | -0.525 |
"]," | -0.481 |
outp | -0.472 |
Extrem | -0.460 |
Exhibit | -0.432 |
Token | ", |
Token ID | 1600 |
Feature activation | +3.42e-03 |
Pos logit contributions | |
�� | +0.840 |
izoph | +0.832 |
="# | +0.781 |
arte | +0.743 |
ム | +0.732 |
Neg logit contributions | |
ocument | -0.913 |
"]," | -0.820 |
outp | -0.816 |
Extrem | -0.788 |
cult | -0.756 |
Token | 6 |
Token ID | 21 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ocument | +3.368 |
"]," | +3.167 |
outp | +3.059 |
Extrem | +2.899 |
cult | +2.855 |
Neg logit contributions | |
�� | -3.381 |
izoph | -3.283 |
="# | -2.947 |
arte | -2.825 |
ム | -2.811 |
Token | { |
Token ID | 1391 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ocument | +2.816 |
"]," | +2.645 |
outp | +2.509 |
Extrem | +2.412 |
Exhibit | +2.268 |
Neg logit contributions | |
�� | -4.409 |
izoph | -4.325 |
="# | -3.932 |
arte | -3.822 |
wagen | -3.802 |
Token | ( |
Token ID | 7 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ocument | +1.904 |
"]," | +1.783 |
outp | +1.719 |
Extrem | +1.659 |
cult | +1.604 |
Neg logit contributions | |
�� | -1.740 |
izoph | -1.694 |
="# | -1.528 |
arte | -1.473 |
ム | -1.449 |
Token | 44 |
Token ID | 2598 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
ocument | +1.133 |
"]," | +1.056 |
outp | +1.024 |
Extrem | +0.987 |
cult | +0.952 |
Neg logit contributions | |
�� | -1.025 |
izoph | -0.998 |
="# | -0.909 |
arte | -0.873 |
ム | -0.862 |
Token | s |
Token ID | 82 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
ocument | +3.525 |
"]," | +3.325 |
outp | +3.177 |
Extrem | +2.958 |
cult | +2.875 |
Neg logit contributions | |
�� | -5.023 |
izoph | -4.941 |
="# | -4.517 |
arte | -4.448 |
skinned | -4.280 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ocument | +1.820 |
"]," | +1.685 |
outp | +1.475 |
Extrem | +1.296 |
cial | +1.212 |
Neg logit contributions | |
�� | -6.588 |
izoph | -6.451 |
="# | -5.975 |
arte | -5.861 |
wagen | -5.824 |
Token | 22 |
Token ID | 2534 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ocument | +4.375 |
"]," | +4.225 |
outp | +3.998 |
Exhibit | +3.702 |
Extrem | +3.543 |
Neg logit contributions | |
�� | -16.689 |
izoph | -16.588 |
="# | -15.688 |
wagen | -14.932 |
ム | -14.875 |
Token | . |
Token ID | 13 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
ocument | +1.323 |
"]," | +1.218 |
outp | +1.175 |
Extrem | +1.128 |
cult | +1.085 |
Neg logit contributions | |
�� | -1.466 |
izoph | -1.439 |
="# | -1.327 |
arte | -1.279 |
ム | -1.265 |
Token | R |
Token ID | 371 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
ocument | +0.649 |
"]," | +0.599 |
outp | +0.576 |
Extrem | +0.556 |
cult | +0.536 |
Neg logit contributions | |
�� | -0.652 |
izoph | -0.638 |
="# | -0.586 |
arte | -0.565 |
ム | -0.559 |
Token | c |
Token ID | 66 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
�� | +0.694 |
izoph | +0.682 |
="# | +0.632 |
arte | +0.617 |
ム | +0.608 |
Neg logit contributions | |
ocument | -0.542 |
"]," | -0.496 |
outp | -0.477 |
Extrem | -0.462 |
Exhibit | -0.434 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
�� | +0.426 |
izoph | +0.416 |
="# | +0.381 |
arte | +0.366 |
ム | +0.361 |
Neg logit contributions | |
ocument | -0.509 |
"]," | -0.473 |
outp | -0.457 |
Extrem | -0.444 |
Exhibit | -0.425 |
Token | the |
Token ID | 262 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
�� | +3.201 |
izoph | +3.103 |
="# | +2.897 |
arte | +2.798 |
ム | +2.780 |
Neg logit contributions | |
ocument | -3.570 |
"]," | -3.212 |
outp | -3.106 |
cult | -2.907 |
Extrem | -2.902 |
Token | cars |
Token ID | 5006 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
ocument | +2.675 |
"]," | +2.522 |
outp | +2.428 |
Extrem | +2.328 |
cult | +2.195 |
Neg logit contributions | |
�� | -3.685 |
izoph | -3.602 |
="# | -3.317 |
arte | -3.201 |
ム | -3.168 |
Token | his |
Token ID | 465 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
�� | +3.584 |
izoph | +3.558 |
="# | +3.252 |
wagen | +3.239 |
arte | +3.148 |
Neg logit contributions | |
ocument | -3.812 |
"]," | -3.451 |
outp | -3.324 |
Extrem | -3.216 |
cult | -3.146 |
Token | tyre |
Token ID | 48216 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ocument | +2.087 |
"]," | +1.932 |
outp | +1.865 |
Extrem | +1.781 |
cult | +1.697 |
Neg logit contributions | |
�� | -2.622 |
izoph | -2.560 |
="# | -2.354 |
arte | -2.283 |
ム | -2.252 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ocument | +2.267 |
"]," | +2.102 |
outp | +2.026 |
Extrem | +1.950 |
cult | +1.876 |
Neg logit contributions | |
�� | -2.366 |
izoph | -2.312 |
="# | -2.116 |
arte | -2.040 |
ム | -2.015 |
Token | half |
Token ID | 2063 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ocument | +1.028 |
"]," | +0.953 |
outp | +0.914 |
Extrem | +0.884 |
cult | +0.852 |
Neg logit contributions | |
�� | -1.035 |
izoph | -1.011 |
="# | -0.926 |
arte | -0.889 |
ム | -0.880 |
Token | flat |
Token ID | 6228 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ocument | +9.186 |
outp | +9.069 |
"]," | +9.065 |
Exhibit | +8.275 |
Extrem | +8.215 |
Neg logit contributions | |
�� | -12.244 |
izoph | -11.542 |
arte | -10.377 |
="# | -10.321 |
ENN | -10.232 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ocument | +1.539 |
"]," | +1.423 |
outp | +1.375 |
Extrem | +1.314 |
cult | +1.258 |
Neg logit contributions | |
�� | -1.828 |
izoph | -1.784 |
="# | -1.638 |
arte | -1.581 |
ム | -1.557 |
Token | � |
Token ID | 447 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
�� | +1.505 |
izoph | +1.470 |
="# | +1.368 |
ム | +1.307 |
arte | +1.305 |
Neg logit contributions | |
ocument | -1.632 |
"]," | -1.496 |
outp | -1.463 |
Extrem | -1.382 |
cult | -1.356 |
Token | � |
Token ID | 251 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
ocument | +1.436 |
"]," | +1.354 |
outp | +1.318 |
Extrem | +1.279 |
cult | +1.245 |
Neg logit contributions | |
�� | -0.844 |
izoph | -0.812 |
="# | -0.718 |
arte | -0.681 |
ム | -0.671 |
Token |
|
Token ID | 198 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
�� | +0.075 |
izoph | +0.073 |
="# | +0.067 |
arte | +0.064 |
ム | +0.063 |
Neg logit contributions | |
ocument | -0.078 |
"]," | -0.072 |
outp | -0.070 |
Extrem | -0.067 |
cult | -0.065 |
Token | with |
Token ID | 351 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
ocument | +2.140 |
"]," | +1.985 |
outp | +1.911 |
Extrem | +1.829 |
cult | +1.753 |
Neg logit contributions | |
�� | -2.522 |
izoph | -2.462 |
="# | -2.257 |
arte | -2.185 |
ム | -2.159 |
Token | j |
Token ID | 474 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
izoph | +0.549 |
�� | +0.546 |
="# | +0.521 |
arte | +0.477 |
ム | +0.468 |
Neg logit contributions | |
ocument | -0.753 |
"]," | -0.682 |
outp | -0.660 |
Extrem | -0.651 |
cult | -0.633 |
Token | agg |
Token ID | 9460 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
�� | +0.080 |
izoph | +0.080 |
="# | +0.073 |
arte | +0.069 |
ム | +0.067 |
Neg logit contributions | |
ocument | -0.118 |
"]," | -0.110 |
outp | -0.107 |
Extrem | -0.106 |
cult | -0.101 |
Token | ies |
Token ID | 444 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
ocument | +2.483 |
"]," | +2.310 |
outp | +2.191 |
Extrem | +2.066 |
cial | +2.009 |
Neg logit contributions | |
�� | -3.603 |
izoph | -3.491 |
="# | -3.187 |
arte | -3.128 |
ム | -3.080 |
Token | ) |
Token ID | 8 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
"]," | +4.469 |
ocument | +4.446 |
outp | +3.936 |
Extrem | +3.910 |
cial | +3.691 |
Neg logit contributions | |
�� | -7.548 |
izoph | -7.299 |
="# | -6.334 |
�� | -6.303 |
arte | -6.252 |
Token | even |
Token ID | 772 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ocument | +4.203 |
"]," | +4.020 |
outp | +3.945 |
Extrem | +3.808 |
cult | +3.690 |
Neg logit contributions | |
�� | -2.431 |
izoph | -2.317 |
="# | -2.020 |
ム | -1.895 |
arte | -1.892 |
Token | though |
Token ID | 996 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
outp | +5.201 |
ocument | +5.111 |
"]," | +4.540 |
Extrem | +4.281 |
Exhibit | +4.087 |
Neg logit contributions | |
�� | -16.597 |
izoph | -15.906 |
ム | -15.028 |
="# | -14.588 |
arte | -14.519 |
Token | it |
Token ID | 340 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
ocument | +3.185 |
"]," | +3.006 |
outp | +2.903 |
Extrem | +2.787 |
cult | +2.679 |
Neg logit contributions | |
�� | -3.167 |
izoph | -3.063 |
="# | -2.745 |
arte | -2.676 |
ム | -2.643 |
Token | does |
Token ID | 857 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
ocument | +4.459 |
outp | +4.189 |
"]," | +4.177 |
Extrem | +3.899 |
cial | +3.786 |
Neg logit contributions | |
�� | -4.918 |
izoph | -4.713 |
="# | -4.168 |
ム | -4.069 |
arte | -4.066 |
Token | look |
Token ID | 804 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
ocument | +3.628 |
"]," | +3.431 |
outp | +3.305 |
Extrem | +3.052 |
Exhibit | +2.993 |
Neg logit contributions | |
�� | -4.988 |
izoph | -4.869 |
="# | -4.377 |
arte | -4.376 |
ム | -4.288 |
Token | nice |
Token ID | 3621 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
�� | +0.788 |
izoph | +0.753 |
="# | +0.712 |
arte | +0.670 |
aster | +0.657 |
Neg logit contributions | |
ocument | -1.020 |
"]," | -0.932 |
outp | -0.903 |
Extrem | -0.874 |
cult | -0.854 |
Token | of |
Token ID | 286 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
�� | +1.711 |
izoph | +1.666 |
="# | +1.609 |
arte | +1.528 |
ム | +1.467 |
Neg logit contributions | |
ocument | -2.179 |
"]," | -1.950 |
outp | -1.858 |
Extrem | -1.843 |
cult | -1.768 |
Token | people |
Token ID | 661 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
ocument | +0.713 |
"]," | +0.655 |
outp | +0.623 |
Extrem | +0.611 |
cial | +0.590 |
Neg logit contributions | |
�� | -0.640 |
izoph | -0.624 |
="# | -0.576 |
arte | -0.548 |
ム | -0.538 |
Token | of |
Token ID | 286 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
�� | +0.386 |
izoph | +0.379 |
="# | +0.361 |
arte | +0.341 |
ム | +0.334 |
Neg logit contributions | |
ocument | -0.442 |
"]," | -0.405 |
outp | -0.386 |
Extrem | -0.378 |
cult | -0.362 |
Token | all |
Token ID | 477 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
ocument | +2.199 |
"]," | +2.030 |
outp | +1.954 |
Extrem | +1.872 |
cult | +1.794 |
Neg logit contributions | |
�� | -2.634 |
izoph | -2.576 |
="# | -2.369 |
arte | -2.291 |
ム | -2.264 |
Token | faiths |
Token ID | 43028 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ocument | +2.566 |
"]," | +2.320 |
outp | +2.228 |
Extrem | +2.000 |
cult | +1.900 |
Neg logit contributions | |
�� | -7.159 |
izoph | -7.012 |
="# | -6.524 |
arte | -6.485 |
ム | -6.381 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
�� | +1.377 |
izoph | +1.348 |
="# | +1.246 |
arte | +1.207 |
ム | +1.193 |
Neg logit contributions | |
ocument | -1.030 |
"]," | -0.945 |
outp | -0.907 |
Extrem | -0.867 |
cult | -0.828 |
Token | colors |
Token ID | 7577 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
outp | +4.806 |
ocument | +4.768 |
"]," | +4.606 |
naturally | +4.206 |
cult | +4.094 |
Neg logit contributions | |
�� | -15.814 |
izoph | -15.370 |
ム | -14.183 |
="# | -14.040 |
arte | -13.949 |
Token | and |
Token ID | 290 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
ocument | +0.411 |
"]," | +0.377 |
outp | +0.361 |
Extrem | +0.353 |
cult | +0.336 |
Neg logit contributions | |
�� | -0.379 |
izoph | -0.371 |
="# | -0.349 |
arte | -0.334 |
ム | -0.323 |
Token | cre |
Token ID | 1126 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
ocument | +2.979 |
"]," | +2.749 |
outp | +2.746 |
cult | +2.285 |
Extrem | +2.284 |
Neg logit contributions | |
�� | -10.123 |
izoph | -9.754 |
="# | -9.108 |
ム | -9.099 |
arte | -8.974 |
Token | eds |
Token ID | 5379 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ocument | +2.227 |
"]," | +1.987 |
outp | +1.858 |
Extrem | +1.739 |
cult | +1.643 |
Neg logit contributions | |
�� | -5.158 |
izoph | -5.058 |
="# | -4.726 |
arte | -4.605 |
ム | -4.587 |
Token | in |
Token ID | 287 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
ocument | +2.717 |
outp | +2.458 |
"]," | +2.449 |
Extrem | +2.281 |
cult | +2.207 |
Neg logit contributions | |
�� | -3.389 |
izoph | -3.324 |
="# | -3.040 |
ム | -2.924 |
arte | -2.916 |
Token | important |
Token ID | 1593 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
�� | +0.809 |
izoph | +0.787 |
="# | +0.727 |
arte | +0.701 |
ム | +0.688 |
Neg logit contributions | |
ocument | -0.766 |
"]," | -0.698 |
outp | -0.659 |
Extrem | -0.645 |
cult | -0.617 |
Token | ." |
Token ID | 526 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
ocument | +0.913 |
"]," | +0.845 |
outp | +0.815 |
Extrem | +0.782 |
cult | +0.750 |
Neg logit contributions | |
�� | -1.050 |
izoph | -1.026 |
="# | -0.942 |
arte | -0.911 |
ム | -0.899 |
Token |
|
Token ID | 198 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
ocument | +0.669 |
"]," | +0.627 |
outp | +0.600 |
Extrem | +0.589 |
Exhibit | +0.559 |
Neg logit contributions | |
�� | -0.722 |
izoph | -0.709 |
="# | -0.644 |
arte | -0.617 |
ム | -0.611 |
Token |
|
Token ID | 198 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
ocument | +0.357 |
"]," | +0.327 |
outp | +0.320 |
Extrem | +0.308 |
cult | +0.297 |
Neg logit contributions | |
�� | -0.312 |
izoph | -0.306 |
="# | -0.284 |
arte | -0.273 |
ム | -0.268 |
Token | D |
Token ID | 35 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ocument | +0.831 |
"]," | +0.772 |
outp | +0.752 |
Extrem | +0.724 |
cult | +0.693 |
Neg logit contributions | |
�� | -0.752 |
izoph | -0.731 |
="# | -0.672 |
arte | -0.645 |
ム | -0.637 |
Token | ella |
Token ID | 12627 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ocument | +0.266 |
"]," | +0.249 |
outp | +0.243 |
Extrem | +0.236 |
cult | +0.226 |
Neg logit contributions | |
�� | -0.201 |
izoph | -0.198 |
="# | -0.178 |
arte | -0.173 |
ム | -0.167 |
Token | Vol |
Token ID | 4709 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
"]," | +4.324 |
ocument | +3.995 |
Extrem | +3.811 |
outp | +3.748 |
Ov | +3.463 |
Neg logit contributions | |
�� | -17.523 |
izoph | -16.901 |
�� | -15.313 |
="# | -14.999 |
ENN | -14.897 |
Token | pe |
Token ID | 431 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
ocument | +2.448 |
"]," | +2.308 |
outp | +2.236 |
Extrem | +2.145 |
cult | +2.099 |
Neg logit contributions | |
�� | -1.997 |
izoph | -1.939 |
="# | -1.726 |
arte | -1.641 |
ム | -1.639 |
Token | agrees |
Token ID | 14386 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
ocument | +3.805 |
"]," | +3.545 |
outp | +3.518 |
Extrem | +3.293 |
Exhibit | +3.186 |
Neg logit contributions | |
�� | -4.515 |
izoph | -4.446 |
="# | -3.989 |
ム | -3.861 |
arte | -3.848 |
Token | . |
Token ID | 13 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ocument | +1.765 |
"]," | +1.626 |
outp | +1.570 |
Extrem | +1.501 |
cult | +1.443 |
Neg logit contributions | |
�� | -2.182 |
izoph | -2.127 |
="# | -1.963 |
arte | -1.905 |
ム | -1.877 |
Token | " |
Token ID | 366 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ocument | +2.251 |
"]," | +2.101 |
outp | +2.016 |
Extrem | +1.964 |
Exhibit | +1.871 |
Neg logit contributions | |
�� | -2.361 |
izoph | -2.310 |
="# | -2.092 |
arte | -2.023 |
ム | -1.994 |
Token | T |
Token ID | 51 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ocument | +1.058 |
"]," | +0.986 |
outp | +0.948 |
Extrem | +0.914 |
cult | +0.883 |
Neg logit contributions | |
�� | -1.071 |
izoph | -1.045 |
="# | -0.952 |
arte | -0.918 |
ム | -0.905 |
Token | rib |
Token ID | 822 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ocument | +1.746 |
"]," | +1.617 |
outp | +1.563 |
Extrem | +1.510 |
cult | +1.461 |
Neg logit contributions | |
�� | -1.634 |
izoph | -1.575 |
="# | -1.444 |
ム | -1.373 |
arte | -1.365 |
Token | al |
Token ID | 282 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ocument | +1.202 |
"]," | +1.078 |
outp | +1.024 |
Extrem | +0.973 |
cult | +0.917 |
Neg logit contributions | |
�� | -2.211 |
izoph | -2.160 |
="# | -2.024 |
arte | -1.956 |
ム | -1.952 |
Token | Unity |
Token ID | 18714 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ocument | +4.482 |
"]," | +4.197 |
outp | +4.048 |
Extrem | +3.987 |
cult | +3.809 |
Neg logit contributions | |
�� | -4.579 |
izoph | -4.411 |
="# | -4.035 |
ム | -3.879 |
arte | -3.875 |
Token | vs |
Token ID | 3691 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
�� | +3.642 |
izoph | +3.588 |
="# | +3.342 |
arte | +3.247 |
ム | +3.214 |
Neg logit contributions | |
ocument | -2.210 |
"]," | -1.990 |
outp | -1.884 |
Extrem | -1.782 |
cial | -1.703 |
Token | Fet |
Token ID | 44649 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ocument | +0.090 |
"]," | +0.083 |
outp | +0.080 |
Extrem | +0.077 |
cult | +0.074 |
Neg logit contributions | |
�� | -0.098 |
izoph | -0.096 |
="# | -0.088 |
arte | -0.085 |
ム | -0.084 |
Token | id |
Token ID | 312 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ocument | +12.323 |
"]," | +11.888 |
outp | +11.223 |
cult | +11.152 |
atal | +11.136 |
Neg logit contributions | |
�� | -8.542 |
izoph | -8.119 |
="# | -7.398 |
ム | -6.796 |
� | -6.533 |
Token | Heath |
Token ID | 25846 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
ocument | +5.700 |
"]," | +5.315 |
Extrem | +5.131 |
outp | +5.099 |
cult | +4.850 |
Neg logit contributions | |
�� | -5.883 |
izoph | -5.663 |
="# | -5.261 |
arte | -4.951 |
ム | -4.946 |
Token |
|
Token ID | 198 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ocument | +3.655 |
"]," | +3.421 |
outp | +3.278 |
Extrem | +3.215 |
cult | +3.136 |
Neg logit contributions | |
�� | -3.912 |
izoph | -3.827 |
="# | -3.493 |
ム | -3.340 |
arte | -3.339 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
�� | +0.143 |
izoph | +0.141 |
="# | +0.132 |
arte | +0.126 |
ム | +0.123 |
Neg logit contributions | |
ocument | -0.173 |
"]," | -0.156 |
outp | -0.154 |
Extrem | -0.148 |
cult | -0.143 |
Token | M |
Token ID | 44 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ocument | +1.075 |
"]," | +1.002 |
outp | +0.964 |
Extrem | +0.929 |
cult | +0.898 |
Neg logit contributions | |
�� | -1.089 |
izoph | -1.062 |
="# | -0.968 |
arte | -0.933 |
ム | -0.920 |
Token |
|
Token ID | 198 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ocument | +1.527 |
"]," | +1.419 |
outp | +1.372 |
Extrem | +1.321 |
cult | +1.272 |
Neg logit contributions | |
�� | -1.497 |
izoph | -1.461 |
="# | -1.334 |
arte | -1.285 |
ム | -1.267 |
Token | The |
Token ID | 464 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
ocument | +2.450 |
"]," | +2.290 |
outp | +2.200 |
Extrem | +2.120 |
cult | +2.066 |
Neg logit contributions | |
�� | -2.336 |
izoph | -2.280 |
="# | -2.045 |
arte | -1.975 |
ム | -1.949 |
Token | problem |
Token ID | 1917 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
�� | +0.356 |
izoph | +0.349 |
="# | +0.323 |
arte | +0.314 |
ム | +0.307 |
Neg logit contributions | |
ocument | -0.299 |
"]," | -0.276 |
outp | -0.255 |
Extrem | -0.248 |
cial | -0.240 |
Token | , |
Token ID | 11 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
ocument | +3.722 |
"]," | +3.421 |
outp | +3.388 |
Extrem | +3.221 |
Exhibit | +3.086 |
Neg logit contributions | |
�� | -4.795 |
izoph | -4.699 |
="# | -4.243 |
ム | -4.126 |
arte | -4.120 |
Token | D |
Token ID | 360 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ocument | +4.546 |
"]," | +4.187 |
outp | +4.168 |
Extrem | +3.960 |
Exhibit | +3.790 |
Neg logit contributions | |
�� | -5.984 |
izoph | -5.814 |
="# | -5.282 |
ム | -5.058 |
arte | -5.037 |
Token | ella |
Token ID | 12627 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ocument | +1.535 |
"]," | +1.438 |
outp | +1.392 |
Extrem | +1.343 |
cult | +1.301 |
Neg logit contributions | |
�� | -1.263 |
izoph | -1.228 |
="# | -1.107 |
arte | -1.060 |
ム | -1.048 |
Token | Vol |
Token ID | 4709 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
"]," | +4.527 |
ocument | +4.270 |
outp | +3.839 |
Extrem | +3.819 |
Ov | +3.527 |
Neg logit contributions | |
�� | -17.129 |
izoph | -16.510 |
�� | -14.853 |
skinned | -14.554 |
artney | -14.532 |
Token | pe |
Token ID | 431 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
ocument | +2.763 |
"]," | +2.613 |
outp | +2.526 |
Extrem | +2.409 |
cult | +2.376 |
Neg logit contributions | |
�� | -2.357 |
izoph | -2.287 |
="# | -2.017 |
ム | -1.934 |
arte | -1.916 |
Token | says |
Token ID | 1139 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ocument | +3.227 |
"]," | +2.993 |
outp | +2.951 |
Extrem | +2.721 |
Exhibit | +2.672 |
Neg logit contributions | |
�� | -3.920 |
izoph | -3.893 |
="# | -3.476 |
ム | -3.361 |
arte | -3.337 |
Token | , |
Token ID | 11 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
ocument | +2.061 |
"]," | +1.882 |
outp | +1.848 |
Extrem | +1.715 |
cult | +1.650 |
Neg logit contributions | |
�� | -3.244 |
izoph | -3.189 |
="# | -2.910 |
ム | -2.853 |
arte | -2.842 |
Token | is |
Token ID | 318 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ocument | +0.594 |
"]," | +0.551 |
outp | +0.534 |
Extrem | +0.511 |
cult | +0.492 |
Neg logit contributions | |
�� | -0.640 |
izoph | -0.626 |
="# | -0.571 |
arte | -0.552 |
ム | -0.546 |
Token | of |
Token ID | 286 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
�� | +0.069 |
izoph | +0.068 |
="# | +0.062 |
arte | +0.060 |
ム | +0.059 |
Neg logit contributions | |
ocument | -0.066 |
"]," | -0.062 |
outp | -0.059 |
Extrem | -0.057 |
cult | -0.055 |
Token | tea |
Token ID | 8887 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
�� | +4.541 |
izoph | +4.305 |
="# | +4.117 |
arte | +3.921 |
aster | +3.838 |
Neg logit contributions | |
ocument | -4.006 |
"]," | -3.701 |
outp | -3.405 |
Extrem | -3.237 |
cial | -3.167 |
Token | -- |
Token ID | 1377 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ocument | +1.406 |
"]," | +1.289 |
outp | +1.253 |
Extrem | +1.195 |
cult | +1.150 |
Neg logit contributions | |
�� | -1.716 |
izoph | -1.683 |
="# | -1.542 |
arte | -1.489 |
ム | -1.473 |
Token | his |
Token ID | 465 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
�� | +1.934 |
izoph | +1.865 |
="# | +1.736 |
arte | +1.701 |
ム | +1.649 |
Neg logit contributions | |
ocument | -1.855 |
"]," | -1.724 |
outp | -1.619 |
Extrem | -1.559 |
cult | -1.512 |
Token | own |
Token ID | 898 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ocument | +1.830 |
"]," | +1.694 |
outp | +1.641 |
Extrem | +1.567 |
cult | +1.497 |
Neg logit contributions | |
�� | -2.284 |
izoph | -2.230 |
="# | -2.050 |
arte | -1.985 |
ム | -1.964 |
Token | n |
Token ID | 299 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ocument | +2.244 |
"]," | +2.079 |
outp | +2.021 |
Extrem | +1.927 |
cult | +1.844 |
Neg logit contributions | |
�� | -2.701 |
izoph | -2.628 |
="# | -2.416 |
arte | -2.340 |
ム | -2.316 |
Token | autical |
Token ID | 37073 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ocument | +11.218 |
"]," | +9.976 |
atal | +9.953 |
outp | +9.654 |
ocks | +9.413 |
Neg logit contributions | |
�� | -9.912 |
izoph | -9.325 |
="# | -8.341 |
ム | -8.042 |
skinned | -7.996 |
Token | experience |
Token ID | 1998 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
ocument | +3.887 |
"]," | +3.619 |
outp | +3.588 |
Extrem | +3.344 |
cult | +3.200 |
Neg logit contributions | |
�� | -5.438 |
izoph | -5.305 |
="# | -4.862 |
arte | -4.731 |
ム | -4.718 |
Token | was |
Token ID | 373 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
ocument | +0.552 |
"]," | +0.512 |
outp | +0.486 |
Extrem | +0.473 |
cult | +0.456 |
Neg logit contributions | |
�� | -0.567 |
izoph | -0.551 |
="# | -0.507 |
arte | -0.489 |
ム | -0.482 |
Token | limited |
Token ID | 3614 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
�� | +1.990 |
izoph | +1.915 |
="# | +1.764 |
arte | +1.707 |
ム | +1.679 |
Neg logit contributions | |
ocument | -1.973 |
"]," | -1.833 |
outp | -1.679 |
Extrem | -1.673 |
cult | -1.620 |
Token | to |
Token ID | 284 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
�� | +0.661 |
izoph | +0.644 |
="# | +0.592 |
arte | +0.571 |
ム | +0.565 |
Neg logit contributions | |
ocument | -0.620 |
"]," | -0.576 |
outp | -0.552 |
Extrem | -0.532 |
cult | -0.512 |
Token | . |
Token ID | 13 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
izoph | +3.167 |
="# | +3.133 |
�� | +3.033 |
arte | +2.934 |
ム | +2.881 |
Neg logit contributions | |
ocument | -4.370 |
outp | -3.951 |
"]," | -3.842 |
Extrem | -3.815 |
disclaimer | -3.640 |
Token | draw |
Token ID | 19334 |
Feature activation | -2.92e-03 |
Pos logit contributions | |
ocument | +5.037 |
"]," | +4.785 |
outp | +4.624 |
cult | +4.440 |
Extrem | +4.428 |
Neg logit contributions | |
�� | -3.020 |
izoph | -2.881 |
="# | -2.480 |
arte | -2.321 |
ム | -2.316 |
Token | ing |
Token ID | 278 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ocument | +0.021 |
"]," | +0.018 |
outp | +0.018 |
Extrem | +0.017 |
cult | +0.016 |
Neg logit contributions | |
�� | -0.033 |
izoph | -0.033 |
="# | -0.031 |
arte | -0.030 |
ム | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
izoph | +1.785 |
�� | +1.745 |
="# | +1.722 |
arte | +1.620 |
ム | +1.602 |
Neg logit contributions | |
ocument | -2.125 |
outp | -1.903 |
"]," | -1.892 |
Extrem | -1.826 |
cult | -1.738 |
Token | String |
Token ID | 10100 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ocument | +1.169 |
"]," | +1.099 |
outp | +1.069 |
Extrem | +1.035 |
cult | +1.003 |
Neg logit contributions | |
�� | -0.809 |
izoph | -0.785 |
="# | -0.702 |
arte | -0.670 |
ム | -0.659 |
Token | Al |
Token ID | 2348 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
"]," | +5.228 |
ocument | +5.075 |
Extrem | +4.255 |
Fla | +4.163 |
cial | +3.997 |
Neg logit contributions | |
�� | -14.245 |
izoph | -13.190 |
wagen | -12.132 |
�� | -12.087 |
artney | -11.986 |
Token | ignment |
Token ID | 16747 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ocument | +6.396 |
"]," | +5.662 |
cial | +5.409 |
outp | +4.805 |
Extrem | +4.764 |
Neg logit contributions | |
�� | -15.338 |
izoph | -13.787 |
ム | -12.915 |
�� | -12.723 |
ENN | -12.408 |
Token | ] |
Token ID | 60 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
ocument | +0.946 |
"]," | +0.851 |
outp | +0.815 |
Extrem | +0.772 |
cult | +0.729 |
Neg logit contributions | |
�� | -1.608 |
izoph | -1.578 |
="# | -1.479 |
arte | -1.436 |
ム | -1.421 |
Token | :: |
Token ID | 3712 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
�� | +0.416 |
izoph | +0.410 |
="# | +0.391 |
arte | +0.373 |
ム | +0.367 |
Neg logit contributions | |
ocument | -0.345 |
"]," | -0.313 |
outp | -0.306 |
Extrem | -0.291 |
cult | -0.278 |
Token | Near |
Token ID | 40640 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ocument | +2.797 |
"]," | +2.568 |
outp | +2.399 |
Extrem | +2.329 |
cult | +2.222 |
Neg logit contributions | |
�� | -4.424 |
izoph | -4.319 |
="# | -3.937 |
wagen | -3.836 |
arte | -3.817 |
Token | } |
Token ID | 1782 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ocument | +1.367 |
"]," | +1.251 |
outp | +1.198 |
Extrem | +1.146 |
cult | +1.089 |
Neg logit contributions | |
�� | -1.965 |
izoph | -1.925 |
="# | -1.780 |
arte | -1.727 |
ム | -1.709 |
Token | 24 |
Token ID | 1731 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
ocument | +1.242 |
"]," | +1.150 |
outp | +1.119 |
Extrem | +1.078 |
cult | +1.037 |
Neg logit contributions | |
�� | -1.124 |
izoph | -1.097 |
="# | -1.006 |
arte | -0.964 |
ム | -0.952 |
Token | # |
Token ID | 1303 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ocument | +2.760 |
"]," | +2.575 |
outp | +2.420 |
Extrem | +2.336 |
Exhibit | +2.214 |
Neg logit contributions | |
�� | -4.746 |
izoph | -4.636 |
="# | -4.195 |
arte | -4.110 |
wagen | -4.066 |
Token | 19 |
Token ID | 1129 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
ocument | +1.189 |
"]," | +1.113 |
outp | +1.080 |
Extrem | +1.043 |
cult | +1.008 |
Neg logit contributions | |
�� | -0.958 |
izoph | -0.932 |
="# | -0.842 |
arte | -0.807 |
ム | -0.795 |
Token | edit |
Token ID | 4370 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
ocument | +0.227 |
"]," | +0.210 |
outp | +0.201 |
Extrem | +0.193 |
cult | +0.187 |
Neg logit contributions | |
�� | -0.238 |
izoph | -0.233 |
="# | -0.213 |
arte | -0.205 |
ム | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ocument | +3.615 |
"]," | +3.354 |
outp | +3.254 |
Extrem | +3.036 |
cult | +2.941 |
Neg logit contributions | |
�� | -4.867 |
izoph | -4.728 |
="# | -4.273 |
arte | -4.203 |
ム | -4.195 |
Token | n |
Token ID | 299 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
�� | +0.204 |
izoph | +0.200 |
="# | +0.183 |
arte | +0.177 |
ム | +0.174 |
Neg logit contributions | |
ocument | -0.188 |
"]," | -0.174 |
outp | -0.166 |
Extrem | -0.160 |
cult | -0.154 |
Token | vm |
Token ID | 14761 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
ocument | +10.761 |
"]," | +9.962 |
outp | +9.472 |
atal | +9.364 |
cial | +9.138 |
Neg logit contributions | |
�� | -9.776 |
izoph | -9.597 |
ム | -8.193 |
="# | -8.160 |
arte | -7.855 |
Token |
|
Token ID | 198 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ocument | +6.693 |
outp | +6.115 |
"]," | +6.111 |
Extrem | +5.638 |
cial | +5.537 |
Neg logit contributions | |
�� | -8.305 |
izoph | -7.903 |
="# | -7.233 |
arte | -7.100 |
ム | -7.092 |
Token |
|
Token ID | 198 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
ocument | +3.232 |
"]," | +3.104 |
outp | +2.939 |
Extrem | +2.819 |
cult | +2.726 |
Neg logit contributions | |
�� | -3.855 |
izoph | -3.731 |
="# | -3.299 |
arte | -3.229 |
ム | -3.202 |
Token | K |
Token ID | 42 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ocument | +0.937 |
"]," | +0.874 |
outp | +0.844 |
Extrem | +0.812 |
cult | +0.787 |
Neg logit contributions | |
�� | -0.883 |
izoph | -0.861 |
="# | -0.781 |
arte | -0.753 |
ム | -0.743 |
Token | ada |
Token ID | 4763 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
izoph | +5.418 |
�� | +5.336 |
arte | +4.984 |
="# | +4.908 |
ENN | +4.891 |
Neg logit contributions | |
ocument | -5.008 |
"]," | -4.611 |
outp | -4.439 |
Extrem | -4.337 |
Exhibit | -4.084 |
Token | Cleveland |
Token ID | 10306 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
�� | +0.343 |
izoph | +0.334 |
="# | +0.302 |
arte | +0.292 |
ム | +0.285 |
Neg logit contributions | |
ocument | -0.423 |
"]," | -0.392 |
outp | -0.374 |
Extrem | -0.360 |
cult | -0.353 |
Token | Browns |
Token ID | 17671 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
�� | +1.048 |
izoph | +1.008 |
="# | +0.931 |
arte | +0.884 |
aster | +0.867 |
Neg logit contributions | |
ocument | -1.433 |
"]," | -1.323 |
outp | -1.278 |
Extrem | -1.220 |
cial | -1.208 |
Token | just |
Token ID | 655 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ocument | +1.842 |
"]," | +1.691 |
outp | +1.651 |
Extrem | +1.574 |
cult | +1.503 |
Neg logit contributions | |
�� | -2.216 |
izoph | -2.169 |
="# | -1.990 |
arte | -1.922 |
ム | -1.898 |
Token | so |
Token ID | 523 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
�� | +2.834 |
izoph | +2.680 |
="# | +2.543 |
arte | +2.466 |
aster | +2.416 |
Neg logit contributions | |
ocument | -2.980 |
"]," | -2.780 |
outp | -2.531 |
Extrem | -2.516 |
cial | -2.448 |
Token | the |
Token ID | 262 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ocument | +1.297 |
"]," | +1.196 |
outp | +1.159 |
Extrem | +1.112 |
cult | +1.064 |
Neg logit contributions | |
�� | -1.467 |
izoph | -1.436 |
="# | -1.318 |
arte | -1.271 |
ム | -1.255 |
Token | Texans |
Token ID | 21012 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ocument | +1.955 |
"]," | +1.817 |
outp | +1.762 |
Extrem | +1.692 |
cult | +1.619 |
Neg logit contributions | |
�� | -2.101 |
izoph | -2.052 |
="# | -1.880 |
arte | -1.810 |
ム | -1.792 |
Token | could |
Token ID | 714 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
ocument | +6.334 |
outp | +6.271 |
"]," | +6.068 |
Extrem | +5.604 |
naturally | +5.567 |
Neg logit contributions | |
izoph | -13.710 |
�� | -13.625 |
="# | -12.562 |
ム | -12.185 |
arte | -11.690 |
Token | off |
Token ID | 572 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ocument | +6.182 |
"]," | +5.829 |
outp | +5.689 |
Exhibit | +5.199 |
Extrem | +5.172 |
Neg logit contributions | |
�� | -7.790 |
izoph | -7.547 |
="# | -6.739 |
ム | -6.651 |
ENN | -6.488 |
Token | load |
Token ID | 2220 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ocument | +3.981 |
"]," | +3.542 |
outp | +3.449 |
Extrem | +3.228 |
cial | +3.189 |
Neg logit contributions | |
�� | -6.868 |
izoph | -6.803 |
="# | -6.253 |
arte | -5.976 |
ム | -5.972 |
Token | his |
Token ID | 465 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ocument | +2.375 |
"]," | +2.204 |
outp | +2.141 |
Extrem | +2.062 |
Exhibit | +1.977 |
Neg logit contributions | |
�� | -2.388 |
izoph | -2.337 |
="# | -2.134 |
arte | -2.049 |
ム | -2.017 |
Token | on |
Token ID | 319 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ocument | +2.243 |
"]," | +2.074 |
outp | +2.004 |
Extrem | +1.915 |
cult | +1.821 |
Neg logit contributions | |
�� | -2.915 |
izoph | -2.852 |
="# | -2.627 |
arte | -2.542 |
ム | -2.515 |
Token | will |
Token ID | 481 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
izoph | +1.871 |
="# | +1.791 |
�� | +1.722 |
arte | +1.698 |
aster | +1.551 |
Neg logit contributions | |
ocument | -4.673 |
"]," | -4.244 |
outp | -4.087 |
Extrem | -4.053 |
cult | -3.945 |
Token | also |
Token ID | 635 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ocument | +2.065 |
"]," | +1.902 |
outp | +1.830 |
Extrem | +1.754 |
cult | +1.679 |
Neg logit contributions | |
�� | -2.500 |
izoph | -2.448 |
="# | -2.256 |
arte | -2.184 |
ム | -2.155 |
Token | included |
Token ID | 3017 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
�� | +0.998 |
izoph | +0.995 |
="# | +0.933 |
arte | +0.908 |
ム | +0.889 |
Neg logit contributions | |
ocument | -0.825 |
"]," | -0.748 |
outp | -0.721 |
Extrem | -0.707 |
cult | -0.665 |
Token | the |
Token ID | 262 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
izoph | +0.886 |
�� | +0.881 |
="# | +0.837 |
arte | +0.793 |
ム | +0.782 |
Neg logit contributions | |
ocument | -1.115 |
"]," | -1.026 |
outp | -0.992 |
Extrem | -0.955 |
cult | -0.935 |
Token | add |
Token ID | 751 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
ocument | +0.271 |
"]," | +0.253 |
outp | +0.244 |
Extrem | +0.235 |
cult | +0.225 |
Neg logit contributions | |
�� | -0.295 |
izoph | -0.286 |
="# | -0.262 |
arte | -0.252 |
ム | -0.249 |
Token | t |
Token ID | 83 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
�� | +0.449 |
izoph | +0.447 |
="# | +0.416 |
arte | +0.403 |
ム | +0.389 |
Neg logit contributions | |
ocument | -0.490 |
"]," | -0.454 |
outp | -0.441 |
Extrem | -0.426 |
Exhibit | -0.403 |
Token | ional |
Token ID | 1538 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
ocument | +4.715 |
"]," | +3.590 |
outp | +3.450 |
cial | +3.446 |
atal | +3.222 |
Neg logit contributions | |
�� | -17.137 |
izoph | -15.759 |
�� | -14.700 |
ム | -14.631 |
wagen | -14.438 |
Token | resources |
Token ID | 4133 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ocument | +0.641 |
"]," | +0.589 |
outp | +0.568 |
Extrem | +0.554 |
cult | +0.537 |
Neg logit contributions | |
�� | -0.557 |
izoph | -0.553 |
="# | -0.503 |
arte | -0.480 |
ム | -0.476 |
Token | and |
Token ID | 290 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
izoph | +0.996 |
�� | +0.992 |
="# | +0.942 |
arte | +0.900 |
ム | +0.879 |
Neg logit contributions | |
ocument | -1.208 |
"]," | -1.096 |
outp | -1.068 |
Extrem | -1.041 |
cult | -1.003 |
Token | policies |
Token ID | 4788 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ocument | +3.943 |
"]," | +3.777 |
outp | +3.649 |
Extrem | +3.447 |
cult | +3.320 |
Neg logit contributions | |
�� | -4.521 |
izoph | -4.265 |
="# | -3.882 |
ム | -3.777 |
arte | -3.770 |
Token | that |
Token ID | 326 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
ocument | +1.281 |
"]," | +1.184 |
outp | +1.143 |
Extrem | +1.103 |
cult | +1.061 |
Neg logit contributions | |
�� | -1.311 |
izoph | -1.282 |
="# | -1.178 |
arte | -1.135 |
ム | -1.122 |
Token | grid |
Token ID | 10706 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
ocument | +0.688 |
"]," | +0.646 |
outp | +0.626 |
Extrem | +0.607 |
cult | +0.589 |
Neg logit contributions | |
�� | -0.502 |
izoph | -0.488 |
="# | -0.439 |
arte | -0.418 |
ム | -0.411 |
Token | point |
Token ID | 966 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
ocument | +0.788 |
"]," | +0.733 |
outp | +0.709 |
Extrem | +0.683 |
cult | +0.658 |
Neg logit contributions | |
�� | -0.764 |
izoph | -0.745 |
="# | -0.679 |
arte | -0.654 |
ム | -0.645 |
Token | ; |
Token ID | 26 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
�� | +0.384 |
izoph | +0.375 |
="# | +0.345 |
arte | +0.333 |
ム | +0.329 |
Neg logit contributions | |
ocument | -0.335 |
"]," | -0.310 |
outp | -0.298 |
Extrem | -0.286 |
cult | -0.275 |
Token | grid |
Token ID | 10706 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ocument | +0.407 |
"]," | +0.377 |
outp | +0.362 |
Extrem | +0.347 |
cult | +0.337 |
Neg logit contributions | |
�� | -0.420 |
izoph | -0.410 |
="# | -0.377 |
arte | -0.362 |
ム | -0.356 |
Token | points |
Token ID | 2173 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
�� | +0.162 |
izoph | +0.159 |
="# | +0.147 |
arte | +0.141 |
ム | +0.139 |
Neg logit contributions | |
ocument | -0.146 |
"]," | -0.135 |
outp | -0.129 |
Extrem | -0.124 |
cult | -0.120 |
Token | closer |
Token ID | 5699 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
�� | +3.964 |
izoph | +3.879 |
="# | +3.672 |
arte | +3.477 |
aster | +3.475 |
Neg logit contributions | |
ocument | -4.508 |
"]," | -4.092 |
outp | -3.781 |
Extrem | -3.759 |
Fla | -3.744 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
�� | +6.417 |
izoph | +6.219 |
="# | +5.910 |
aster | +5.576 |
ム | +5.441 |
Neg logit contributions | |
ocument | -8.434 |
"]," | -7.753 |
outp | -7.119 |
Extrem | -7.071 |
Fla | -6.986 |
Token | a |
Token ID | 257 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
�� | +1.283 |
izoph | +1.258 |
="# | +1.156 |
arte | +1.097 |
ム | +1.082 |
Neg logit contributions | |
ocument | -1.299 |
"]," | -1.194 |
outp | -1.147 |
Extrem | -1.108 |
cult | -1.080 |
Token | v |
Token ID | 410 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
�� | +0.874 |
izoph | +0.853 |
="# | +0.792 |
arte | +0.748 |
ム | +0.739 |
Neg logit contributions | |
ocument | -0.883 |
"]," | -0.815 |
outp | -0.784 |
Extrem | -0.759 |
cult | -0.736 |
Token | ort |
Token ID | 419 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ocument | +1.313 |
"]," | +1.228 |
outp | +1.191 |
Extrem | +1.152 |
cult | +1.113 |
Neg logit contributions | |
�� | -1.053 |
izoph | -1.027 |
="# | -0.927 |
arte | -0.890 |
ム | -0.873 |
Token | on |
Token ID | 261 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
�� | +0.181 |
izoph | +0.177 |
="# | +0.162 |
arte | +0.156 |
ム | +0.155 |
Neg logit contributions | |
ocument | -0.157 |
"]," | -0.146 |
outp | -0.141 |
Extrem | -0.135 |
cult | -0.129 |
Token | ( |
Token ID | 7 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
izoph | +7.883 |
="# | +7.762 |
aster | +7.709 |
�� | +7.700 |
arte | +7.648 |
Neg logit contributions | |
ocument | -8.464 |
"]," | -7.465 |
outp | -7.378 |
Extrem | -7.331 |
Exhibit | -7.079 |
Token | 0 |
Token ID | 15 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
�� | +3.714 |
izoph | +3.669 |
="# | +3.407 |
arte | +3.313 |
ム | +3.246 |
Neg logit contributions | |
ocument | -3.540 |
"]," | -3.255 |
outp | -3.185 |
Extrem | -3.047 |
cult | -2.927 |
Token | , |
Token ID | 11 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
ocument | +0.214 |
"]," | +0.197 |
outp | +0.189 |
Extrem | +0.181 |
cult | +0.173 |
Neg logit contributions | |
�� | -0.273 |
izoph | -0.268 |
="# | -0.247 |
arte | -0.239 |
ム | -0.236 |
Token | 0 |
Token ID | 15 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
�� | +3.027 |
izoph | +2.993 |
="# | +2.742 |
arte | +2.647 |
ム | +2.585 |
Neg logit contributions | |
ocument | -3.726 |
"]," | -3.452 |
outp | -3.413 |
Extrem | -3.272 |
cult | -3.170 |
Token | , |
Token ID | 11 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
�� | +0.336 |
izoph | +0.329 |
="# | +0.304 |
arte | +0.294 |
ム | +0.291 |
Neg logit contributions | |
ocument | -0.260 |
"]," | -0.239 |
outp | -0.229 |
Extrem | -0.219 |
cult | -0.210 |
Token | ($ |
Token ID | 16763 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
�� | +3.373 |
izoph | +3.341 |
="# | +3.051 |
arte | +2.955 |
ム | +2.891 |
Neg logit contributions | |
ocument | -4.559 |
"]," | -4.232 |
outp | -4.199 |
Extrem | -4.030 |
Exhibit | -3.910 |
Token | SR |
Token ID | 12562 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
�� | +7.415 |
izoph | +7.268 |
="# | +6.950 |
arte | +6.678 |
aster | +6.440 |
Neg logit contributions | |
ocument | -9.218 |
outp | -8.603 |
"]," | -8.505 |
Extrem | -8.495 |
Exhibit | -8.060 |
Token | . |
Token ID | 13 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
�� | +4.501 |
izoph | +4.453 |
="# | +4.119 |
arte | +3.922 |
ム | +3.905 |
Neg logit contributions | |
ocument | -4.447 |
"]," | -4.135 |
outp | -3.989 |
Extrem | -3.876 |
cult | -3.705 |
Token | Width |
Token ID | 30916 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
�� | +0.489 |
izoph | +0.479 |
="# | +0.443 |
arte | +0.426 |
ム | +0.421 |
Neg logit contributions | |
ocument | -0.465 |
"]," | -0.428 |
outp | -0.417 |
Extrem | -0.398 |
cult | -0.383 |
Token | ), |
Token ID | 828 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ocument | +0.102 |
"]," | +0.093 |
outp | +0.090 |
Extrem | +0.086 |
cult | +0.083 |
Neg logit contributions | |
�� | -0.128 |
izoph | -0.126 |
="# | -0.116 |
arte | -0.112 |
ム | -0.111 |
Token | ($ |
Token ID | 16763 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
�� | +2.033 |
izoph | +1.999 |
="# | +1.830 |
arte | +1.754 |
ム | +1.727 |
Neg logit contributions | |
ocument | -2.287 |
"]," | -2.121 |
outp | -2.068 |
Extrem | -1.993 |
cult | -1.924 |
Token | globally |
Token ID | 18309 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
�� | +1.708 |
izoph | +1.671 |
="# | +1.548 |
arte | +1.507 |
ム | +1.480 |
Neg logit contributions | |
ocument | -1.766 |
"]," | -1.658 |
outp | -1.552 |
Extrem | -1.501 |
cult | -1.464 |
Token | to |
Token ID | 284 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
�� | +1.693 |
izoph | +1.652 |
="# | +1.525 |
arte | +1.483 |
ム | +1.454 |
Neg logit contributions | |
ocument | -1.676 |
"]," | -1.566 |
outp | -1.479 |
Extrem | -1.439 |
cult | -1.383 |
Token | try |
Token ID | 1949 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
izoph | +3.293 |
�� | +3.226 |
="# | +3.051 |
arte | +2.925 |
aster | +2.898 |
Neg logit contributions | |
ocument | -3.871 |
"]," | -3.534 |
outp | -3.386 |
Extrem | -3.304 |
cult | -3.224 |
Token | and |
Token ID | 290 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
�� | +0.440 |
izoph | +0.429 |
="# | +0.388 |
arte | +0.376 |
ム | +0.371 |
Neg logit contributions | |
ocument | -0.396 |
"]," | -0.369 |
outp | -0.356 |
Extrem | -0.339 |
cult | -0.327 |
Token | establish |
Token ID | 4474 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
izoph | +1.566 |
�� | +1.551 |
="# | +1.450 |
arte | +1.391 |
aster | +1.359 |
Neg logit contributions | |
ocument | -1.771 |
"]," | -1.617 |
outp | -1.544 |
Extrem | -1.533 |
cult | -1.473 |
Token | how |
Token ID | 703 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
izoph | +5.067 |
�� | +4.929 |
="# | +4.617 |
aster | +4.413 |
arte | +4.347 |
Neg logit contributions | |
ocument | -6.403 |
"]," | -5.905 |
outp | -5.580 |
cult | -5.410 |
Extrem | -5.337 |
Token | many |
Token ID | 867 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
izoph | +5.595 |
�� | +5.586 |
="# | +5.090 |
aster | +4.872 |
ム | +4.747 |
Neg logit contributions | |
ocument | -8.684 |
"]," | -7.951 |
outp | -7.259 |
Extrem | -7.220 |
ocks | -7.199 |
Token | turtles |
Token ID | 36288 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
izoph | +4.837 |
�� | +4.825 |
="# | +4.528 |
ム | +4.278 |
aster | +4.247 |
Neg logit contributions | |
ocument | -4.818 |
"]," | -4.416 |
outp | -4.100 |
Extrem | -3.971 |
cult | -3.935 |
Token | worldwide |
Token ID | 8688 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
�� | +2.294 |
izoph | +2.277 |
="# | +2.086 |
arte | +1.996 |
ム | +1.964 |
Neg logit contributions | |
ocument | -2.622 |
"]," | -2.405 |
outp | -2.289 |
Extrem | -2.244 |
cult | -2.186 |
Token | had |
Token ID | 550 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
�� | +3.333 |
izoph | +3.311 |
="# | +3.034 |
arte | +2.891 |
ム | +2.839 |
Neg logit contributions | |
ocument | -4.043 |
"]," | -3.733 |
outp | -3.529 |
Extrem | -3.468 |
cult | -3.387 |
Token | ingested |
Token ID | 44694 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
�� | +3.542 |
izoph | +3.504 |
="# | +3.167 |
ム | +3.067 |
aster | +2.986 |
Neg logit contributions | |
ocument | -4.543 |
"]," | -4.196 |
outp | -3.968 |
Extrem | -3.888 |
cult | -3.825 |
Token | erie |
Token ID | 18287 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
�� | +2.159 |
izoph | +2.103 |
="# | +1.890 |
arte | +1.797 |
ENN | +1.756 |
Neg logit contributions | |
ocument | -3.353 |
"]," | -3.194 |
outp | -3.041 |
Extrem | -2.969 |
cult | -2.849 |
Token | of |
Token ID | 286 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
�� | +3.824 |
izoph | +3.735 |
="# | +3.437 |
arte | +3.347 |
ム | +3.248 |
Neg logit contributions | |
ocument | -4.233 |
"]," | -4.034 |
outp | -3.730 |
Extrem | -3.663 |
cult | -3.530 |
Token | the |
Token ID | 262 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
�� | +5.433 |
izoph | +5.320 |
="# | +4.969 |
arte | +4.851 |
ENN | +4.718 |
Neg logit contributions | |
ocument | -4.939 |
"]," | -4.413 |
outp | -4.075 |
cult | -3.862 |
Extrem | -3.834 |
Token | super |
Token ID | 2208 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
�� | +3.553 |
izoph | +3.484 |
="# | +3.203 |
arte | +3.181 |
ENN | +3.094 |
Neg logit contributions | |
ocument | -3.046 |
"]," | -2.794 |
outp | -2.593 |
Extrem | -2.450 |
cult | -2.408 |
Token | - |
Token ID | 12 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
�� | +0.899 |
izoph | +0.879 |
="# | +0.809 |
arte | +0.787 |
ム | +0.772 |
Neg logit contributions | |
ocument | -0.782 |
"]," | -0.720 |
outp | -0.691 |
Extrem | -0.664 |
Exhibit | -0.631 |
Token | rich |
Token ID | 7527 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
ocument | +0.015 |
"]," | +0.014 |
outp | +0.014 |
Extrem | +0.013 |
cult | +0.013 |
Neg logit contributions | |
�� | -0.012 |
izoph | -0.012 |
="# | -0.011 |
arte | -0.010 |
ム | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
�� | +6.750 |
izoph | +6.651 |
="# | +6.207 |
arte | +6.156 |
ENN | +6.029 |
Neg logit contributions | |
ocument | -7.509 |
"]," | -7.051 |
outp | -6.282 |
Extrem | -6.201 |
cult | -6.172 |
Token | And |
Token ID | 843 |
Feature activation | -4.87e-03 |
Pos logit contributions | |
�� | +0.604 |
izoph | +0.588 |
="# | +0.548 |
arte | +0.526 |
ム | +0.518 |
Neg logit contributions | |
ocument | -0.670 |
"]," | -0.611 |
outp | -0.603 |
Extrem | -0.559 |
cult | -0.558 |
Token | then |
Token ID | 788 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ocument | +0.045 |
"]," | +0.041 |
outp | +0.040 |
Extrem | +0.038 |
cult | +0.037 |
Neg logit contributions | |
�� | -0.046 |
izoph | -0.044 |
="# | -0.041 |
arte | -0.039 |
ENN | -0.038 |
Token | perhaps |
Token ID | 3737 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
�� | +2.887 |
izoph | +2.811 |
="# | +2.628 |
arte | +2.518 |
wagen | +2.455 |
Neg logit contributions | |
ocument | -3.162 |
"]," | -2.906 |
outp | -2.745 |
Extrem | -2.653 |
cult | -2.638 |
Token | we |
Token ID | 356 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
�� | +3.076 |
izoph | +3.046 |
="# | +2.776 |
arte | +2.670 |
aster | +2.619 |
Neg logit contributions | |
ocument | -3.408 |
"]," | -3.114 |
outp | -2.931 |
Extrem | -2.834 |
cult | -2.831 |
Token | eria |
Token ID | 5142 |
Feature activation | -5.50e-03 |
Pos logit contributions | |
ocument | +1.901 |
"]," | +1.750 |
outp | +1.676 |
Extrem | +1.597 |
cult | +1.528 |
Neg logit contributions | |
�� | -2.557 |
izoph | -2.500 |
="# | -2.309 |
arte | -2.222 |
ム | -2.219 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ocument | +0.048 |
"]," | +0.044 |
outp | +0.043 |
Extrem | +0.041 |
cult | +0.039 |
Neg logit contributions | |
�� | -0.054 |
izoph | -0.053 |
="# | -0.049 |
arte | -0.047 |
ム | -0.046 |
Token | topped |
Token ID | 20633 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
ocument | +1.138 |
"]," | +1.056 |
outp | +1.019 |
Extrem | +0.979 |
cult | +0.941 |
Neg logit contributions | |
�� | -1.217 |
izoph | -1.188 |
="# | -1.087 |
arte | -1.049 |
ム | -1.036 |
Token | with |
Token ID | 351 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
�� | +0.351 |
izoph | +0.344 |
="# | +0.315 |
arte | +0.305 |
ム | +0.301 |
Neg logit contributions | |
ocument | -0.314 |
"]," | -0.290 |
outp | -0.280 |
Extrem | -0.269 |
cult | -0.258 |
Token | red |
Token ID | 2266 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
�� | +1.351 |
izoph | +1.331 |
="# | +1.226 |
arte | +1.187 |
ム | +1.164 |
Neg logit contributions | |
ocument | -1.307 |
"]," | -1.196 |
outp | -1.152 |
Extrem | -1.104 |
cial | -1.073 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ocument | +0.066 |
"]," | +0.061 |
outp | +0.058 |
Extrem | +0.056 |
cult | +0.054 |
Neg logit contributions | |
�� | -0.079 |
izoph | -0.078 |
="# | -0.072 |
arte | -0.070 |
ム | -0.069 |
Token | yellow |
Token ID | 7872 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
�� | +7.352 |
izoph | +7.280 |
="# | +6.960 |
arte | +6.772 |
gold | +6.502 |
Neg logit contributions | |
ocument | -9.725 |
"]," | -8.796 |
Extrem | -8.642 |
outp | -8.224 |
cult | -8.168 |
Token | peppers |
Token ID | 31804 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
ocument | +1.998 |
"]," | +1.844 |
outp | +1.777 |
Extrem | +1.700 |
cult | +1.629 |
Neg logit contributions | |
�� | -2.395 |
izoph | -2.341 |
="# | -2.152 |
arte | -2.081 |
ム | -2.055 |
Token | , |
Token ID | 11 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
�� | +0.364 |
izoph | +0.356 |
="# | +0.328 |
arte | +0.319 |
ム | +0.312 |
Neg logit contributions | |
ocument | -0.329 |
"]," | -0.304 |
outp | -0.292 |
Extrem | -0.282 |
cult | -0.270 |
Token | cour |
Token ID | 1093 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
�� | +2.189 |
izoph | +2.146 |
="# | +1.988 |
arte | +1.931 |
ム | +1.883 |
Neg logit contributions | |
ocument | -2.059 |
"]," | -1.880 |
outp | -1.788 |
Extrem | -1.736 |
cult | -1.678 |
Token | get |
Token ID | 1136 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ocument | +1.530 |
"]," | +1.448 |
outp | +1.412 |
Extrem | +1.373 |
cult | +1.335 |
Neg logit contributions | |
�� | -0.786 |
izoph | -0.760 |
="# | -0.661 |
arte | -0.625 |
ム | -0.610 |
Token | in |
Token ID | 287 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
ocument | +0.488 |
"]," | +0.452 |
outp | +0.435 |
Extrem | +0.419 |
cult | +0.403 |
Neg logit contributions | |
�� | -0.520 |
izoph | -0.508 |
="# | -0.466 |
arte | -0.450 |
ム | -0.444 |
Token | September |
Token ID | 2693 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
�� | +0.553 |
izoph | +0.545 |
="# | +0.499 |
arte | +0.476 |
ム | +0.469 |
Neg logit contributions | |
ocument | -0.759 |
"]," | -0.714 |
outp | -0.673 |
Extrem | -0.659 |
cult | -0.649 |
Token | from |
Token ID | 422 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
�� | +1.605 |
izoph | +1.560 |
="# | +1.490 |
arte | +1.426 |
ム | +1.408 |
Neg logit contributions | |
ocument | -1.501 |
"]," | -1.382 |
Extrem | -1.270 |
outp | -1.267 |
cult | -1.221 |
Token | August |
Token ID | 2932 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
�� | +1.875 |
izoph | +1.859 |
="# | +1.727 |
arte | +1.654 |
ム | +1.631 |
Neg logit contributions | |
ocument | -2.229 |
"]," | -2.060 |
outp | -1.925 |
Extrem | -1.897 |
cult | -1.862 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
�� | +1.982 |
izoph | +1.941 |
="# | +1.821 |
arte | +1.766 |
ム | +1.731 |
Neg logit contributions | |
ocument | -1.922 |
"]," | -1.796 |
outp | -1.638 |
Extrem | -1.624 |
cult | -1.571 |
Token |
|
Token ID | 198 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ocument | +0.268 |
"]," | +0.248 |
outp | +0.241 |
Extrem | +0.230 |
cult | +0.223 |
Neg logit contributions | |
�� | -0.259 |
izoph | -0.252 |
="# | -0.232 |
arte | -0.223 |
ム | -0.220 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
="# | +2.055 |
�� | +2.053 |
izoph | +2.016 |
arte | +1.894 |
ム | +1.861 |
Neg logit contributions | |
ocument | -3.190 |
outp | -2.859 |
"]," | -2.811 |
Extrem | -2.707 |
cult | -2.623 |
Token | The |
Token ID | 464 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
�� | +0.112 |
izoph | +0.109 |
="# | +0.101 |
arte | +0.098 |
ム | +0.096 |
Neg logit contributions | |
ocument | -0.113 |
"]," | -0.104 |
outp | -0.101 |
Extrem | -0.098 |
cult | -0.093 |
Token | return |
Token ID | 1441 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
�� | +1.313 |
izoph | +1.295 |
="# | +1.200 |
arte | +1.162 |
ム | +1.140 |
Neg logit contributions | |
ocument | -1.430 |
"]," | -1.326 |
outp | -1.240 |
Extrem | -1.194 |
cult | -1.194 |
Token | of |
Token ID | 286 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ocument | +0.127 |
"]," | +0.117 |
outp | +0.113 |
Extrem | +0.109 |
cult | +0.105 |
Neg logit contributions | |
�� | -0.129 |
izoph | -0.125 |
="# | -0.115 |
arte | -0.111 |
ム | -0.110 |
Token | production |
Token ID | 3227 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ocument | +1.165 |
"]," | +1.075 |
outp | +1.034 |
Extrem | +0.991 |
cult | +0.951 |
Neg logit contributions | |
�� | -1.385 |
izoph | -1.354 |
="# | -1.247 |
arte | -1.206 |
ム | -1.191 |
Token | in |
Token ID | 287 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ocument | +1.222 |
"]," | +1.134 |
outp | +1.096 |
Extrem | +1.051 |
cult | +1.011 |
Neg logit contributions | |
�� | -1.298 |
izoph | -1.268 |
="# | -1.158 |
arte | -1.119 |
ム | -1.105 |
Token | is |
Token ID | 318 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ocument | +3.424 |
"]," | +3.181 |
outp | +3.064 |
Extrem | +2.936 |
Exhibit | +2.808 |
Neg logit contributions | |
�� | -4.192 |
izoph | -4.130 |
="# | -3.751 |
arte | -3.660 |
ム | -3.648 |
Token | illuminated |
Token ID | 35162 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
�� | +1.900 |
izoph | +1.838 |
="# | +1.707 |
arte | +1.607 |
ENN | +1.599 |
Neg logit contributions | |
ocument | -1.984 |
"]," | -1.818 |
outp | -1.743 |
Extrem | -1.709 |
cult | -1.657 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
�� | +1.782 |
izoph | +1.735 |
="# | +1.608 |
arte | +1.528 |
ム | +1.510 |
Neg logit contributions | |
ocument | -1.750 |
"]," | -1.629 |
outp | -1.553 |
Extrem | -1.521 |
cult | -1.456 |
Token | The |
Token ID | 383 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
�� | +0.203 |
izoph | +0.197 |
="# | +0.182 |
arte | +0.174 |
ム | +0.172 |
Neg logit contributions | |
ocument | -0.204 |
"]," | -0.188 |
outp | -0.183 |
Extrem | -0.173 |
cult | -0.169 |
Token | starting |
Token ID | 3599 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ocument | +0.268 |
"]," | +0.246 |
outp | +0.235 |
Extrem | +0.226 |
cult | +0.218 |
Neg logit contributions | |
�� | -0.322 |
izoph | -0.315 |
="# | -0.290 |
arte | -0.280 |
ム | -0.275 |
Token | position |
Token ID | 2292 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
�� | +1.820 |
izoph | +1.771 |
="# | +1.647 |
arte | +1.575 |
ENN | +1.547 |
Neg logit contributions | |
ocument | -1.698 |
"]," | -1.560 |
outp | -1.492 |
Extrem | -1.452 |
cult | -1.403 |
Token | for |
Token ID | 329 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
�� | +2.315 |
izoph | +2.230 |
="# | +2.100 |
arte | +1.988 |
aster | +1.943 |
Neg logit contributions | |
ocument | -2.502 |
"]," | -2.306 |
outp | -2.200 |
Extrem | -2.148 |
cult | -2.094 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
�� | +0.988 |
izoph | +0.965 |
="# | +0.881 |
arte | +0.844 |
ム | +0.831 |
Neg logit contributions | |
ocument | -1.045 |
"]," | -0.972 |
outp | -0.933 |
Extrem | -0.903 |
cult | -0.873 |
Token | monkey |
Token ID | 21657 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
ocument | +0.955 |
"]," | +0.881 |
outp | +0.846 |
Extrem | +0.814 |
cult | +0.785 |
Neg logit contributions | |
�� | -1.050 |
izoph | -1.027 |
="# | -0.943 |
arte | -0.910 |
ム | -0.896 |
Token | ( |
Token ID | 357 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
�� | +0.580 |
izoph | +0.562 |
="# | +0.521 |
arte | +0.501 |
ム | +0.492 |
Neg logit contributions | |
ocument | -0.567 |
"]," | -0.526 |
outp | -0.504 |
Extrem | -0.489 |
cult | -0.469 |
Token | voucher |
Token ID | 40621 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
ocument | +0.342 |
"]," | +0.315 |
outp | +0.301 |
Extrem | +0.290 |
cult | +0.278 |
Neg logit contributions | |
�� | -0.406 |
izoph | -0.397 |
="# | -0.366 |
arte | -0.353 |
ム | -0.349 |
Token | programs |
Token ID | 4056 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
�� | +0.335 |
izoph | +0.328 |
="# | +0.303 |
arte | +0.292 |
ム | +0.287 |
Neg logit contributions | |
ocument | -0.307 |
"]," | -0.281 |
outp | -0.268 |
Extrem | -0.260 |
cult | -0.250 |
Token | . |
Token ID | 13 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
�� | +0.561 |
izoph | +0.544 |
="# | +0.502 |
arte | +0.487 |
ム | +0.479 |
Neg logit contributions | |
ocument | -0.518 |
"]," | -0.484 |
outp | -0.457 |
Extrem | -0.444 |
cult | -0.429 |
Token | " |
Token ID | 366 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ocument | +3.958 |
"]," | +3.735 |
outp | +3.531 |
Extrem | +3.525 |
Exhibit | +3.371 |
Neg logit contributions | |
�� | -4.279 |
izoph | -4.212 |
="# | -3.724 |
arte | -3.618 |
wagen | -3.577 |
Token | Where |
Token ID | 8496 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ocument | +2.456 |
"]," | +2.297 |
outp | +2.200 |
Extrem | +2.127 |
cult | +2.059 |
Neg logit contributions | |
�� | -2.382 |
izoph | -2.326 |
="# | -2.090 |
arte | -2.021 |
ム | -1.990 |
Token | public |
Token ID | 1171 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
�� | +1.303 |
izoph | +1.261 |
="# | +1.168 |
arte | +1.128 |
ENN | +1.097 |
Neg logit contributions | |
ocument | -1.385 |
"]," | -1.295 |
outp | -1.238 |
Extrem | -1.195 |
cult | -1.158 |
Token | money |
Token ID | 1637 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
�� | +2.007 |
izoph | +1.973 |
="# | +1.850 |
arte | +1.764 |
wagen | +1.741 |
Neg logit contributions | |
ocument | -1.875 |
"]," | -1.721 |
outp | -1.592 |
Extrem | -1.581 |
cult | -1.522 |
Token | flows |
Token ID | 15623 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
�� | +1.306 |
izoph | +1.269 |
="# | +1.195 |
arte | +1.136 |
wagen | +1.102 |
Neg logit contributions | |
ocument | -1.449 |
"]," | -1.329 |
Extrem | -1.240 |
outp | -1.239 |
cult | -1.194 |
Token | , |
Token ID | 11 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
ocument | +0.622 |
"]," | +0.575 |
outp | +0.550 |
Extrem | +0.532 |
cult | +0.512 |
Neg logit contributions | |
�� | -0.662 |
izoph | -0.647 |
="# | -0.595 |
arte | -0.573 |
ム | -0.564 |
Token | public |
Token ID | 1171 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
�� | +0.428 |
izoph | +0.418 |
="# | +0.384 |
arte | +0.369 |
ム | +0.362 |
Neg logit contributions | |
ocument | -0.430 |
"]," | -0.397 |
outp | -0.379 |
Extrem | -0.367 |
cult | -0.355 |
Token | accountability |
Token ID | 18241 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
izoph | +3.929 |
�� | +3.898 |
="# | +3.713 |
arte | +3.513 |
aster | +3.508 |
Neg logit contributions | |
ocument | -4.084 |
"]," | -3.703 |
Extrem | -3.419 |
outp | -3.327 |
cult | -3.275 |
Token | v |
Token ID | 410 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ocument | +1.688 |
"]," | +1.561 |
outp | +1.485 |
Extrem | +1.439 |
cult | +1.391 |
Neg logit contributions | |
�� | -1.870 |
izoph | -1.838 |
="# | -1.696 |
arte | -1.639 |
ム | -1.610 |
Token | . |
Token ID | 764 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
izoph | +1.251 |
�� | +1.244 |
="# | +1.185 |
arte | +1.137 |
ム | +1.107 |
Neg logit contributions | |
ocument | -1.900 |
"]," | -1.760 |
outp | -1.698 |
Extrem | -1.642 |
cult | -1.601 |
Token | normal |
Token ID | 3487 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ocument | +3.385 |
outp | +3.028 |
"]," | +2.927 |
Extrem | +2.650 |
naturally | +2.507 |
Neg logit contributions | |
�� | -9.633 |
izoph | -9.267 |
="# | -8.797 |
ム | -8.560 |
ENN | -8.418 |
Token | * |
Token ID | 1635 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
�� | +1.699 |
izoph | +1.680 |
="# | +1.616 |
arte | +1.584 |
ム | +1.569 |
Neg logit contributions | |
ocument | -1.138 |
"]," | -1.022 |
outp | -0.934 |
Extrem | -0.910 |
cult | -0.872 |
Token | 1 |
Token ID | 352 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
izoph | +2.379 |
�� | +2.351 |
="# | +2.241 |
arte | +2.167 |
aster | +2.087 |
Neg logit contributions | |
ocument | -2.747 |
"]," | -2.492 |
Extrem | -2.313 |
outp | -2.311 |
cult | -2.281 |
Token | ; |
Token ID | 2162 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ocument | +4.837 |
outp | +4.419 |
"]," | +4.352 |
Extrem | +4.179 |
Exhibit | +4.002 |
Neg logit contributions | |
�� | -7.583 |
izoph | -7.335 |
="# | -6.568 |
wagen | -6.398 |
arte | -6.324 |
Token | } |
Token ID | 1782 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
�� | +0.285 |
izoph | +0.281 |
="# | +0.266 |
arte | +0.261 |
ム | +0.255 |
Neg logit contributions | |
ocument | -0.138 |
"]," | -0.122 |
outp | -0.112 |
Extrem | -0.106 |
cult | -0.102 |
Token |
|
Token ID | 198 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
�� | +5.087 |
izoph | +4.966 |
="# | +4.483 |
arte | +4.432 |
wagen | +4.272 |
Neg logit contributions | |
ocument | -6.634 |
"]," | -6.250 |
outp | -6.038 |
Extrem | -5.739 |
cult | -5.736 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ocument | +0.247 |
"]," | +0.226 |
outp | +0.221 |
Extrem | +0.213 |
cult | +0.205 |
Neg logit contributions | |
�� | -0.214 |
izoph | -0.210 |
="# | -0.196 |
arte | -0.187 |
ム | -0.184 |
Token | The |
Token ID | 464 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
�� | +1.698 |
izoph | +1.662 |
="# | +1.533 |
arte | +1.476 |
ム | +1.437 |
Neg logit contributions | |
ocument | -2.095 |
"]," | -1.962 |
outp | -1.928 |
Extrem | -1.854 |
Exhibit | -1.776 |
Token | result |
Token ID | 1255 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
�� | +0.723 |
izoph | +0.712 |
="# | +0.661 |
arte | +0.635 |
ム | +0.624 |
Neg logit contributions | |
ocument | -0.622 |
"]," | -0.576 |
outp | -0.543 |
Extrem | -0.522 |
cult | -0.512 |
Token | , |
Token ID | 11 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
�� | +2.293 |
izoph | +2.247 |
="# | +2.095 |
arte | +2.024 |
ム | +1.993 |
Neg logit contributions | |
ocument | -2.141 |
"]," | -1.970 |
outp | -1.868 |
Extrem | -1.812 |
cult | -1.739 |
Token | � |
Token ID | 564 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
�� | +6.191 |
izoph | +6.032 |
="# | +5.720 |
Bowen | +5.458 |
arte | +5.423 |
Neg logit contributions | |
ocument | -7.398 |
"]," | -6.775 |
outp | -6.462 |
cult | -6.202 |
Extrem | -6.147 |
Token | � |
Token ID | 250 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
ocument | +1.643 |
"]," | +1.560 |
outp | +1.517 |
Extrem | +1.474 |
cult | +1.433 |
Neg logit contributions | |
�� | -0.887 |
izoph | -0.874 |
="# | -0.761 |
arte | -0.721 |
wagen | -0.702 |
Token | he |
Token ID | 258 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
�� | +1.879 |
izoph | +1.822 |
="# | +1.658 |
arte | +1.582 |
ム | +1.568 |
Neg logit contributions | |
ocument | -2.652 |
"]," | -2.499 |
outp | -2.431 |
Extrem | -2.352 |
Exhibit | -2.263 |
Token | doesn |
Token ID | 1595 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
�� | +0.238 |
izoph | +0.232 |
="# | +0.213 |
arte | +0.207 |
ム | +0.203 |
Neg logit contributions | |
ocument | -0.255 |
"]," | -0.236 |
outp | -0.228 |
Extrem | -0.221 |
cult | -0.212 |
Token | � |
Token ID | 447 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ocument | +0.378 |
"]," | +0.345 |
outp | +0.337 |
Extrem | +0.321 |
cult | +0.306 |
Neg logit contributions | |
�� | -0.437 |
izoph | -0.430 |
="# | -0.402 |
arte | -0.387 |
ム | -0.383 |
Token | � |
Token ID | 247 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
ocument | +0.167 |
"]," | +0.159 |
outp | +0.155 |
Extrem | +0.152 |
cult | +0.148 |
Neg logit contributions | |
�� | -0.055 |
izoph | -0.052 |
="# | -0.043 |
arte | -0.039 |
ム | -0.038 |
Token | t |
Token ID | 83 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ocument | +0.388 |
"]," | +0.358 |
outp | +0.346 |
Extrem | +0.334 |
cult | +0.318 |
Neg logit contributions | |
�� | -0.395 |
izoph | -0.386 |
="# | -0.355 |
arte | -0.343 |
ム | -0.338 |
Token | know |
Token ID | 760 |
Feature activation | +2.59e-03 |
Pos logit contributions | |
ocument | +1.056 |
"]," | +0.978 |
outp | +0.943 |
Extrem | +0.913 |
cult | +0.878 |
Neg logit contributions | |
�� | -1.008 |
izoph | -0.989 |
="# | -0.910 |
arte | -0.874 |
ム | -0.861 |
Token | where |
Token ID | 810 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
�� | +0.024 |
izoph | +0.023 |
="# | +0.021 |
arte | +0.021 |
ム | +0.020 |
Neg logit contributions | |
ocument | -0.024 |
"]," | -0.022 |
outp | -0.021 |
Extrem | -0.021 |
cult | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
�� | +2.298 |
izoph | +2.257 |
="# | +2.092 |
arte | +2.008 |
ム | +1.960 |
Neg logit contributions | |
ocument | -2.475 |
"]," | -2.316 |
outp | -2.206 |
Extrem | -2.102 |
cult | -2.077 |
Token | LE |
Token ID | 2538 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
�� | +3.096 |
izoph | +2.989 |
="# | +2.699 |
arte | +2.623 |
ENN | +2.601 |
Neg logit contributions | |
ocument | -4.523 |
"]," | -4.262 |
outp | -4.140 |
Extrem | -3.973 |
cial | -3.890 |
Token | Online |
Token ID | 7467 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
�� | +3.338 |
izoph | +3.288 |
="# | +3.006 |
arte | +2.919 |
ENN | +2.902 |
Neg logit contributions | |
ocument | -3.197 |
"]," | -3.029 |
outp | -2.941 |
Extrem | -2.799 |
cult | -2.666 |
Token | : |
Token ID | 25 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
�� | +2.346 |
izoph | +2.308 |
="# | +2.124 |
arte | +2.042 |
ム | +2.009 |
Neg logit contributions | |
ocument | -2.037 |
"]," | -1.874 |
outp | -1.820 |
Extrem | -1.706 |
cult | -1.666 |
Token | Research |
Token ID | 4992 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
�� | +4.000 |
izoph | +3.884 |
="# | +3.611 |
arte | +3.479 |
ム | +3.449 |
Neg logit contributions | |
ocument | -3.870 |
"]," | -3.532 |
outp | -3.466 |
Extrem | -3.216 |
tarians | -3.173 |
Token | in |
Token ID | 287 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
�� | +5.146 |
izoph | +5.088 |
="# | +4.672 |
arte | +4.526 |
ム | +4.464 |
Neg logit contributions | |
ocument | -5.307 |
"]," | -4.815 |
outp | -4.635 |
cult | -4.388 |
Extrem | -4.372 |
Token | Middle |
Token ID | 6046 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
ocument | +0.883 |
"]," | +0.819 |
outp | +0.789 |
Extrem | +0.760 |
cult | +0.728 |
Neg logit contributions | |
�� | -0.981 |
izoph | -0.959 |
="# | -0.879 |
arte | -0.848 |
ム | -0.838 |
Token | Level |
Token ID | 5684 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ocument | +4.821 |
"]," | +4.465 |
Extrem | +4.256 |
outp | +4.214 |
cult | +4.061 |
Neg logit contributions | |
�� | -5.376 |
izoph | -5.245 |
="# | -4.809 |
wagen | -4.623 |
arte | -4.598 |
Token | Education |
Token ID | 7868 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ocument | +3.332 |
"]," | +3.106 |
outp | +2.956 |
Extrem | +2.927 |
cult | +2.759 |
Neg logit contributions | |
�� | -4.174 |
izoph | -4.059 |
="# | -3.726 |
ム | -3.602 |
arte | -3.599 |
Token | , |
Token ID | 11 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
�� | +1.068 |
izoph | +1.050 |
="# | +0.970 |
arte | +0.938 |
ム | +0.922 |
Neg logit contributions | |
ocument | -0.920 |
"]," | -0.846 |
outp | -0.817 |
Extrem | -0.774 |
cult | -0.753 |
Token | 33 |
Token ID | 4747 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
�� | +1.701 |
izoph | +1.674 |
="# | +1.561 |
arte | +1.507 |
ム | +1.474 |
Neg logit contributions | |
ocument | -1.613 |
"]," | -1.481 |
outp | -1.422 |
Extrem | -1.353 |
cult | -1.328 |
Token | ( |
Token ID | 7 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
�� | +2.156 |
izoph | +2.109 |
="# | +1.939 |
arte | +1.874 |
ム | +1.853 |
Neg logit contributions | |
ocument | -1.844 |
"]," | -1.702 |
outp | -1.640 |
Extrem | -1.573 |
cult | -1.506 |
Token | interested |
Token ID | 4609 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ocument | +1.345 |
"]," | +1.252 |
outp | +1.207 |
Extrem | +1.164 |
cult | +1.122 |
Neg logit contributions | |
�� | -1.322 |
izoph | -1.290 |
="# | -1.178 |
arte | -1.134 |
ム | -1.119 |
Token | in |
Token ID | 287 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
�� | +2.833 |
izoph | +2.748 |
="# | +2.561 |
arte | +2.435 |
ム | +2.382 |
Neg logit contributions | |
ocument | -2.992 |
"]," | -2.805 |
outp | -2.656 |
Extrem | -2.604 |
cial | -2.509 |
Token | supporting |
Token ID | 6493 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ocument | +1.293 |
"]," | +1.204 |
outp | +1.163 |
Extrem | +1.121 |
cult | +1.080 |
Neg logit contributions | |
�� | -1.238 |
izoph | -1.207 |
="# | -1.100 |
arte | -1.059 |
ム | -1.044 |
Token | them |
Token ID | 606 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
ocument | +2.084 |
"]," | +1.903 |
outp | +1.841 |
Extrem | +1.747 |
cult | +1.658 |
Neg logit contributions | |
�� | -3.036 |
izoph | -2.967 |
="# | -2.733 |
arte | -2.667 |
ム | -2.637 |
Token | and |
Token ID | 290 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ocument | +0.773 |
"]," | +0.717 |
outp | +0.688 |
Extrem | +0.664 |
cult | +0.638 |
Neg logit contributions | |
�� | -0.832 |
izoph | -0.814 |
="# | -0.747 |
arte | -0.720 |
ム | -0.711 |
Token | ask |
Token ID | 1265 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
�� | +2.588 |
izoph | +2.510 |
="# | +2.368 |
arte | +2.242 |
aster | +2.189 |
Neg logit contributions | |
ocument | -2.939 |
"]," | -2.658 |
outp | -2.526 |
Extrem | -2.497 |
cult | -2.430 |
Token | them |
Token ID | 606 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ocument | +3.207 |
"]," | +2.949 |
outp | +2.858 |
Extrem | +2.734 |
Exhibit | +2.588 |
Neg logit contributions | |
�� | -4.390 |
izoph | -4.261 |
="# | -3.893 |
arte | -3.809 |
ム | -3.790 |
Token | to |
Token ID | 284 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ocument | +3.491 |
"]," | +3.210 |
outp | +3.127 |
Extrem | +2.991 |
cial | +2.866 |
Neg logit contributions | |
�� | -4.099 |
izoph | -3.949 |
="# | -3.587 |
arte | -3.510 |
ム | -3.474 |
Token | articulate |
Token ID | 32154 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ocument | +1.836 |
"]," | +1.694 |
outp | +1.631 |
Extrem | +1.575 |
cult | +1.512 |
Neg logit contributions | |
�� | -1.970 |
izoph | -1.936 |
="# | -1.784 |
arte | -1.715 |
ム | -1.688 |
Token | what |
Token ID | 644 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
�� | +1.256 |
izoph | +1.251 |
="# | +1.146 |
arte | +1.077 |
ム | +1.064 |
Neg logit contributions | |
ocument | -1.433 |
"]," | -1.338 |
outp | -1.268 |
Extrem | -1.231 |
cult | -1.208 |
Token | they |
Token ID | 484 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
�� | +0.754 |
izoph | +0.748 |
="# | +0.692 |
arte | +0.661 |
ム | +0.651 |
Neg logit contributions | |
ocument | -0.701 |
"]," | -0.653 |
outp | -0.617 |
Extrem | -0.596 |
cult | -0.577 |
Token | business |
Token ID | 1597 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
ocument | +0.985 |
"]," | +0.913 |
outp | +0.880 |
Extrem | +0.844 |
cult | +0.811 |
Neg logit contributions | |
�� | -1.121 |
izoph | -1.095 |
="# | -1.003 |
arte | -0.970 |
ム | -0.957 |
Token | were |
Token ID | 547 |
Feature activation | -7.41e-03 |
Pos logit contributions | |
�� | +0.301 |
izoph | +0.293 |
="# | +0.271 |
arte | +0.262 |
ム | +0.257 |
Neg logit contributions | |
ocument | -0.294 |
"]," | -0.270 |
outp | -0.261 |
Extrem | -0.252 |
cult | -0.242 |
Token | sent |
Token ID | 1908 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
ocument | +0.063 |
"]," | +0.058 |
outp | +0.055 |
Extrem | +0.054 |
cult | +0.052 |
Neg logit contributions | |
�� | -0.073 |
izoph | -0.072 |
="# | -0.067 |
arte | -0.065 |
ム | -0.064 |
Token | letters |
Token ID | 7475 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
ocument | +3.167 |
"]," | +2.915 |
outp | +2.855 |
Extrem | +2.744 |
cial | +2.603 |
Neg logit contributions | |
�� | -3.804 |
izoph | -3.701 |
="# | -3.324 |
arte | -3.245 |
ム | -3.183 |
Token | asking |
Token ID | 4737 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
�� | +0.633 |
izoph | +0.619 |
="# | +0.579 |
arte | +0.547 |
ム | +0.542 |
Neg logit contributions | |
ocument | -0.639 |
"]," | -0.594 |
outp | -0.558 |
Extrem | -0.541 |
cult | -0.528 |
Token | them |
Token ID | 606 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ocument | +0.837 |
"]," | +0.774 |
outp | +0.746 |
Extrem | +0.715 |
cult | +0.688 |
Neg logit contributions | |
�� | -0.931 |
izoph | -0.910 |
="# | -0.838 |
arte | -0.808 |
ム | -0.797 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ocument | +1.765 |
"]," | +1.635 |
outp | +1.573 |
Extrem | +1.497 |
cult | +1.452 |
Neg logit contributions | |
�� | -2.110 |
izoph | -2.061 |
="# | -1.841 |
arte | -1.798 |
ム | -1.776 |
Token | attend |
Token ID | 5262 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
izoph | +1.498 |
�� | +1.491 |
="# | +1.429 |
arte | +1.336 |
aster | +1.323 |
Neg logit contributions | |
ocument | -1.674 |
"]," | -1.517 |
outp | -1.472 |
Extrem | -1.443 |
cult | -1.390 |
Token | an |
Token ID | 281 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ocument | +4.802 |
"]," | +4.458 |
outp | +4.325 |
Extrem | +4.184 |
Exhibit | +3.944 |
Neg logit contributions | |
�� | -6.119 |
izoph | -5.904 |
="# | -5.331 |
arte | -5.279 |
ム | -5.200 |
Token | interview |
Token ID | 2720 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ocument | +1.696 |
"]," | +1.561 |
outp | +1.507 |
Extrem | +1.432 |
cult | +1.356 |
Neg logit contributions | |
�� | -2.331 |
izoph | -2.268 |
="# | -2.096 |
arte | -2.033 |
ム | -2.011 |
Token | under |
Token ID | 739 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ocument | +0.886 |
"]," | +0.819 |
outp | +0.787 |
Extrem | +0.757 |
cult | +0.727 |
Neg logit contributions | |
�� | -0.990 |
izoph | -0.969 |
="# | -0.893 |
arte | -0.861 |
ム | -0.851 |
Token | � |
Token ID | 247 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ocument | +2.453 |
"]," | +2.337 |
outp | +2.285 |
Extrem | +2.230 |
cult | +2.177 |
Neg logit contributions | |
�� | -0.820 |
izoph | -0.778 |
="# | -0.640 |
arte | -0.587 |
ム | -0.570 |
Token | s |
Token ID | 82 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
�� | +0.190 |
izoph | +0.185 |
="# | +0.169 |
arte | +0.164 |
ム | +0.161 |
Neg logit contributions | |
ocument | -0.187 |
"]," | -0.174 |
outp | -0.167 |
Extrem | -0.162 |
cult | -0.154 |
Token | more |
Token ID | 517 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
�� | +0.137 |
izoph | +0.134 |
="# | +0.122 |
arte | +0.118 |
ム | +0.116 |
Neg logit contributions | |
ocument | -0.145 |
"]," | -0.135 |
outp | -0.127 |
Extrem | -0.125 |
cult | -0.120 |
Token | significant |
Token ID | 2383 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ocument | +2.806 |
"]," | +2.599 |
outp | +2.535 |
Extrem | +2.400 |
cult | +2.296 |
Neg logit contributions | |
�� | -3.590 |
izoph | -3.491 |
="# | -3.220 |
arte | -3.118 |
ム | -3.079 |
Token | than |
Token ID | 621 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ocument | +1.754 |
"]," | +1.607 |
outp | +1.557 |
Extrem | +1.470 |
cult | +1.405 |
Neg logit contributions | |
�� | -2.482 |
izoph | -2.423 |
="# | -2.239 |
arte | -2.177 |
ム | -2.149 |
Token | a |
Token ID | 257 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ocument | +2.963 |
"]," | +2.758 |
outp | +2.710 |
Extrem | +2.571 |
Exhibit | +2.487 |
Neg logit contributions | |
�� | -3.314 |
izoph | -3.237 |
="# | -2.979 |
arte | -2.874 |
ム | -2.831 |
Token | tweet |
Token ID | 6126 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ocument | +1.856 |
"]," | +1.711 |
outp | +1.659 |
Extrem | +1.577 |
cult | +1.512 |
Neg logit contributions | |
�� | -2.365 |
izoph | -2.314 |
="# | -2.130 |
arte | -2.070 |
ム | -2.033 |
Token | . |
Token ID | 13 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
�� | +2.611 |
izoph | +2.555 |
="# | +2.405 |
arte | +2.309 |
aster | +2.272 |
Neg logit contributions | |
ocument | -2.589 |
"]," | -2.417 |
outp | -2.259 |
Extrem | -2.224 |
cult | -2.131 |
Token | I |
Token ID | 314 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
ocument | +0.454 |
"]," | +0.418 |
outp | +0.408 |
Extrem | +0.386 |
cult | +0.377 |
Neg logit contributions | |
�� | -0.437 |
izoph | -0.426 |
="# | -0.393 |
arte | -0.379 |
ム | -0.374 |
Token | � |
Token ID | 447 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ocument | +0.240 |
"]," | +0.222 |
outp | +0.214 |
Extrem | +0.206 |
cult | +0.198 |
Neg logit contributions | |
�� | -0.240 |
izoph | -0.236 |
="# | -0.217 |
arte | -0.210 |
ム | -0.205 |
Token | � |
Token ID | 247 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
ocument | +0.291 |
"]," | +0.278 |
outp | +0.272 |
Extrem | +0.266 |
cult | +0.259 |
Neg logit contributions | |
�� | -0.088 |
izoph | -0.082 |
="# | -0.067 |
arte | -0.061 |
ム | -0.059 |
Token | Bo |
Token ID | 3248 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
ocument | +2.352 |
"]," | +2.235 |
outp | +2.149 |
Extrem | +2.084 |
ocks | +1.956 |
Neg logit contributions | |
�� | -3.704 |
izoph | -3.630 |
="# | -3.219 |
ム | -3.157 |
arte | -3.081 |
Token | ass |
Token ID | 562 |
Feature activation | -5.20e-04 |
Pos logit contributions | |
�� | +0.133 |
izoph | +0.129 |
="# | +0.111 |
arte | +0.107 |
ム | +0.103 |
Neg logit contributions | |
ocument | -0.279 |
"]," | -0.264 |
outp | -0.258 |
Extrem | -0.251 |
cult | -0.244 |
Token | on |
Token ID | 261 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
ocument | +0.005 |
"]," | +0.005 |
outp | +0.004 |
Extrem | +0.004 |
cult | +0.004 |
Neg logit contributions | |
�� | -0.005 |
izoph | -0.005 |
="# | -0.004 |
arte | -0.004 |
ム | -0.004 |
Token | H |
Token ID | 367 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
�� | +3.801 |
izoph | +3.735 |
="# | +3.505 |
arte | +3.428 |
ム | +3.232 |
Neg logit contributions | |
ocument | -4.300 |
"]," | -3.832 |
outp | -3.677 |
Extrem | -3.546 |
cult | -3.516 |
Token | agen |
Token ID | 11286 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
ocument | +1.972 |
"]," | +1.827 |
outp | +1.762 |
Extrem | +1.695 |
cult | +1.633 |
Neg logit contributions | |
�� | -2.032 |
izoph | -1.994 |
="# | -1.822 |
arte | -1.762 |
ム | -1.734 |
Token | ( |
Token ID | 357 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
ocument | +3.743 |
"]," | +3.590 |
outp | +3.431 |
Extrem | +3.264 |
cial | +3.049 |
Neg logit contributions | |
�� | -6.241 |
izoph | -6.129 |
="# | -5.614 |
ム | -5.309 |
skinned | -5.298 |
Token | Sky |
Token ID | 22308 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ocument | +0.802 |
"]," | +0.737 |
outp | +0.715 |
Extrem | +0.683 |
cult | +0.657 |
Neg logit contributions | |
�� | -0.851 |
izoph | -0.832 |
="# | -0.769 |
arte | -0.742 |
ム | -0.734 |
Token | Pro |
Token ID | 1041 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ocument | +2.874 |
"]," | +2.859 |
outp | +2.642 |
Extrem | +2.587 |
cial | +2.393 |
Neg logit contributions | |
�� | -5.133 |
izoph | -5.021 |
="# | -4.597 |
ム | -4.520 |
arte | -4.481 |
Token | cy |
Token ID | 948 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
�� | +0.765 |
izoph | +0.730 |
="# | +0.673 |
arte | +0.640 |
ム | +0.623 |
Neg logit contributions | |
ocument | -1.107 |
"]," | -1.019 |
outp | -0.990 |
Extrem | -0.967 |
cult | -0.931 |
Token | cling |
Token ID | 8493 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ocument | +1.568 |
"]," | +1.431 |
outp | +1.308 |
Extrem | +1.204 |
cial | +1.168 |
Neg logit contributions | |
�� | -3.700 |
izoph | -3.641 |
="# | -3.392 |
arte | -3.288 |
ム | -3.271 |
Token | ) |
Token ID | 8 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ocument | +1.424 |
"]," | +1.353 |
outp | +1.283 |
Extrem | +1.231 |
cult | +1.160 |
Neg logit contributions | |
�� | -1.986 |
izoph | -1.928 |
="# | -1.763 |
arte | -1.718 |
ム | -1.709 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
�� | +0.235 |
izoph | +0.231 |
="# | +0.213 |
arte | +0.206 |
ム | +0.204 |
Neg logit contributions | |
ocument | -0.205 |
"]," | -0.190 |
outp | -0.180 |
Extrem | -0.174 |
cult | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ocument | +1.347 |
"]," | +1.258 |
outp | +1.206 |
Extrem | +1.174 |
cult | +1.119 |
Neg logit contributions | |
�� | -1.401 |
izoph | -1.368 |
="# | -1.241 |
arte | -1.196 |
ム | -1.178 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
�� | +1.210 |
izoph | +1.193 |
="# | +1.150 |
arte | +1.087 |
ム | +1.070 |
Neg logit contributions | |
ocument | -1.615 |
"]," | -1.444 |
outp | -1.441 |
Extrem | -1.380 |
cult | -1.335 |
Token | Ms |
Token ID | 10128 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ocument | +0.997 |
"]," | +0.928 |
outp | +0.898 |
Extrem | +0.865 |
cult | +0.833 |
Neg logit contributions | |
�� | -0.952 |
izoph | -0.928 |
="# | -0.846 |
arte | -0.814 |
ム | -0.803 |
Token | . |
Token ID | 13 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
ocument | +2.750 |
"]," | +2.561 |
outp | +2.443 |
Extrem | +2.353 |
cult | +2.245 |
Neg logit contributions | |
�� | -3.463 |
izoph | -3.346 |
="# | -3.067 |
arte | -2.955 |
ム | -2.935 |
Token | Lap |
Token ID | 26944 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
ocument | +1.916 |
"]," | +1.791 |
outp | +1.717 |
Extrem | +1.662 |
Exhibit | +1.578 |
Neg logit contributions | |
�� | -2.263 |
izoph | -2.201 |
="# | -2.036 |
arte | -1.950 |
ム | -1.938 |
Token | eral |
Token ID | 1691 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
ocument | +3.760 |
"]," | +3.373 |
outp | +2.784 |
cial | +2.761 |
atal | +2.732 |
Neg logit contributions | |
�� | -12.193 |
izoph | -11.769 |
="# | -10.765 |
ム | -10.689 |
ENN | -10.608 |
Token | also |
Token ID | 635 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
ocument | +2.776 |
"]," | +2.593 |
outp | +2.534 |
Extrem | +2.412 |
cult | +2.331 |
Neg logit contributions | |
�� | -2.709 |
izoph | -2.649 |
="# | -2.381 |
arte | -2.281 |
ム | -2.269 |
Token | reached |
Token ID | 4251 |
Feature activation | +9.28e-03 |
Pos logit contributions | |
�� | +0.560 |
izoph | +0.544 |
="# | +0.506 |
arte | +0.491 |
ム | +0.477 |
Neg logit contributions | |
ocument | -0.635 |
"]," | -0.587 |
outp | -0.556 |
Extrem | -0.552 |
cult | -0.526 |
Token | some |
Token ID | 617 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
�� | +0.099 |
izoph | +0.098 |
="# | +0.090 |
arte | +0.088 |
ム | +0.087 |
Neg logit contributions | |
ocument | -0.072 |
"]," | -0.066 |
outp | -0.063 |
Extrem | -0.060 |
cult | -0.058 |
Token | unsettling |
Token ID | 38192 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
izoph | +5.202 |
�� | +5.128 |
="# | +4.771 |
aster | +4.556 |
arte | +4.522 |
Neg logit contributions | |
ocument | -5.701 |
"]," | -5.253 |
outp | -4.759 |
cult | -4.615 |
Extrem | -4.592 |
Token | study |
Token ID | 2050 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ocument | +2.128 |
"]," | +1.979 |
outp | +1.919 |
Extrem | +1.838 |
cult | +1.752 |
Neg logit contributions | |
�� | -2.401 |
izoph | -2.342 |
="# | -2.145 |
arte | -2.077 |
ム | -2.053 |
Token | found |
Token ID | 1043 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
ocument | +2.235 |
"]," | +2.071 |
outp | +1.998 |
Extrem | +1.914 |
cult | +1.837 |
Neg logit contributions | |
�� | -2.523 |
izoph | -2.467 |
="# | -2.259 |
arte | -2.184 |
ム | -2.159 |
Token | that |
Token ID | 326 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ocument | +3.661 |
"]," | +3.493 |
outp | +3.386 |
Extrem | +3.229 |
Exhibit | +3.100 |
Neg logit contributions | |
�� | -4.396 |
izoph | -4.254 |
="# | -3.910 |
arte | -3.832 |
ム | -3.743 |
Token | Y |
Token ID | 575 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ocument | +2.509 |
"]," | +2.356 |
outp | +2.273 |
Extrem | +2.184 |
cult | +2.088 |
Neg logit contributions | |
�� | -2.759 |
izoph | -2.687 |
="# | -2.464 |
arte | -2.386 |
ム | -2.354 |
Token | Ba |
Token ID | 34458 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ocument | +2.030 |
"]," | +1.890 |
outp | +1.826 |
Extrem | +1.754 |
cult | +1.692 |
Neg logit contributions | |
�� | -2.064 |
izoph | -2.011 |
="# | -1.831 |
arte | -1.762 |
ム | -1.742 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
ocument | +4.405 |
"]," | +4.069 |
outp | +4.020 |
Extrem | +3.800 |
cult | +3.604 |
Neg logit contributions | |
�� | -5.686 |
izoph | -5.604 |
="# | -4.970 |
arte | -4.939 |
wagen | -4.816 |
Token | Cu |
Token ID | 46141 |
Feature activation | -4.87e-03 |
Pos logit contributions | |
ocument | +2.017 |
"]," | +1.675 |
outp | +1.442 |
Extrem | +1.208 |
cult | +0.945 |
Neg logit contributions | |
�� | -14.204 |
izoph | -13.823 |
="# | -12.571 |
wagen | -12.462 |
arte | -12.441 |
Token | 3 |
Token ID | 18 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
ocument | +0.048 |
"]," | +0.044 |
outp | +0.043 |
Extrem | +0.041 |
cult | +0.040 |
Neg logit contributions | |
�� | -0.042 |
izoph | -0.041 |
="# | -0.038 |
arte | -0.037 |
ム | -0.036 |
Token | O |
Token ID | 46 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ocument | +4.110 |
"]," | +3.897 |
outp | +3.706 |
Extrem | +3.482 |
cult | +3.233 |
Neg logit contributions | |
�� | -7.759 |
izoph | -7.534 |
="# | -6.727 |
wagen | -6.698 |
arte | -6.588 |
Token | 6 |
Token ID | 21 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
�� | +0.950 |
izoph | +0.939 |
="# | +0.872 |
arte | +0.827 |
ム | +0.815 |
Neg logit contributions | |
ocument | -1.460 |
"]," | -1.349 |
outp | -1.321 |
Extrem | -1.285 |
Exhibit | -1.232 |
Token | + |
Token ID | 10 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ocument | +2.016 |
"]," | +1.788 |
outp | +1.732 |
Extrem | +1.580 |
cult | +1.463 |
Neg logit contributions | |
�� | -4.771 |
izoph | -4.703 |
="# | -4.356 |
arte | -4.274 |
wagen | -4.215 |
Token | 24 |
Token ID | 1731 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
ocument | +1.242 |
"]," | +1.150 |
outp | +1.119 |
Extrem | +1.078 |
cult | +1.037 |
Neg logit contributions | |
�� | -1.124 |
izoph | -1.097 |
="# | -1.006 |
arte | -0.964 |
ム | -0.952 |
Token | # |
Token ID | 1303 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ocument | +2.760 |
"]," | +2.575 |
outp | +2.420 |
Extrem | +2.336 |
Exhibit | +2.214 |
Neg logit contributions | |
�� | -4.746 |
izoph | -4.636 |
="# | -4.195 |
arte | -4.110 |
wagen | -4.066 |
Token | 19 |
Token ID | 1129 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
ocument | +1.189 |
"]," | +1.113 |
outp | +1.080 |
Extrem | +1.043 |
cult | +1.008 |
Neg logit contributions | |
�� | -0.958 |
izoph | -0.932 |
="# | -0.842 |
arte | -0.807 |
ム | -0.795 |
Token | edit |
Token ID | 4370 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
ocument | +0.227 |
"]," | +0.210 |
outp | +0.201 |
Extrem | +0.193 |
cult | +0.187 |
Neg logit contributions | |
�� | -0.238 |
izoph | -0.233 |
="# | -0.213 |
arte | -0.205 |
ム | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ocument | +3.615 |
"]," | +3.354 |
outp | +3.254 |
Extrem | +3.036 |
cult | +2.941 |
Neg logit contributions | |
�� | -4.867 |
izoph | -4.728 |
="# | -4.273 |
arte | -4.203 |
ム | -4.195 |
Token | n |
Token ID | 299 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
�� | +0.204 |
izoph | +0.200 |
="# | +0.183 |
arte | +0.177 |
ム | +0.174 |
Neg logit contributions | |
ocument | -0.188 |
"]," | -0.174 |
outp | -0.166 |
Extrem | -0.160 |
cult | -0.154 |
Token | vm |
Token ID | 14761 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
ocument | +10.761 |
"]," | +9.962 |
outp | +9.472 |
atal | +9.364 |
cial | +9.138 |
Neg logit contributions | |
�� | -9.776 |
izoph | -9.597 |
ム | -8.193 |
="# | -8.160 |
arte | -7.855 |
Token |
|
Token ID | 198 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ocument | +6.693 |
outp | +6.115 |
"]," | +6.111 |
Extrem | +5.638 |
cial | +5.537 |
Neg logit contributions | |
�� | -8.305 |
izoph | -7.903 |
="# | -7.233 |
arte | -7.100 |
ム | -7.092 |
Token |
|
Token ID | 198 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
ocument | +3.232 |
"]," | +3.104 |
outp | +2.939 |
Extrem | +2.819 |
cult | +2.726 |
Neg logit contributions | |
�� | -3.855 |
izoph | -3.731 |
="# | -3.299 |
arte | -3.229 |
ム | -3.202 |
Token | K |
Token ID | 42 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ocument | +0.937 |
"]," | +0.874 |
outp | +0.844 |
Extrem | +0.812 |
cult | +0.787 |
Neg logit contributions | |
�� | -0.883 |
izoph | -0.861 |
="# | -0.781 |
arte | -0.753 |
ム | -0.743 |
Token | ada |
Token ID | 4763 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
izoph | +5.418 |
�� | +5.336 |
arte | +4.984 |
="# | +4.908 |
ENN | +4.891 |
Neg logit contributions | |
ocument | -5.008 |
"]," | -4.611 |
outp | -4.439 |
Extrem | -4.337 |
Exhibit | -4.084 |
Token | ( |
Token ID | 357 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
ocument | +0.697 |
"]," | +0.645 |
outp | +0.617 |
Extrem | +0.596 |
cult | +0.570 |
Neg logit contributions | |
�� | -0.814 |
izoph | -0.800 |
="# | -0.730 |
arte | -0.706 |
ム | -0.695 |
Token | and |
Token ID | 392 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
ocument | +0.622 |
"]," | +0.580 |
outp | +0.562 |
Extrem | +0.542 |
cult | +0.521 |
Neg logit contributions | |
�� | -0.557 |
izoph | -0.542 |
="# | -0.493 |
arte | -0.475 |
ム | -0.468 |
Token | counting |
Token ID | 14143 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ocument | +0.345 |
"]," | +0.320 |
outp | +0.307 |
Extrem | +0.295 |
cult | +0.285 |
Neg logit contributions | |
�� | -0.369 |
izoph | -0.360 |
="# | -0.331 |
arte | -0.319 |
ム | -0.315 |
Token | )[ |
Token ID | 38381 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ocument | +2.198 |
"]," | +2.024 |
outp | +1.942 |
Extrem | +1.858 |
Exhibit | +1.774 |
Neg logit contributions | |
�� | -2.878 |
izoph | -2.808 |
="# | -2.574 |
arte | -2.502 |
ム | -2.455 |
Token | h |
Token ID | 71 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
�� | +1.193 |
izoph | +1.157 |
="# | +1.076 |
arte | +1.028 |
ム | +1.022 |
Neg logit contributions | |
ocument | -1.238 |
"]," | -1.144 |
outp | -1.116 |
Extrem | -1.074 |
cult | -1.028 |
Token | int |
Token ID | 600 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
izoph | +3.890 |
�� | +3.841 |
="# | +3.533 |
arte | +3.389 |
ENN | +3.309 |
Neg logit contributions | |
ocument | -4.587 |
"]," | -4.255 |
outp | -4.240 |
Extrem | -4.090 |
Exhibit | -3.908 |
Token | : |
Token ID | 25 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ocument | +6.943 |
"]," | +6.323 |
outp | +6.021 |
Extrem | +5.787 |
Exhibit | +5.781 |
Neg logit contributions | |
�� | -10.103 |
izoph | -10.055 |
artney | -8.882 |
wagen | -8.844 |
arte | -8.790 |
Token | for |
Token ID | 329 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ocument | +2.439 |
"]," | +2.258 |
outp | +2.187 |
Extrem | +2.111 |
cult | +2.024 |
Neg logit contributions | |
�� | -2.543 |
izoph | -2.481 |
="# | -2.254 |
arte | -2.182 |
ム | -2.148 |
Token | ease |
Token ID | 10152 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
�� | +1.644 |
izoph | +1.609 |
="# | +1.484 |
arte | +1.428 |
ム | +1.413 |
Neg logit contributions | |
ocument | -1.575 |
"]," | -1.461 |
outp | -1.398 |
Extrem | -1.344 |
cult | -1.299 |
Token | of |
Token ID | 286 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
�� | +0.995 |
izoph | +0.969 |
="# | +0.893 |
arte | +0.859 |
ム | +0.851 |
Neg logit contributions | |
ocument | -0.898 |
"]," | -0.828 |
outp | -0.801 |
Extrem | -0.773 |
cult | -0.738 |
Token | navigation |
Token ID | 16408 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
ocument | +2.600 |
"]," | +2.426 |
outp | +2.329 |
Extrem | +2.229 |
cult | +2.133 |
Neg logit contributions | |
�� | -3.116 |
izoph | -3.030 |
="# | -2.780 |
arte | -2.687 |
ム | -2.671 |
Token | 4 |
Token ID | 604 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
ocument | +0.526 |
"]," | +0.485 |
outp | +0.467 |
Extrem | +0.448 |
cult | +0.431 |
Neg logit contributions | |
�� | -0.594 |
izoph | -0.582 |
="# | -0.534 |
arte | -0.517 |
ム | -0.509 |
Token | T |
Token ID | 309 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
ocument | +3.702 |
"]," | +3.464 |
outp | +3.338 |
Extrem | +3.176 |
cial | +3.094 |
Neg logit contributions | |
�� | -4.822 |
izoph | -4.722 |
="# | -4.311 |
ム | -4.149 |
arte | -4.141 |
Token | 15 |
Token ID | 1314 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
�� | +0.605 |
izoph | +0.588 |
="# | +0.530 |
arte | +0.510 |
ム | +0.500 |
Neg logit contributions | |
ocument | -0.786 |
"]," | -0.737 |
outp | -0.713 |
Extrem | -0.690 |
cult | -0.669 |
Token | screws |
Token ID | 23742 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
ocument | +0.018 |
"]," | +0.017 |
outp | +0.016 |
Extrem | +0.015 |
cult | +0.015 |
Neg logit contributions | |
�� | -0.025 |
izoph | -0.024 |
="# | -0.022 |
arte | -0.022 |
ム | -0.021 |
Token | Now |
Token ID | 3844 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
ocument | +0.311 |
"]," | +0.288 |
outp | +0.277 |
Extrem | +0.266 |
cult | +0.256 |
Neg logit contributions | |
�� | -0.332 |
izoph | -0.324 |
="# | -0.299 |
arte | -0.288 |
ム | -0.284 |
Token | head |
Token ID | 1182 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
ocument | +3.040 |
"]," | +2.797 |
outp | +2.705 |
Extrem | +2.549 |
cial | +2.471 |
Neg logit contributions | |
�� | -4.043 |
izoph | -3.917 |
="# | -3.619 |
ム | -3.488 |
arte | -3.487 |
Token | over |
Token ID | 625 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ocument | +6.198 |
outp | +5.664 |
"]," | +5.611 |
Extrem | +5.238 |
cult | +5.223 |
Neg logit contributions | |
�� | -9.408 |
izoph | -9.153 |
="# | -8.325 |
ム | -7.997 |
arte | -7.918 |
Token | to |
Token ID | 284 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
ocument | +1.495 |
"]," | +1.385 |
outp | +1.338 |
Extrem | +1.286 |
cult | +1.238 |
Neg logit contributions | |
�� | -1.654 |
izoph | -1.619 |
="# | -1.472 |
arte | -1.422 |
ム | -1.396 |
Token | the |
Token ID | 262 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
ocument | +5.766 |
"]," | +5.350 |
outp | +5.204 |
Extrem | +5.050 |
Exhibit | +4.940 |
Neg logit contributions | |
�� | -7.243 |
izoph | -7.062 |
="# | -6.389 |
arte | -6.157 |
ム | -6.156 |
Token | passenger |
Token ID | 11849 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ocument | +5.516 |
"]," | +5.199 |
outp | +5.110 |
Extrem | +4.899 |
Exhibit | +4.737 |
Neg logit contributions | |
�� | -7.068 |
izoph | -6.882 |
="# | -6.324 |
arte | -6.072 |
ム | -5.998 |
Token | side |
Token ID | 1735 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
ocument | +2.763 |
"]," | +2.580 |
outp | +2.502 |
Extrem | +2.393 |
cult | +2.309 |
Neg logit contributions | |
�� | -2.907 |
izoph | -2.825 |
="# | -2.588 |
arte | -2.499 |
ム | -2.446 |