Token | mot |
Token ID | 27926 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
berry | +0.913 |
ythm | +0.772 |
ilateral | +0.768 |
worm | +0.764 |
enne | +0.761 |
Neg logit contributions | |
destro | -1.100 |
newsp | -1.040 |
Dumb | -1.040 |
disadvant | -1.029 |
unda | -1.028 |
Token | ivated |
Token ID | 30829 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
destro | +0.826 |
Dumb | +0.774 |
unda | +0.766 |
disadvant | +0.760 |
lift | +0.755 |
Neg logit contributions | |
berry | -1.446 |
ythm | -1.290 |
worm | -1.275 |
enne | -1.270 |
ilateral | -1.267 |
Token | arrests |
Token ID | 14794 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
berry | +1.245 |
ythm | +1.091 |
enne | +1.080 |
worm | +1.079 |
ilateral | +1.074 |
Neg logit contributions | |
destro | -0.831 |
unda | -0.776 |
Dumb | -0.771 |
lift | -0.765 |
newsp | -0.762 |
Token | . |
Token ID | 13 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
destro | +1.940 |
Dumb | +1.843 |
unda | +1.824 |
disadvant | +1.823 |
lift | +1.818 |
Neg logit contributions | |
berry | -2.090 |
ythm | -1.815 |
enne | -1.786 |
worm | -1.785 |
ilateral | -1.780 |
Token | Every |
Token ID | 3887 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
berry | +0.961 |
ythm | +0.826 |
worm | +0.809 |
enne | +0.808 |
ilateral | +0.803 |
Neg logit contributions | |
destro | -0.888 |
disadvant | -0.817 |
newsp | -0.813 |
unda | -0.813 |
lift | -0.798 |
Token | Friday |
Token ID | 3217 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
destro | +0.597 |
Dumb | +0.557 |
unda | +0.554 |
disadvant | +0.551 |
lift | +0.549 |
Neg logit contributions | |
berry | -0.860 |
ythm | -0.756 |
worm | -0.747 |
ilateral | -0.745 |
enne | -0.745 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
destro | +5.116 |
Dumb | +5.020 |
lift | +4.999 |
newsp | +4.944 |
disadvant | +4.940 |
Neg logit contributions | |
berry | -6.833 |
ythm | -6.305 |
autical | -6.096 |
enne | -6.079 |
ilateral | -6.049 |
Token | we |
Token ID | 356 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
destro | +0.237 |
unda | +0.222 |
Dumb | +0.221 |
disadvant | +0.221 |
lift | +0.220 |
Neg logit contributions | |
berry | -0.284 |
ythm | -0.246 |
worm | -0.244 |
enne | -0.243 |
ilateral | -0.243 |
Token | bring |
Token ID | 2222 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
berry | +0.623 |
ythm | +0.539 |
worm | +0.537 |
enne | +0.536 |
ilateral | +0.535 |
Neg logit contributions | |
destro | -0.497 |
Dumb | -0.468 |
disadvant | -0.465 |
unda | -0.464 |
lift | -0.461 |
Token | you |
Token ID | 345 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
destro | +0.113 |
disadvant | +0.107 |
Dumb | +0.106 |
unda | +0.106 |
lift | +0.106 |
Neg logit contributions | |
berry | -0.092 |
ythm | -0.077 |
worm | -0.076 |
ilateral | -0.076 |
enne | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
berry | +0.857 |
ythm | +0.735 |
worm | +0.725 |
ilateral | +0.725 |
enne | +0.721 |
Neg logit contributions | |
destro | -0.781 |
disadvant | -0.728 |
unda | -0.719 |
Dumb | -0.716 |
newsp | -0.713 |
Token | her |
Token ID | 607 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
berry | +0.804 |
ythm | +0.717 |
enne | +0.712 |
worm | +0.712 |
ilateral | +0.710 |
Neg logit contributions | |
destro | -0.374 |
Dumb | -0.340 |
unda | -0.336 |
disadvant | -0.335 |
newsp | -0.333 |
Token | skirt |
Token ID | 23967 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
berry | +1.049 |
ythm | +0.896 |
worm | +0.892 |
enne | +0.888 |
ilateral | +0.884 |
Neg logit contributions | |
destro | -0.905 |
unda | -0.847 |
Dumb | -0.842 |
lift | -0.841 |
disadvant | -0.841 |
Token | . |
Token ID | 13 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
destro | +0.281 |
Dumb | +0.266 |
unda | +0.264 |
disadvant | +0.263 |
lift | +0.262 |
Neg logit contributions | |
berry | -0.293 |
ythm | -0.253 |
worm | -0.249 |
enne | -0.248 |
ilateral | -0.248 |
Token |
|
Token ID | 198 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
berry | +0.074 |
ythm | +0.065 |
enne | +0.064 |
worm | +0.064 |
ilateral | +0.063 |
Neg logit contributions | |
destro | -0.068 |
disadvant | -0.063 |
Dumb | -0.063 |
unda | -0.063 |
newsp | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
destro | +0.700 |
Dumb | +0.696 |
lift | +0.690 |
unda | +0.687 |
practise | +0.673 |
Neg logit contributions | |
berry | -0.802 |
ythm | -0.701 |
ilateral | -0.692 |
enne | -0.690 |
worm | -0.689 |
Token | Ste |
Token ID | 7447 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
berry | +0.045 |
ythm | +0.039 |
worm | +0.038 |
enne | +0.038 |
ilateral | +0.038 |
Neg logit contributions | |
destro | -0.039 |
Dumb | -0.037 |
unda | -0.037 |
disadvant | -0.036 |
lift | -0.036 |
Token | lla |
Token ID | 8466 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
unda | +5.662 |
lift | +5.578 |
Dumb | +5.311 |
practise | +5.309 |
obscurity | +5.190 |
Neg logit contributions | |
berry | -5.171 |
ythm | -4.554 |
ilateral | -4.480 |
worm | -4.445 |
autical | -4.427 |
Token | understood |
Token ID | 7247 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
destro | +2.428 |
Dumb | +2.317 |
lift | +2.294 |
unda | +2.278 |
practise | +2.269 |
Neg logit contributions | |
berry | -2.975 |
ythm | -2.641 |
ilateral | -2.592 |
autical | -2.585 |
enne | -2.577 |
Token | . |
Token ID | 13 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
destro | +1.676 |
Dumb | +1.587 |
unda | +1.570 |
disadvant | +1.566 |
lift | +1.564 |
Neg logit contributions | |
berry | -2.102 |
ythm | -1.844 |
worm | -1.814 |
enne | -1.813 |
ilateral | -1.809 |
Token | This |
Token ID | 770 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
destro | +1.144 |
Dumb | +1.088 |
unda | +1.072 |
lift | +1.069 |
disadvant | +1.064 |
Neg logit contributions | |
berry | -1.589 |
ythm | -1.400 |
worm | -1.381 |
enne | -1.379 |
ilateral | -1.379 |
Token | wasn |
Token ID | 2492 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
destro | +0.819 |
Dumb | +0.766 |
unda | +0.762 |
disadvant | +0.757 |
lift | +0.755 |
Neg logit contributions | |
berry | -1.142 |
ythm | -1.005 |
enne | -0.992 |
worm | -0.992 |
ilateral | -0.987 |
Token | deployed |
Token ID | 12380 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
berry | +0.807 |
ythm | +0.699 |
worm | +0.692 |
ilateral | +0.688 |
enne | +0.687 |
Neg logit contributions | |
destro | -0.684 |
Dumb | -0.650 |
unda | -0.644 |
disadvant | -0.643 |
lift | -0.641 |
Token | with |
Token ID | 351 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
destro | +0.956 |
Dumb | +0.904 |
unda | +0.897 |
disadvant | +0.895 |
lift | +0.891 |
Neg logit contributions | |
berry | -1.044 |
ythm | -0.903 |
worm | -0.891 |
enne | -0.889 |
ilateral | -0.887 |
Token | maximum |
Token ID | 5415 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
destro | +0.054 |
Dumb | +0.050 |
unda | +0.050 |
disadvant | +0.050 |
lift | +0.049 |
Neg logit contributions | |
berry | -0.074 |
ythm | -0.065 |
worm | -0.064 |
ilateral | -0.064 |
enne | -0.064 |
Token | deployment |
Token ID | 14833 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
destro | +0.987 |
Dumb | +0.925 |
unda | +0.917 |
disadvant | +0.913 |
lift | +0.911 |
Neg logit contributions | |
berry | -1.431 |
ythm | -1.265 |
worm | -1.247 |
enne | -1.246 |
ilateral | -1.243 |
Token | in |
Token ID | 287 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
destro | +0.265 |
Dumb | +0.251 |
unda | +0.248 |
disadvant | +0.248 |
lift | +0.247 |
Neg logit contributions | |
berry | -0.303 |
ythm | -0.263 |
worm | -0.260 |
enne | -0.259 |
ilateral | -0.259 |
Token | Roh |
Token ID | 32694 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
berry | +0.169 |
ythm | +0.147 |
worm | +0.146 |
ilateral | +0.145 |
enne | +0.145 |
Neg logit contributions | |
destro | -0.136 |
unda | -0.127 |
Dumb | -0.127 |
disadvant | -0.127 |
newsp | -0.126 |
Token | t |
Token ID | 83 |
Feature activation | -7.69e-03 |
Pos logit contributions | |
unda | +5.586 |
lift | +5.517 |
Dumb | +5.432 |
practise | +5.234 |
obscurity | +5.124 |
Neg logit contributions | |
berry | -5.191 |
ythm | -4.498 |
autical | -4.490 |
ilateral | -4.455 |
enne | -4.408 |
Token | ak |
Token ID | 461 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
berry | +0.018 |
ythm | +0.015 |
ilateral | +0.015 |
enne | +0.015 |
worm | +0.015 |
Neg logit contributions | |
destro | -0.021 |
disadvant | -0.020 |
Dumb | -0.019 |
newsp | -0.019 |
unda | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
destro | +0.380 |
Dumb | +0.357 |
unda | +0.355 |
disadvant | +0.355 |
lift | +0.353 |
Neg logit contributions | |
berry | -0.442 |
ythm | -0.384 |
worm | -0.379 |
enne | -0.378 |
ilateral | -0.376 |
Token | Additional |
Token ID | 15891 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
berry | +0.583 |
ythm | +0.509 |
worm | +0.502 |
ilateral | +0.499 |
enne | +0.498 |
Neg logit contributions | |
destro | -0.466 |
disadvant | -0.434 |
unda | -0.430 |
newsp | -0.427 |
Dumb | -0.426 |
Token | columns |
Token ID | 15180 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
destro | +1.220 |
Dumb | +1.142 |
unda | +1.131 |
disadvant | +1.127 |
lift | +1.123 |
Neg logit contributions | |
berry | -1.843 |
ythm | -1.631 |
worm | -1.609 |
enne | -1.608 |
ilateral | -1.604 |
Token | Ah |
Token ID | 10910 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
destro | +0.020 |
Dumb | +0.019 |
unda | +0.019 |
disadvant | +0.019 |
lift | +0.019 |
Neg logit contributions | |
berry | -0.023 |
ythm | -0.020 |
worm | -0.020 |
enne | -0.020 |
ilateral | -0.020 |
Token | ." |
Token ID | 526 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
berry | +0.173 |
ythm | +0.149 |
worm | +0.147 |
enne | +0.147 |
ilateral | +0.146 |
Neg logit contributions | |
destro | -0.178 |
Dumb | -0.169 |
unda | -0.168 |
disadvant | -0.167 |
lift | -0.167 |
Token |
|
Token ID | 198 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
berry | +1.018 |
ythm | +0.876 |
worm | +0.859 |
enne | +0.857 |
ilateral | +0.854 |
Neg logit contributions | |
destro | -1.063 |
disadvant | -0.997 |
Dumb | -0.995 |
newsp | -0.993 |
unda | -0.990 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
berry | +0.015 |
ythm | +0.013 |
worm | +0.013 |
enne | +0.013 |
ilateral | +0.013 |
Neg logit contributions | |
destro | -0.014 |
Dumb | -0.014 |
unda | -0.014 |
lift | -0.013 |
disadvant | -0.013 |
Token | " |
Token ID | 1 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
berry | +0.609 |
ythm | +0.530 |
worm | +0.524 |
enne | +0.523 |
ilateral | +0.519 |
Neg logit contributions | |
destro | -0.516 |
Dumb | -0.479 |
disadvant | -0.477 |
newsp | -0.474 |
unda | -0.474 |
Token | Ste |
Token ID | 7447 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
destro | +0.603 |
Dumb | +0.581 |
lift | +0.575 |
unda | +0.575 |
disadvant | +0.568 |
Neg logit contributions | |
berry | -0.718 |
ythm | -0.627 |
ilateral | -0.619 |
worm | -0.617 |
enne | -0.616 |
Token | lla |
Token ID | 8466 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
unda | +5.468 |
lift | +5.391 |
Dumb | +5.205 |
practise | +5.157 |
obscurity | +5.046 |
Neg logit contributions | |
berry | -4.883 |
ilateral | -4.275 |
ythm | -4.263 |
autical | -4.192 |
worm | -4.188 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
destro | +2.429 |
Dumb | +2.327 |
unda | +2.316 |
lift | +2.290 |
disadvant | +2.279 |
Neg logit contributions | |
berry | -2.500 |
ythm | -2.179 |
ilateral | -2.158 |
worm | -2.147 |
autical | -2.142 |
Token |
|
Token ID | 198 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
berry | +1.210 |
ythm | +1.046 |
worm | +1.024 |
enne | +1.021 |
ilateral | +1.018 |
Neg logit contributions | |
destro | -1.244 |
Dumb | -1.172 |
disadvant | -1.171 |
newsp | -1.166 |
unda | -1.162 |
Token |
|
Token ID | 198 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
berry | +0.150 |
ythm | +0.130 |
worm | +0.128 |
enne | +0.127 |
ilateral | +0.127 |
Neg logit contributions | |
destro | -0.147 |
Dumb | -0.139 |
unda | -0.138 |
disadvant | -0.138 |
lift | -0.137 |
Token | When |
Token ID | 2215 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
berry | +0.688 |
ythm | +0.600 |
worm | +0.591 |
enne | +0.590 |
ilateral | +0.586 |
Neg logit contributions | |
destro | -0.587 |
Dumb | -0.547 |
disadvant | -0.544 |
unda | -0.541 |
newsp | -0.540 |
Token | the |
Token ID | 262 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
destro | +1.438 |
Dumb | +1.372 |
lift | +1.350 |
disadvant | +1.348 |
newsp | +1.347 |
Neg logit contributions | |
berry | -1.586 |
ythm | -1.382 |
enne | -1.366 |
worm | -1.348 |
autical | -1.348 |
Token | mobile |
Token ID | 5175 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
destro | +0.915 |
Dumb | +0.866 |
unda | +0.855 |
disadvant | +0.854 |
lift | +0.852 |
Neg logit contributions | |
berry | -1.093 |
ythm | -0.957 |
enne | -0.943 |
worm | -0.940 |
ilateral | -0.936 |
Token | consumer |
Token ID | 7172 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
destro | +1.832 |
Dumb | +1.738 |
disadvant | +1.724 |
unda | +1.719 |
newsp | +1.716 |
Neg logit contributions | |
berry | -1.863 |
ythm | -1.620 |
enne | -1.591 |
worm | -1.588 |
ilateral | -1.587 |
Token | that |
Token ID | 326 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
destro | +0.567 |
Dumb | +0.537 |
unda | +0.531 |
disadvant | +0.531 |
lift | +0.530 |
Neg logit contributions | |
berry | -0.635 |
ythm | -0.552 |
enne | -0.543 |
worm | -0.542 |
ilateral | -0.541 |
Token | his |
Token ID | 465 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
destro | +1.677 |
Dumb | +1.597 |
disadvant | +1.579 |
lift | +1.576 |
unda | +1.574 |
Neg logit contributions | |
berry | -1.887 |
ythm | -1.655 |
enne | -1.629 |
worm | -1.612 |
autical | -1.611 |
Token | or |
Token ID | 393 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
destro | +2.148 |
Dumb | +2.054 |
unda | +2.025 |
lift | +2.023 |
disadvant | +2.022 |
Neg logit contributions | |
berry | -2.217 |
ythm | -1.935 |
enne | -1.902 |
worm | -1.889 |
ilateral | -1.884 |
Token | her |
Token ID | 607 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
lift | +2.649 |
practise | +2.628 |
Dumb | +2.531 |
unda | +2.510 |
destro | +2.421 |
Neg logit contributions | |
berry | -7.866 |
enne | -7.197 |
ythm | -7.169 |
ilateral | -7.147 |
autical | -7.115 |
Token | registration |
Token ID | 9352 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
destro | +0.228 |
Dumb | +0.213 |
unda | +0.212 |
disadvant | +0.211 |
lift | +0.210 |
Neg logit contributions | |
berry | -0.334 |
ythm | -0.294 |
worm | -0.291 |
ilateral | -0.290 |
enne | -0.290 |
Token | will |
Token ID | 481 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
destro | +0.860 |
Dumb | +0.807 |
unda | +0.800 |
disadvant | +0.796 |
lift | +0.794 |
Neg logit contributions | |
berry | -1.264 |
ythm | -1.118 |
worm | -1.103 |
enne | -1.102 |
ilateral | -1.099 |
Token | expire |
Token ID | 24264 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
destro | +0.830 |
Dumb | +0.776 |
unda | +0.773 |
lift | +0.772 |
practise | +0.764 |
Neg logit contributions | |
berry | -1.193 |
ythm | -1.065 |
enne | -1.053 |
worm | -1.043 |
ilateral | -1.040 |
Token | , |
Token ID | 11 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
destro | +1.637 |
Dumb | +1.556 |
disadvant | +1.539 |
unda | +1.539 |
lift | +1.532 |
Neg logit contributions | |
berry | -1.948 |
ythm | -1.705 |
enne | -1.678 |
worm | -1.674 |
ilateral | -1.670 |
Token | " |
Token ID | 1 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
berry | +0.455 |
ythm | +0.386 |
worm | +0.380 |
enne | +0.378 |
ilateral | +0.377 |
Neg logit contributions | |
destro | -0.532 |
Dumb | -0.506 |
unda | -0.504 |
disadvant | -0.501 |
lift | -0.500 |
Token | in |
Token ID | 287 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
destro | +1.332 |
Dumb | +1.265 |
disadvant | +1.250 |
unda | +1.247 |
lift | +1.246 |
Neg logit contributions | |
berry | -1.455 |
ythm | -1.267 |
enne | -1.243 |
worm | -1.242 |
ilateral | -1.241 |
Token | Houston |
Token ID | 6995 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
destro | +0.751 |
Dumb | +0.710 |
unda | +0.707 |
disadvant | +0.705 |
lift | +0.702 |
Neg logit contributions | |
berry | -0.758 |
ythm | -0.652 |
worm | -0.643 |
enne | -0.642 |
ilateral | -0.640 |
Token | . |
Token ID | 13 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
destro | +1.422 |
Dumb | +1.349 |
unda | +1.334 |
disadvant | +1.332 |
lift | +1.331 |
Neg logit contributions | |
berry | -1.532 |
ythm | -1.331 |
worm | -1.310 |
ilateral | -1.307 |
enne | -1.307 |
Token | The |
Token ID | 383 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
destro | +0.069 |
unda | +0.064 |
Dumb | +0.064 |
disadvant | +0.064 |
newsp | +0.064 |
Neg logit contributions | |
berry | -0.083 |
ythm | -0.072 |
worm | -0.071 |
enne | -0.071 |
ilateral | -0.071 |
Token | compiled |
Token ID | 14102 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
destro | +0.633 |
unda | +0.593 |
Dumb | +0.590 |
disadvant | +0.589 |
lift | +0.584 |
Neg logit contributions | |
berry | -0.853 |
ythm | -0.746 |
worm | -0.740 |
enne | -0.738 |
ilateral | -0.734 |
Token | addresses |
Token ID | 9405 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
destro | +3.536 |
Dumb | +3.397 |
newsp | +3.349 |
disparate | +3.307 |
lift | +3.249 |
Neg logit contributions | |
berry | -7.164 |
ythm | -6.551 |
ilateral | -6.410 |
autical | -6.399 |
yth | -6.379 |
Token | had |
Token ID | 550 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
berry | +0.239 |
ythm | +0.207 |
worm | +0.205 |
enne | +0.205 |
ilateral | +0.203 |
Neg logit contributions | |
destro | -0.206 |
Dumb | -0.195 |
unda | -0.194 |
disadvant | -0.193 |
lift | -0.192 |
Token | such |
Token ID | 884 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
destro | +0.792 |
Dumb | +0.746 |
unda | +0.741 |
disadvant | +0.738 |
lift | +0.736 |
Neg logit contributions | |
berry | -0.961 |
ythm | -0.838 |
worm | -0.827 |
enne | -0.825 |
ilateral | -0.823 |
Token | a |
Token ID | 257 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
berry | +2.243 |
ythm | +1.959 |
worm | +1.950 |
ilateral | +1.938 |
enne | +1.927 |
Neg logit contributions | |
destro | -1.537 |
unda | -1.447 |
Dumb | -1.413 |
lift | -1.409 |
disadvant | -1.406 |
Token | long |
Token ID | 890 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
berry | +1.971 |
worm | +1.726 |
hod | +1.725 |
enne | +1.724 |
ythm | +1.717 |
Neg logit contributions | |
destro | -1.223 |
unda | -1.152 |
Dumb | -1.120 |
lift | -1.116 |
disadvant | -1.110 |
Token | "… |
Token ID | 24426 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
destro | +0.389 |
Dumb | +0.369 |
unda | +0.366 |
lift | +0.365 |
disadvant | +0.364 |
Neg logit contributions | |
berry | -0.426 |
ythm | -0.370 |
worm | -0.364 |
enne | -0.363 |
ilateral | -0.363 |
Token | Alright |
Token ID | 31442 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
berry | +0.413 |
ythm | +0.360 |
worm | +0.355 |
enne | +0.355 |
ilateral | +0.353 |
Neg logit contributions | |
destro | -0.345 |
Dumb | -0.323 |
unda | -0.321 |
disadvant | -0.321 |
newsp | -0.319 |
Token | ." |
Token ID | 526 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
destro | +0.664 |
Dumb | +0.635 |
unda | +0.632 |
lift | +0.627 |
disadvant | +0.625 |
Neg logit contributions | |
berry | -0.661 |
ythm | -0.571 |
worm | -0.563 |
ilateral | -0.562 |
autical | -0.557 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
berry | +0.339 |
ythm | +0.292 |
worm | +0.287 |
enne | +0.286 |
ilateral | +0.285 |
Neg logit contributions | |
destro | -0.342 |
disadvant | -0.320 |
Dumb | -0.320 |
unda | -0.318 |
newsp | -0.318 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
destro | +0.462 |
Dumb | +0.451 |
lift | +0.447 |
unda | +0.446 |
practise | +0.438 |
Neg logit contributions | |
berry | -0.509 |
ythm | -0.443 |
ilateral | -0.436 |
enne | -0.436 |
worm | -0.435 |
Token | Ste |
Token ID | 7447 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
berry | +0.294 |
ythm | +0.256 |
worm | +0.253 |
enne | +0.253 |
ilateral | +0.251 |
Neg logit contributions | |
destro | -0.248 |
Dumb | -0.232 |
disadvant | -0.230 |
unda | -0.230 |
newsp | -0.229 |
Token | lla |
Token ID | 8466 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
unda | +5.404 |
lift | +5.330 |
Dumb | +5.087 |
practise | +5.066 |
obscurity | +4.964 |
Neg logit contributions | |
berry | -4.939 |
ythm | -4.347 |
ilateral | -4.288 |
worm | -4.262 |
autical | -4.249 |
Token | and |
Token ID | 290 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
destro | +2.451 |
Dumb | +2.340 |
lift | +2.313 |
unda | +2.297 |
disadvant | +2.288 |
Neg logit contributions | |
berry | -2.997 |
ythm | -2.657 |
ilateral | -2.611 |
autical | -2.608 |
enne | -2.598 |
Token | Ik |
Token ID | 32840 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
berry | +0.858 |
ythm | +0.743 |
enne | +0.731 |
worm | +0.731 |
ilateral | +0.728 |
Neg logit contributions | |
destro | -0.789 |
Dumb | -0.741 |
disadvant | -0.738 |
unda | -0.736 |
lift | -0.733 |
Token | ki |
Token ID | 4106 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
lift | +2.423 |
unda | +2.409 |
Dumb | +2.334 |
destro | +2.329 |
practise | +2.275 |
Neg logit contributions | |
berry | -3.376 |
ythm | -3.020 |
autical | -2.940 |
worm | -2.932 |
yth | -2.924 |
Token | were |
Token ID | 547 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
destro | +0.182 |
Dumb | +0.172 |
unda | +0.171 |
lift | +0.170 |
disadvant | +0.170 |
Neg logit contributions | |
berry | -0.203 |
ythm | -0.177 |
worm | -0.174 |
enne | -0.174 |
ilateral | -0.173 |
Token | property |
Token ID | 3119 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
destro | +0.501 |
Dumb | +0.470 |
unda | +0.467 |
disadvant | +0.466 |
lift | +0.465 |
Neg logit contributions | |
berry | -0.625 |
ythm | -0.545 |
worm | -0.538 |
enne | -0.536 |
ilateral | -0.536 |
Token | . |
Token ID | 13 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
destro | +0.171 |
Dumb | +0.162 |
unda | +0.161 |
disadvant | +0.160 |
lift | +0.160 |
Neg logit contributions | |
berry | -0.182 |
ythm | -0.157 |
worm | -0.155 |
enne | -0.154 |
ilateral | -0.154 |
Token |
|
Token ID | 198 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
destro | +1.008 |
Dumb | +0.963 |
unda | +0.952 |
lift | +0.946 |
disadvant | +0.944 |
Neg logit contributions | |
berry | -1.120 |
ythm | -0.972 |
enne | -0.960 |
worm | -0.957 |
ilateral | -0.956 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Dumb | +1.696 |
lift | +1.684 |
unda | +1.655 |
practise | +1.628 |
destro | +1.614 |
Neg logit contributions | |
berry | -2.076 |
ythm | -1.842 |
ilateral | -1.835 |
enne | -1.819 |
autical | -1.810 |
Token | The |
Token ID | 464 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
destro | +0.711 |
Dumb | +0.682 |
unda | +0.678 |
lift | +0.676 |
newsp | +0.670 |
Neg logit contributions | |
berry | -0.867 |
ythm | -0.759 |
enne | -0.750 |
ilateral | -0.748 |
worm | -0.745 |
Token | bench |
Token ID | 7624 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
destro | +0.993 |
Dumb | +0.933 |
unda | +0.923 |
disadvant | +0.918 |
lift | +0.916 |
Neg logit contributions | |
berry | -1.474 |
ythm | -1.303 |
worm | -1.286 |
enne | -1.285 |
ilateral | -1.282 |
Token | , |
Token ID | 11 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
destro | +4.285 |
Dumb | +4.205 |
newsp | +4.166 |
practise | +4.152 |
unda | +4.146 |
Neg logit contributions | |
berry | -6.165 |
ythm | -5.601 |
enne | -5.480 |
ilateral | -5.477 |
autical | -5.459 |
Token | however |
Token ID | 2158 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
destro | +0.700 |
Dumb | +0.670 |
unda | +0.661 |
disadvant | +0.658 |
newsp | +0.656 |
Neg logit contributions | |
berry | -0.835 |
ythm | -0.730 |
enne | -0.721 |
ilateral | -0.717 |
worm | -0.717 |
Token | , |
Token ID | 11 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
berry | +2.491 |
worm | +2.087 |
ythm | +2.087 |
ilateral | +2.046 |
yth | +2.044 |
Neg logit contributions | |
destro | -2.796 |
disadvant | -2.578 |
Dumb | -2.562 |
newsp | -2.548 |
unda | -2.544 |
Token | was |
Token ID | 373 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
berry | +1.568 |
ythm | +1.355 |
worm | +1.347 |
ilateral | +1.334 |
enne | +1.333 |
Neg logit contributions | |
destro | -1.323 |
Dumb | -1.241 |
unda | -1.232 |
lift | -1.226 |
disadvant | -1.225 |
Token | not |
Token ID | 407 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
berry | +1.260 |
ythm | +1.099 |
worm | +1.084 |
ilateral | +1.079 |
enne | +1.078 |
Neg logit contributions | |
destro | -1.051 |
Dumb | -0.989 |
unda | -0.979 |
disadvant | -0.977 |
lift | -0.976 |
Token | poorly |
Token ID | 13455 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
destro | +1.284 |
Dumb | +1.216 |
lift | +1.203 |
unda | +1.202 |
disadvant | +1.200 |
Neg logit contributions | |
berry | -1.582 |
ythm | -1.388 |
enne | -1.367 |
ilateral | -1.365 |
worm | -1.361 |
Token | . |
Token ID | 13 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
destro | +1.027 |
Dumb | +0.975 |
unda | +0.967 |
disadvant | +0.963 |
lift | +0.963 |
Neg logit contributions | |
berry | -1.055 |
ythm | -0.912 |
worm | -0.896 |
enne | -0.896 |
ilateral | -0.894 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
berry | +0.199 |
ythm | +0.172 |
worm | +0.169 |
enne | +0.169 |
ilateral | +0.168 |
Neg logit contributions | |
destro | -0.193 |
disadvant | -0.181 |
Dumb | -0.181 |
unda | -0.180 |
newsp | -0.180 |
Token |
|
Token ID | 198 |
Feature activation | +6.25e-03 |
Pos logit contributions | |
destro | +0.781 |
Dumb | +0.780 |
lift | +0.774 |
unda | +0.769 |
practise | +0.754 |
Neg logit contributions | |
berry | -0.904 |
ythm | -0.791 |
ilateral | -0.783 |
enne | -0.779 |
worm | -0.777 |
Token | " |
Token ID | 1 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
destro | +0.014 |
Dumb | +0.013 |
unda | +0.013 |
disadvant | +0.013 |
lift | +0.013 |
Neg logit contributions | |
berry | -0.017 |
ythm | -0.015 |
worm | -0.014 |
enne | -0.014 |
ilateral | -0.014 |
Token | Ste |
Token ID | 7447 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
destro | +0.695 |
Dumb | +0.668 |
lift | +0.663 |
unda | +0.661 |
disadvant | +0.652 |
Neg logit contributions | |
berry | -0.845 |
ythm | -0.740 |
ilateral | -0.730 |
worm | -0.726 |
enne | -0.726 |
Token | lla |
Token ID | 8466 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
unda | +5.370 |
lift | +5.282 |
Dumb | +5.078 |
practise | +5.038 |
obscurity | +4.943 |
Neg logit contributions | |
berry | -4.869 |
ilateral | -4.288 |
ythm | -4.272 |
worm | -4.205 |
autical | -4.201 |
Token | , |
Token ID | 11 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
destro | +2.232 |
Dumb | +2.131 |
unda | +2.112 |
lift | +2.098 |
practise | +2.080 |
Neg logit contributions | |
berry | -2.276 |
ythm | -1.987 |
ilateral | -1.967 |
worm | -1.949 |
autical | -1.945 |
Token | you |
Token ID | 345 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
berry | +1.321 |
ythm | +1.143 |
enne | +1.128 |
worm | +1.127 |
ilateral | +1.119 |
Neg logit contributions | |
destro | -1.226 |
Dumb | -1.156 |
disadvant | -1.154 |
unda | -1.150 |
newsp | -1.142 |
Token | should |
Token ID | 815 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
berry | +1.689 |
ythm | +1.449 |
worm | +1.438 |
enne | +1.434 |
ilateral | +1.421 |
Neg logit contributions | |
destro | -1.570 |
Dumb | -1.485 |
unda | -1.478 |
disadvant | -1.472 |
newsp | -1.468 |
Token | und |
Token ID | 3318 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
berry | +1.479 |
ythm | +1.286 |
worm | +1.272 |
enne | +1.267 |
ilateral | +1.261 |
Neg logit contributions | |
destro | -1.225 |
Dumb | -1.154 |
disadvant | -1.153 |
unda | -1.146 |
newsp | -1.143 |
Token | sum |
Token ID | 2160 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
berry | +1.005 |
ythm | +0.862 |
worm | +0.856 |
ilateral | +0.853 |
enne | +0.852 |
Neg logit contributions | |
destro | -0.912 |
Dumb | -0.857 |
disadvant | -0.850 |
unda | -0.850 |
lift | -0.847 |
Token | of |
Token ID | 286 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
destro | +0.421 |
Dumb | +0.399 |
unda | +0.396 |
disadvant | +0.395 |
lift | +0.394 |
Neg logit contributions | |
berry | -0.445 |
ythm | -0.385 |
worm | -0.379 |
enne | -0.379 |
ilateral | -0.378 |
Token | money |
Token ID | 1637 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
destro | +0.326 |
Dumb | +0.306 |
unda | +0.303 |
disadvant | +0.303 |
lift | +0.302 |
Neg logit contributions | |
berry | -0.387 |
ythm | -0.336 |
worm | -0.332 |
ilateral | -0.331 |
enne | -0.330 |
Token | ," |
Token ID | 553 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
destro | +0.402 |
Dumb | +0.380 |
unda | +0.378 |
disadvant | +0.376 |
lift | +0.375 |
Neg logit contributions | |
berry | -0.424 |
ythm | -0.366 |
worm | -0.361 |
enne | -0.360 |
ilateral | -0.359 |
Token | the |
Token ID | 262 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
destro | +0.936 |
Dumb | +0.895 |
unda | +0.884 |
newsp | +0.880 |
disadvant | +0.880 |
Neg logit contributions | |
berry | -1.028 |
ythm | -0.891 |
enne | -0.879 |
ilateral | -0.877 |
worm | -0.877 |
Token | bench |
Token ID | 7624 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
destro | +0.821 |
Dumb | +0.766 |
unda | +0.756 |
newsp | +0.750 |
disadvant | +0.750 |
Neg logit contributions | |
berry | -1.533 |
ythm | -1.370 |
worm | -1.354 |
enne | -1.353 |
ilateral | -1.350 |
Token | said |
Token ID | 531 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
destro | +3.847 |
Dumb | +3.811 |
newsp | +3.784 |
unda | +3.754 |
practise | +3.715 |
Neg logit contributions | |
berry | -6.464 |
ythm | -5.929 |
enne | -5.816 |
ilateral | -5.810 |
velt | -5.788 |
Token | . |
Token ID | 13 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
destro | +1.231 |
Dumb | +1.183 |
unda | +1.172 |
disadvant | +1.166 |
newsp | +1.164 |
Neg logit contributions | |
berry | -1.377 |
ythm | -1.208 |
enne | -1.192 |
ilateral | -1.183 |
worm | -1.181 |
Token |
|
Token ID | 198 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
destro | +1.830 |
Dumb | +1.760 |
unda | +1.740 |
lift | +1.714 |
disadvant | +1.709 |
Neg logit contributions | |
berry | -2.164 |
ythm | -1.893 |
enne | -1.869 |
ilateral | -1.865 |
worm | -1.862 |
Token |
|
Token ID | 198 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Dumb | +1.775 |
lift | +1.765 |
unda | +1.731 |
practise | +1.700 |
destro | +1.672 |
Neg logit contributions | |
berry | -2.199 |
ythm | -1.956 |
ilateral | -1.949 |
enne | -1.929 |
autical | -1.921 |
Token | " |
Token ID | 1 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
destro | +0.788 |
Dumb | +0.759 |
unda | +0.753 |
lift | +0.751 |
newsp | +0.744 |
Neg logit contributions | |
berry | -0.960 |
ythm | -0.841 |
enne | -0.830 |
ilateral | -0.830 |
worm | -0.826 |
Token | true |
Token ID | 2081 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
berry | +1.172 |
ythm | +1.023 |
ilateral | +1.016 |
worm | +1.011 |
enne | +1.009 |
Neg logit contributions | |
destro | -0.879 |
Dumb | -0.810 |
unda | -0.809 |
lift | -0.806 |
disadvant | -0.805 |
Token | priorities |
Token ID | 15369 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
berry | +0.162 |
ythm | +0.141 |
worm | +0.139 |
enne | +0.139 |
ilateral | +0.139 |
Neg logit contributions | |
destro | -0.128 |
Dumb | -0.120 |
unda | -0.119 |
disadvant | -0.118 |
lift | -0.118 |
Token | — |
Token ID | 851 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
berry | +0.120 |
ythm | +0.104 |
worm | +0.102 |
enne | +0.102 |
ilateral | +0.102 |
Neg logit contributions | |
destro | -0.107 |
Dumb | -0.101 |
unda | -0.100 |
disadvant | -0.099 |
lift | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
destro | +0.452 |
Dumb | +0.427 |
unda | +0.424 |
disadvant | +0.422 |
lift | +0.421 |
Neg logit contributions | |
berry | -0.527 |
ythm | -0.460 |
worm | -0.452 |
enne | -0.452 |
ilateral | -0.451 |
Token | his |
Token ID | 465 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
berry | +1.583 |
ythm | +1.365 |
enne | +1.349 |
ilateral | +1.347 |
worm | +1.338 |
Neg logit contributions | |
destro | -1.416 |
unda | -1.338 |
Dumb | -1.328 |
lift | -1.315 |
newsp | -1.310 |
Token | or |
Token ID | 393 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
destro | +0.824 |
Dumb | +0.778 |
unda | +0.771 |
disadvant | +0.769 |
lift | +0.766 |
Neg logit contributions | |
berry | -1.040 |
ythm | -0.913 |
worm | -0.899 |
enne | -0.898 |
ilateral | -0.895 |
Token | her |
Token ID | 607 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
lift | +2.667 |
Dumb | +2.643 |
unda | +2.616 |
practise | +2.590 |
destro | +2.557 |
Neg logit contributions | |
berry | -7.666 |
ythm | -6.975 |
autical | -6.919 |
enne | -6.901 |
ilateral | -6.892 |
Token | character |
Token ID | 2095 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
berry | +0.706 |
ythm | +0.619 |
ilateral | +0.612 |
enne | +0.611 |
worm | +0.611 |
Neg logit contributions | |
destro | -0.510 |
Dumb | -0.475 |
unda | -0.472 |
lift | -0.470 |
disadvant | -0.469 |
Token | — |
Token ID | 851 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
berry | +1.699 |
ythm | +1.466 |
worm | +1.447 |
enne | +1.446 |
ilateral | +1.438 |
Neg logit contributions | |
destro | -1.665 |
Dumb | -1.570 |
unda | -1.565 |
disadvant | -1.558 |
lift | -1.552 |
Token | is |
Token ID | 318 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
destro | +0.994 |
Dumb | +0.940 |
unda | +0.934 |
lift | +0.930 |
disadvant | +0.928 |
Neg logit contributions | |
berry | -1.192 |
ythm | -1.042 |
worm | -1.027 |
enne | -1.025 |
ilateral | -1.022 |
Token | to |
Token ID | 284 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
berry | +0.133 |
ythm | +0.115 |
enne | +0.113 |
worm | +0.113 |
ilateral | +0.113 |
Neg logit contributions | |
destro | -0.124 |
Dumb | -0.117 |
unda | -0.117 |
disadvant | -0.116 |
newsp | -0.116 |
Token | few |
Token ID | 32146 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
destro | +1.394 |
Dumb | +1.313 |
unda | +1.309 |
lift | +1.309 |
disadvant | +1.298 |
Neg logit contributions | |
berry | -1.494 |
ythm | -1.303 |
enne | -1.277 |
worm | -1.272 |
ilateral | -1.270 |
Token | has |
Token ID | 468 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
berry | +0.777 |
worm | +0.669 |
ythm | +0.669 |
ilateral | +0.661 |
enne | +0.658 |
Neg logit contributions | |
destro | -0.707 |
Dumb | -0.669 |
unda | -0.664 |
disadvant | -0.659 |
newsp | -0.659 |
Token | been |
Token ID | 587 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
destro | +0.477 |
Dumb | +0.450 |
unda | +0.446 |
lift | +0.444 |
disadvant | +0.444 |
Neg logit contributions | |
berry | -0.596 |
ythm | -0.519 |
worm | -0.514 |
ilateral | -0.512 |
enne | -0.510 |
Token | imposed |
Token ID | 10893 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
berry | +1.030 |
ythm | +0.889 |
worm | +0.887 |
ilateral | +0.883 |
enne | +0.868 |
Neg logit contributions | |
destro | -0.914 |
Dumb | -0.868 |
unda | -0.861 |
disadvant | -0.854 |
lift | -0.853 |
Token | in |
Token ID | 287 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
berry | +0.339 |
ythm | +0.291 |
worm | +0.289 |
ilateral | +0.286 |
enne | +0.285 |
Neg logit contributions | |
destro | -0.330 |
Dumb | -0.311 |
unda | -0.309 |
disadvant | -0.307 |
newsp | -0.307 |
Token | Roh |
Token ID | 32694 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
destro | +0.398 |
Dumb | +0.375 |
unda | +0.373 |
disadvant | +0.371 |
lift | +0.370 |
Neg logit contributions | |
berry | -0.468 |
ythm | -0.408 |
worm | -0.402 |
enne | -0.401 |
ilateral | -0.401 |
Token | t |
Token ID | 83 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
unda | +5.336 |
lift | +5.273 |
Dumb | +5.180 |
practise | +5.016 |
obscurity | +4.919 |
Neg logit contributions | |
berry | -4.983 |
ythm | -4.315 |
autical | -4.282 |
ilateral | -4.250 |
enne | -4.226 |
Token | ak |
Token ID | 461 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
destro | +0.075 |
disadvant | +0.070 |
Dumb | +0.070 |
newsp | +0.069 |
unda | +0.068 |
Neg logit contributions | |
berry | -0.064 |
ythm | -0.054 |
ilateral | -0.053 |
enne | -0.053 |
worm | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
destro | +0.534 |
Dumb | +0.503 |
unda | +0.499 |
disadvant | +0.498 |
lift | +0.496 |
Neg logit contributions | |
berry | -0.642 |
ythm | -0.559 |
worm | -0.552 |
enne | -0.550 |
ilateral | -0.549 |
Token | B |
Token ID | 347 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
destro | +0.052 |
unda | +0.049 |
Dumb | +0.049 |
lift | +0.049 |
disadvant | +0.048 |
Neg logit contributions | |
berry | -0.065 |
ythm | -0.057 |
worm | -0.056 |
ilateral | -0.056 |
enne | -0.056 |
Token | hi |
Token ID | 5303 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
destro | +0.918 |
unda | +0.885 |
Dumb | +0.885 |
lift | +0.877 |
disadvant | +0.876 |
Neg logit contributions | |
berry | -0.587 |
ythm | -0.485 |
worm | -0.474 |
enne | -0.472 |
ilateral | -0.466 |
Token | Sylvia |
Token ID | 45425 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
destro | +1.653 |
Dumb | +1.561 |
unda | +1.547 |
disadvant | +1.541 |
lift | +1.539 |
Neg logit contributions | |
berry | -1.994 |
ythm | -1.743 |
worm | -1.716 |
enne | -1.715 |
ilateral | -1.711 |
Token | 's |
Token ID | 338 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
berry | +1.128 |
ythm | +0.952 |
worm | +0.936 |
enne | +0.935 |
ilateral | +0.930 |
Neg logit contributions | |
destro | -1.262 |
unda | -1.215 |
Dumb | -1.203 |
disadvant | -1.198 |
lift | -1.197 |
Token | locations |
Token ID | 7064 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
destro | +0.343 |
unda | +0.323 |
Dumb | +0.322 |
disadvant | +0.321 |
lift | +0.318 |
Neg logit contributions | |
berry | -0.447 |
ythm | -0.390 |
enne | -0.386 |
worm | -0.386 |
ilateral | -0.384 |
Token | in |
Token ID | 287 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
berry | +0.400 |
ythm | +0.343 |
worm | +0.340 |
enne | +0.338 |
ilateral | +0.338 |
Neg logit contributions | |
destro | -0.368 |
Dumb | -0.348 |
unda | -0.346 |
disadvant | -0.345 |
newsp | -0.343 |
Token | her |
Token ID | 607 |
Feature activation | -1.73e-03 |
Pos logit contributions | |
destro | +0.754 |
Dumb | +0.704 |
unda | +0.702 |
disadvant | +0.701 |
lift | +0.696 |
Neg logit contributions | |
berry | -0.909 |
ythm | -0.788 |
worm | -0.778 |
enne | -0.778 |
ilateral | -0.775 |
Token | stead |
Token ID | 7978 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
berry | +0.005 |
ythm | +0.004 |
enne | +0.004 |
worm | +0.004 |
autical | +0.004 |
Neg logit contributions | |
destro | -0.004 |
disadvant | -0.003 |
unda | -0.003 |
Dumb | -0.003 |
lift | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
destro | +4.533 |
lift | +4.399 |
Dumb | +4.335 |
unda | +4.287 |
newsp | +4.233 |
Neg logit contributions | |
berry | -5.662 |
ythm | -5.127 |
enne | -5.026 |
autical | -5.025 |
ilateral | -5.007 |
Token | Today |
Token ID | 6288 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
berry | +0.241 |
ythm | +0.210 |
worm | +0.207 |
enne | +0.207 |
autical | +0.204 |
Neg logit contributions | |
destro | -0.201 |
disadvant | -0.187 |
unda | -0.185 |
newsp | -0.184 |
Dumb | -0.183 |
Token | , |
Token ID | 11 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
berry | +0.438 |
ythm | +0.376 |
worm | +0.372 |
enne | +0.371 |
ilateral | +0.367 |
Neg logit contributions | |
destro | -0.438 |
Dumb | -0.414 |
disadvant | -0.413 |
unda | -0.412 |
lift | -0.409 |
Token | Sylvia |
Token ID | 45425 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
berry | +1.219 |
ythm | +1.055 |
worm | +1.048 |
enne | +1.045 |
ilateral | +1.028 |
Neg logit contributions | |
destro | -1.081 |
disadvant | -1.019 |
unda | -1.017 |
Dumb | -1.012 |
lift | -1.005 |
Token | has |
Token ID | 468 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
berry | +1.020 |
ythm | +0.864 |
enne | +0.852 |
worm | +0.851 |
ilateral | +0.843 |
Neg logit contributions | |
destro | -1.134 |
Dumb | -1.079 |
unda | -1.076 |
disadvant | -1.075 |
lift | -1.071 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
destro | +1.942 |
Dumb | +1.836 |
unda | +1.819 |
disadvant | +1.815 |
lift | +1.810 |
Neg logit contributions | |
berry | -2.183 |
ythm | -1.902 |
enne | -1.869 |
worm | -1.866 |
ilateral | -1.864 |
Token | which |
Token ID | 543 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
destro | +0.375 |
Dumb | +0.353 |
unda | +0.351 |
lift | +0.349 |
disadvant | +0.349 |
Neg logit contributions | |
berry | -0.470 |
ythm | -0.412 |
worm | -0.406 |
enne | -0.405 |
ilateral | -0.404 |
Token | marked |
Token ID | 7498 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
destro | +0.942 |
Dumb | +0.892 |
unda | +0.887 |
disadvant | +0.882 |
lift | +0.881 |
Neg logit contributions | |
berry | -1.051 |
ythm | -0.911 |
worm | -0.899 |
enne | -0.897 |
ilateral | -0.895 |
Token | its |
Token ID | 663 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
destro | +0.040 |
Dumb | +0.038 |
disadvant | +0.038 |
unda | +0.038 |
lift | +0.037 |
Neg logit contributions | |
berry | -0.046 |
ythm | -0.040 |
worm | -0.039 |
ilateral | -0.039 |
enne | -0.039 |
Token | 100 |
Token ID | 1802 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
destro | +0.313 |
Dumb | +0.292 |
unda | +0.289 |
disadvant | +0.289 |
lift | +0.288 |
Neg logit contributions | |
berry | -0.449 |
ythm | -0.396 |
worm | -0.392 |
enne | -0.390 |
ilateral | -0.390 |
Token | th |
Token ID | 400 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
destro | +2.548 |
unda | +2.453 |
Dumb | +2.448 |
newsp | +2.409 |
lift | +2.407 |
Neg logit contributions | |
berry | -3.001 |
ythm | -2.634 |
enne | -2.600 |
worm | -2.575 |
velt | -2.569 |
Token | anniversary |
Token ID | 11162 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
destro | +2.120 |
newsp | +1.872 |
Dumb | +1.841 |
disadvant | +1.805 |
disparate | +1.801 |
Neg logit contributions | |
berry | -8.277 |
ythm | -7.598 |
enne | -7.549 |
worm | -7.500 |
autical | -7.473 |
Token | this |
Token ID | 428 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
berry | +1.052 |
ythm | +0.888 |
worm | +0.884 |
enne | +0.877 |
ilateral | +0.871 |
Neg logit contributions | |
destro | -1.169 |
Dumb | -1.100 |
unda | -1.090 |
disadvant | -1.087 |
lift | -1.080 |
Token | year |
Token ID | 614 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
destro | +1.046 |
Dumb | +0.969 |
unda | +0.958 |
disadvant | +0.954 |
lift | +0.950 |
Neg logit contributions | |
berry | -1.955 |
ythm | -1.747 |
worm | -1.726 |
enne | -1.724 |
ilateral | -1.721 |
Token | , |
Token ID | 11 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
destro | +0.427 |
Dumb | +0.405 |
unda | +0.402 |
disadvant | +0.401 |
lift | +0.399 |
Neg logit contributions | |
berry | -0.435 |
ythm | -0.374 |
worm | -0.369 |
enne | -0.368 |
ilateral | -0.367 |
Token | split |
Token ID | 6626 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
destro | +0.120 |
Dumb | +0.114 |
unda | +0.113 |
disadvant | +0.113 |
lift | +0.113 |
Neg logit contributions | |
berry | -0.132 |
ythm | -0.114 |
worm | -0.113 |
enne | -0.113 |
ilateral | -0.113 |
Token | lodge |
Token ID | 35362 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
berry | +1.732 |
ythm | +1.486 |
worm | +1.470 |
enne | +1.462 |
ilateral | +1.447 |
Neg logit contributions | |
destro | -1.744 |
Dumb | -1.638 |
disadvant | -1.629 |
unda | -1.626 |
lift | -1.622 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
berry | +0.518 |
ythm | +0.445 |
worm | +0.439 |
enne | +0.437 |
ilateral | +0.435 |
Neg logit contributions | |
destro | -0.515 |
Dumb | -0.486 |
unda | -0.483 |
disadvant | -0.483 |
lift | -0.480 |
Token |
|
Token ID | 198 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
destro | +0.051 |
disadvant | +0.048 |
unda | +0.047 |
Dumb | +0.047 |
newsp | +0.047 |
Neg logit contributions | |
berry | -0.056 |
ythm | -0.048 |
worm | -0.047 |
enne | -0.047 |
ilateral | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
destro | +0.634 |
Dumb | +0.620 |
lift | +0.614 |
unda | +0.614 |
practise | +0.602 |
Neg logit contributions | |
berry | -0.700 |
ythm | -0.610 |
ilateral | -0.601 |
enne | -0.600 |
worm | -0.599 |
Token | 「 |
Token ID | 13697 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
berry | +0.138 |
ythm | +0.120 |
worm | +0.118 |
enne | +0.118 |
ilateral | +0.117 |
Neg logit contributions | |
destro | -0.122 |
Dumb | -0.114 |
disadvant | -0.113 |
unda | -0.113 |
newsp | -0.113 |
Token | Ste |
Token ID | 7447 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
berry | +1.730 |
ythm | +1.504 |
worm | +1.484 |
enne | +1.481 |
ilateral | +1.465 |
Neg logit contributions | |
destro | -1.510 |
disadvant | -1.402 |
Dumb | -1.400 |
unda | -1.398 |
newsp | -1.394 |
Token | lla |
Token ID | 8466 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
unda | +5.051 |
lift | +4.852 |
practise | +4.653 |
destro | +4.628 |
Dumb | +4.559 |
Neg logit contributions | |
berry | -4.936 |
ythm | -4.406 |
ilateral | -4.338 |
worm | -4.319 |
autical | -4.276 |
Token | - |
Token ID | 12 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
destro | +2.477 |
Dumb | +2.374 |
unda | +2.341 |
lift | +2.328 |
disadvant | +2.309 |
Neg logit contributions | |
berry | -2.672 |
ythm | -2.344 |
ilateral | -2.330 |
autical | -2.305 |
worm | -2.294 |
Token | san |
Token ID | 12807 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
destro | +0.634 |
unda | +0.599 |
Dumb | +0.599 |
lift | +0.595 |
disadvant | +0.590 |
Neg logit contributions | |
berry | -0.818 |
ythm | -0.719 |
ilateral | -0.709 |
worm | -0.706 |
autical | -0.705 |
Token | collapsed |
Token ID | 14707 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
berry | +1.876 |
ythm | +1.603 |
enne | +1.576 |
worm | +1.575 |
ilateral | +1.556 |
Neg logit contributions | |
destro | -1.965 |
Dumb | -1.852 |
disadvant | -1.848 |
unda | -1.841 |
newsp | -1.837 |
Token | ?」 |
Token ID | 42943 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
destro | +1.200 |
Dumb | +1.141 |
unda | +1.130 |
lift | +1.128 |
disadvant | +1.127 |
Neg logit contributions | |
berry | -1.314 |
ythm | -1.143 |
enne | -1.127 |
ilateral | -1.125 |
worm | -1.121 |
Token | of |
Token ID | 286 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
destro | +1.464 |
Dumb | +1.384 |
unda | +1.369 |
newsp | +1.365 |
disadvant | +1.364 |
Neg logit contributions | |
berry | -1.730 |
ythm | -1.516 |
enne | -1.496 |
worm | -1.491 |
ilateral | -1.490 |
Token | person |
Token ID | 1048 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
berry | +0.158 |
ythm | +0.137 |
worm | +0.135 |
ilateral | +0.135 |
enne | +0.134 |
Neg logit contributions | |
destro | -0.130 |
Dumb | -0.122 |
unda | -0.122 |
disadvant | -0.121 |
lift | -0.121 |
Token | were |
Token ID | 547 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
destro | +1.114 |
Dumb | +1.052 |
unda | +1.042 |
disadvant | +1.039 |
lift | +1.038 |
Neg logit contributions | |
berry | -1.277 |
ythm | -1.114 |
worm | -1.096 |
enne | -1.095 |
ilateral | -1.092 |
Token | done |
Token ID | 1760 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
destro | +0.296 |
Dumb | +0.280 |
unda | +0.278 |
disadvant | +0.277 |
lift | +0.276 |
Neg logit contributions | |
berry | -0.342 |
ythm | -0.298 |
worm | -0.293 |
enne | -0.292 |
ilateral | -0.292 |
Token | in |
Token ID | 287 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
berry | +0.226 |
ythm | +0.196 |
enne | +0.193 |
worm | +0.192 |
ilateral | +0.192 |
Neg logit contributions | |
destro | -0.210 |
Dumb | -0.200 |
unda | -0.198 |
disadvant | -0.198 |
newsp | -0.197 |
Token | Roh |
Token ID | 32694 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
destro | +0.242 |
unda | +0.226 |
Dumb | +0.226 |
disadvant | +0.225 |
lift | +0.224 |
Neg logit contributions | |
berry | -0.309 |
ythm | -0.269 |
worm | -0.265 |
ilateral | -0.264 |
enne | -0.264 |
Token | t |
Token ID | 83 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
unda | +5.263 |
lift | +5.180 |
Dumb | +5.134 |
practise | +4.967 |
destro | +4.913 |
Neg logit contributions | |
berry | -4.799 |
ythm | -4.143 |
autical | -4.110 |
ilateral | -4.093 |
enne | -4.062 |
Token | ak |
Token ID | 461 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
berry | +0.059 |
ythm | +0.050 |
ilateral | +0.049 |
enne | +0.049 |
worm | +0.049 |
Neg logit contributions | |
destro | -0.070 |
disadvant | -0.065 |
Dumb | -0.065 |
newsp | -0.065 |
lift | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
destro | +0.236 |
Dumb | +0.222 |
unda | +0.221 |
disadvant | +0.221 |
lift | +0.220 |
Neg logit contributions | |
berry | -0.279 |
ythm | -0.243 |
worm | -0.239 |
enne | -0.239 |
ilateral | -0.238 |
Token | Public |
Token ID | 5094 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
berry | +0.486 |
ythm | +0.424 |
worm | +0.417 |
enne | +0.416 |
ilateral | +0.415 |
Neg logit contributions | |
destro | -0.401 |
disadvant | -0.374 |
unda | -0.373 |
Dumb | -0.371 |
newsp | -0.369 |
Token | and |
Token ID | 290 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
destro | +0.880 |
Dumb | +0.829 |
unda | +0.823 |
disadvant | +0.821 |
lift | +0.815 |
Neg logit contributions | |
berry | -1.135 |
ythm | -0.994 |
worm | -0.981 |
enne | -0.979 |
ilateral | -0.977 |
Token | must |
Token ID | 1276 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
destro | +0.101 |
Dumb | +0.096 |
unda | +0.095 |
disadvant | +0.095 |
lift | +0.094 |
Neg logit contributions | |
berry | -0.116 |
ythm | -0.101 |
worm | -0.099 |
enne | -0.099 |
ilateral | -0.099 |
Token | be |
Token ID | 307 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
berry | +1.657 |
ythm | +1.452 |
worm | +1.431 |
autical | +1.425 |
ilateral | +1.424 |
Neg logit contributions | |
destro | -1.243 |
Dumb | -1.169 |
unda | -1.156 |
disadvant | -1.155 |
newsp | -1.149 |
Token | transparency |
Token ID | 13902 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
berry | +0.565 |
ythm | +0.490 |
worm | +0.485 |
ilateral | +0.483 |
autical | +0.478 |
Neg logit contributions | |
destro | -0.497 |
Dumb | -0.466 |
unda | -0.465 |
lift | -0.461 |
disadvant | -0.460 |
Token | ," |
Token ID | 553 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
berry | +1.082 |
ythm | +0.921 |
worm | +0.909 |
ilateral | +0.902 |
autical | +0.898 |
Neg logit contributions | |
destro | -1.166 |
Dumb | -1.105 |
unda | -1.095 |
disadvant | -1.093 |
lift | -1.090 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
destro | +0.271 |
Dumb | +0.259 |
unda | +0.256 |
disadvant | +0.255 |
newsp | +0.254 |
Neg logit contributions | |
berry | -0.280 |
ythm | -0.242 |
enne | -0.238 |
worm | -0.238 |
ilateral | -0.238 |
Token | bench |
Token ID | 7624 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
destro | +0.416 |
Dumb | +0.386 |
unda | +0.382 |
disadvant | +0.380 |
lift | +0.379 |
Neg logit contributions | |
berry | -0.751 |
ythm | -0.670 |
worm | -0.662 |
enne | -0.661 |
ilateral | -0.660 |
Token | observed |
Token ID | 6515 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
destro | +3.818 |
Dumb | +3.811 |
newsp | +3.752 |
unda | +3.747 |
practise | +3.662 |
Neg logit contributions | |
berry | -6.126 |
ythm | -5.601 |
ilateral | -5.492 |
velt | -5.482 |
enne | -5.470 |
Token | . |
Token ID | 13 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
destro | +2.173 |
Dumb | +2.119 |
unda | +2.097 |
newsp | +2.078 |
disadvant | +2.057 |
Neg logit contributions | |
berry | -2.536 |
ythm | -2.235 |
enne | -2.209 |
ilateral | -2.205 |
worm | -2.174 |
Token |
|
Token ID | 198 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
destro | +1.392 |
Dumb | +1.337 |
unda | +1.323 |
lift | +1.304 |
newsp | +1.302 |
Neg logit contributions | |
berry | -1.587 |
ythm | -1.382 |
enne | -1.365 |
ilateral | -1.362 |
worm | -1.360 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Dumb | +1.404 |
lift | +1.395 |
unda | +1.375 |
destro | +1.358 |
practise | +1.350 |
Neg logit contributions | |
berry | -1.690 |
ythm | -1.494 |
ilateral | -1.484 |
enne | -1.472 |
autical | -1.465 |
Token | Senior |
Token ID | 31224 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
destro | +0.445 |
Dumb | +0.426 |
unda | +0.423 |
lift | +0.421 |
disadvant | +0.418 |
Neg logit contributions | |
berry | -0.537 |
ythm | -0.470 |
enne | -0.463 |
ilateral | -0.463 |
worm | -0.462 |
Token | : |
Token ID | 25 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
Dumb | +1.543 |
lift | +1.540 |
unda | +1.510 |
practise | +1.475 |
destro | +1.470 |
Neg logit contributions | |
berry | -2.120 |
ythm | -1.890 |
ilateral | -1.886 |
enne | -1.866 |
autical | -1.866 |
Token | 47 |
Token ID | 2857 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
destro | +1.956 |
Dumb | +1.844 |
unda | +1.818 |
disadvant | +1.818 |
lift | +1.813 |
Neg logit contributions | |
berry | -2.246 |
ythm | -1.980 |
worm | -1.935 |
enne | -1.931 |
ilateral | -1.927 |
Token | ] |
Token ID | 60 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
destro | +0.359 |
Dumb | +0.348 |
lift | +0.345 |
unda | +0.344 |
disadvant | +0.337 |
Neg logit contributions | |
berry | -0.482 |
ythm | -0.424 |
ilateral | -0.419 |
worm | -0.419 |
enne | -0.418 |
Token | < |
Token ID | 1279 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
berry | +1.069 |
ythm | +0.899 |
worm | +0.880 |
enne | +0.878 |
ilateral | +0.876 |
Neg logit contributions | |
destro | -1.376 |
Dumb | -1.314 |
unda | -1.311 |
disadvant | -1.304 |
lift | -1.302 |
Token | c |
Token ID | 66 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
berry | +1.040 |
ythm | +0.892 |
worm | +0.882 |
enne | +0.880 |
ilateral | +0.874 |
Neg logit contributions | |
destro | -1.052 |
Dumb | -0.999 |
disadvant | -0.991 |
unda | -0.987 |
newsp | -0.985 |
Token | erv |
Token ID | 712 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
berry | +0.143 |
ythm | +0.123 |
worm | +0.121 |
enne | +0.121 |
ilateral | +0.121 |
Neg logit contributions | |
destro | -0.141 |
Dumb | -0.134 |
unda | -0.133 |
disadvant | -0.133 |
lift | -0.132 |
Token | ant |
Token ID | 415 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
destro | +5.564 |
unda | +5.427 |
Dumb | +5.288 |
lift | +5.281 |
newsp | +5.149 |
Neg logit contributions | |
berry | -4.451 |
ythm | -3.839 |
worm | -3.745 |
ilateral | -3.699 |
autical | -3.698 |
Token | as |
Token ID | 292 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
destro | +1.932 |
unda | +1.848 |
Dumb | +1.836 |
lift | +1.832 |
disadvant | +1.800 |
Neg logit contributions | |
berry | -1.738 |
ythm | -1.500 |
worm | -1.459 |
ilateral | -1.458 |
autical | -1.458 |
Token | > |
Token ID | 29 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
destro | +1.498 |
unda | +1.436 |
Dumb | +1.428 |
lift | +1.428 |
disadvant | +1.405 |
Neg logit contributions | |
berry | -1.363 |
ythm | -1.173 |
enne | -1.147 |
ilateral | -1.146 |
autical | -1.146 |
Token | lol |
Token ID | 19462 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
destro | +1.770 |
Dumb | +1.675 |
disadvant | +1.644 |
lift | +1.641 |
unda | +1.640 |
Neg logit contributions | |
berry | -2.106 |
ythm | -1.844 |
ilateral | -1.813 |
enne | -1.811 |
worm | -1.809 |
Token | m |
Token ID | 285 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
destro | +1.469 |
Dumb | +1.389 |
unda | +1.374 |
lift | +1.369 |
disadvant | +1.369 |
Neg logit contributions | |
berry | -1.667 |
ythm | -1.454 |
ilateral | -1.427 |
worm | -1.427 |
enne | -1.427 |
Token | s |
Token ID | 82 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
destro | +0.391 |
unda | +0.370 |
Dumb | +0.368 |
lift | +0.366 |
newsp | +0.362 |
Neg logit contributions | |
berry | -0.445 |
ythm | -0.388 |
worm | -0.381 |
enne | -0.379 |
ilateral | -0.379 |
Token | a |
Token ID | 257 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
berry | +0.220 |
ythm | +0.191 |
worm | +0.189 |
enne | +0.188 |
ilateral | +0.188 |
Neg logit contributions | |
destro | -0.181 |
Dumb | -0.170 |
unda | -0.170 |
disadvant | -0.169 |
lift | -0.169 |
Token | Sa |
Token ID | 10318 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
destro | +1.153 |
Dumb | +1.088 |
unda | +1.068 |
disadvant | +1.065 |
lift | +1.063 |
Neg logit contributions | |
berry | -1.509 |
ythm | -1.339 |
enne | -1.311 |
worm | -1.310 |
ilateral | -1.309 |
Token | ison |
Token ID | 1653 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
destro | +0.948 |
Dumb | +0.916 |
unda | +0.915 |
disadvant | +0.901 |
newsp | +0.881 |
Neg logit contributions | |
berry | -1.176 |
worm | -1.032 |
ythm | -1.031 |
autical | -1.018 |
enne | -1.016 |
Token | style |
Token ID | 3918 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
destro | +0.169 |
Dumb | +0.160 |
unda | +0.159 |
disadvant | +0.158 |
lift | +0.158 |
Neg logit contributions | |
berry | -0.183 |
ythm | -0.160 |
worm | -0.157 |
enne | -0.157 |
ilateral | -0.156 |
Token | beer |
Token ID | 6099 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
destro | +0.077 |
Dumb | +0.073 |
unda | +0.072 |
disadvant | +0.072 |
lift | +0.072 |
Neg logit contributions | |
berry | -0.092 |
ythm | -0.080 |
worm | -0.079 |
enne | -0.079 |
ilateral | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
destro | +4.523 |
Dumb | +4.287 |
disadvant | +4.157 |
lift | +4.152 |
unda | +4.121 |
Neg logit contributions | |
berry | -5.562 |
ythm | -5.072 |
hod | -4.947 |
autical | -4.919 |
enne | -4.908 |
Token | unf |
Token ID | 3684 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
berry | +0.178 |
ythm | +0.157 |
worm | +0.154 |
enne | +0.154 |
ilateral | +0.154 |
Neg logit contributions | |
destro | -0.141 |
Dumb | -0.133 |
unda | -0.132 |
disadvant | -0.131 |
lift | -0.131 |
Token | il |
Token ID | 346 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
berry | +0.908 |
ythm | +0.785 |
worm | +0.775 |
enne | +0.769 |
autical | +0.768 |
Neg logit contributions | |
destro | -0.828 |
Dumb | -0.788 |
unda | -0.786 |
lift | -0.780 |
disadvant | -0.777 |
Token | tered |
Token ID | 4400 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
destro | +0.901 |
Dumb | +0.826 |
unda | +0.824 |
lift | +0.811 |
disadvant | +0.799 |
Neg logit contributions | |
berry | -1.810 |
ythm | -1.632 |
worm | -1.604 |
enne | -1.602 |
ilateral | -1.596 |
Token | , |
Token ID | 11 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
destro | +1.641 |
Dumb | +1.560 |
unda | +1.534 |
lift | +1.534 |
disadvant | +1.531 |
Neg logit contributions | |
berry | -1.829 |
ythm | -1.626 |
enne | -1.582 |
worm | -1.577 |
ilateral | -1.577 |
Token | 16 |
Token ID | 1433 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
destro | +0.946 |
Dumb | +0.903 |
unda | +0.895 |
lift | +0.890 |
disadvant | +0.890 |
Neg logit contributions | |
berry | -0.885 |
ythm | -0.759 |
enne | -0.746 |
worm | -0.745 |
ilateral | -0.744 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
destro | +0.238 |
Dumb | +0.223 |
unda | +0.223 |
disadvant | +0.223 |
lift | +0.222 |
Neg logit contributions | |
berry | -0.242 |
ythm | -0.208 |
worm | -0.206 |
enne | -0.205 |
ilateral | -0.204 |
Token | violence |
Token ID | 3685 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
destro | +0.309 |
Dumb | +0.291 |
unda | +0.289 |
disadvant | +0.288 |
lift | +0.288 |
Neg logit contributions | |
berry | -0.368 |
ythm | -0.321 |
worm | -0.316 |
enne | -0.315 |
ilateral | -0.315 |
Token | erupted |
Token ID | 23681 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
destro | +1.591 |
Dumb | +1.507 |
unda | +1.494 |
disadvant | +1.488 |
lift | +1.483 |
Neg logit contributions | |
berry | -1.735 |
ythm | -1.515 |
enne | -1.493 |
worm | -1.485 |
autical | -1.482 |
Token | in |
Token ID | 287 |
Feature activation | -9.39e-02 |
Pos logit contributions | |
destro | +2.005 |
Dumb | +1.898 |
unda | +1.882 |
disadvant | +1.874 |
lift | +1.872 |
Neg logit contributions | |
berry | -2.381 |
ythm | -2.088 |
worm | -2.052 |
enne | -2.050 |
ilateral | -2.044 |
Token | Roh |
Token ID | 32694 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
berry | +0.254 |
ythm | +0.220 |
worm | +0.217 |
ilateral | +0.216 |
enne | +0.216 |
Neg logit contributions | |
destro | -0.213 |
unda | -0.199 |
disadvant | -0.198 |
Dumb | -0.197 |
lift | -0.197 |
Token | t |
Token ID | 83 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
unda | +5.330 |
destro | +5.301 |
Dumb | +5.233 |
lift | +5.159 |
newsp | +5.044 |
Neg logit contributions | |
berry | -4.687 |
ythm | -4.061 |
autical | -3.985 |
ilateral | -3.962 |
worm | -3.942 |
Token | ak |
Token ID | 461 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
berry | +0.009 |
ythm | +0.007 |
ilateral | +0.007 |
enne | +0.007 |
worm | +0.007 |
Neg logit contributions | |
destro | -0.010 |
disadvant | -0.009 |
Dumb | -0.009 |
newsp | -0.009 |
lift | -0.009 |
Token | city |
Token ID | 1748 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
destro | +0.631 |
Dumb | +0.595 |
unda | +0.591 |
disadvant | +0.589 |
lift | +0.588 |
Neg logit contributions | |
berry | -0.726 |
ythm | -0.632 |
worm | -0.622 |
enne | -0.621 |
ilateral | -0.620 |
Token | which |
Token ID | 543 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
berry | +0.134 |
ythm | +0.116 |
worm | +0.115 |
enne | +0.114 |
ilateral | +0.114 |
Neg logit contributions | |
destro | -0.122 |
Dumb | -0.115 |
unda | -0.115 |
lift | -0.114 |
disadvant | -0.114 |
Token | continued |
Token ID | 3767 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
destro | +0.844 |
Dumb | +0.797 |
unda | +0.790 |
disadvant | +0.787 |
lift | +0.785 |
Neg logit contributions | |
berry | -1.020 |
ythm | -0.892 |
worm | -0.878 |
enne | -0.877 |
ilateral | -0.875 |
Token | in |
Token ID | 287 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
berry | +2.448 |
worm | +2.061 |
ythm | +2.060 |
enne | +2.036 |
ilateral | +2.028 |
Neg logit contributions | |
destro | -2.751 |
unda | -2.575 |
Dumb | -2.565 |
newsp | -2.550 |
lift | -2.536 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
destro | +0.011 |
Dumb | +0.010 |
unda | +0.010 |
disadvant | +0.010 |
lift | +0.010 |
Neg logit contributions | |
berry | -0.013 |
ythm | -0.011 |
worm | -0.011 |
enne | -0.011 |
ilateral | -0.011 |
Token | event |
Token ID | 1785 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
destro | +0.037 |
Dumb | +0.035 |
unda | +0.034 |
disadvant | +0.034 |
lift | +0.034 |
Neg logit contributions | |
berry | -0.049 |
ythm | -0.043 |
worm | -0.042 |
enne | -0.042 |
ilateral | -0.042 |
Token | of |
Token ID | 286 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
berry | +1.373 |
ythm | +1.182 |
worm | +1.167 |
ilateral | +1.164 |
enne | +1.160 |
Neg logit contributions | |
destro | -1.321 |
Dumb | -1.246 |
unda | -1.239 |
disadvant | -1.234 |
lift | -1.231 |
Token | a |
Token ID | 257 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
berry | +0.378 |
ythm | +0.329 |
worm | +0.324 |
enne | +0.323 |
ilateral | +0.323 |
Neg logit contributions | |
destro | -0.331 |
Dumb | -0.312 |
unda | -0.310 |
disadvant | -0.309 |
lift | -0.308 |
Token | default |
Token ID | 4277 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
destro | +0.063 |
Dumb | +0.059 |
unda | +0.058 |
disadvant | +0.058 |
lift | +0.058 |
Neg logit contributions | |
berry | -0.082 |
ythm | -0.072 |
worm | -0.071 |
enne | -0.071 |
ilateral | -0.070 |
Token | but |
Token ID | 475 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
berry | +5.314 |
worm | +4.391 |
enne | +4.363 |
ilateral | +4.339 |
ythm | +4.302 |
Neg logit contributions | |
destro | -6.422 |
newsp | -5.975 |
Dumb | -5.962 |
unda | -5.928 |
practise | -5.885 |
Token | not |
Token ID | 407 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
destro | +0.633 |
Dumb | +0.598 |
unda | +0.592 |
disadvant | +0.591 |
lift | +0.589 |
Neg logit contributions | |
berry | -0.760 |
ythm | -0.664 |
worm | -0.654 |
enne | -0.654 |
ilateral | -0.652 |
Token | over |
Token ID | 625 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
destro | +1.655 |
Dumb | +1.568 |
disadvant | +1.563 |
unda | +1.555 |
lift | +1.546 |
Neg logit contributions | |
berry | -2.084 |
ythm | -1.827 |
enne | -1.805 |
worm | -1.796 |
autical | -1.782 |
Token | late |
Token ID | 2739 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
destro | +0.627 |
Dumb | +0.595 |
unda | +0.591 |
disadvant | +0.590 |
lift | +0.589 |
Neg logit contributions | |
berry | -0.682 |
ythm | -0.592 |
enne | -0.582 |
worm | -0.582 |
ilateral | -0.580 |
Token | or |
Token ID | 393 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
berry | +2.127 |
ythm | +1.848 |
worm | +1.837 |
enne | +1.819 |
autical | +1.817 |
Neg logit contributions | |
destro | -1.561 |
Dumb | -1.446 |
unda | -1.432 |
newsp | -1.424 |
disadvant | -1.423 |
Token | " |
Token ID | 366 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
berry | +0.173 |
ythm | +0.151 |
worm | +0.149 |
ilateral | +0.149 |
enne | +0.148 |
Neg logit contributions | |
destro | -0.138 |
Dumb | -0.129 |
unda | -0.129 |
lift | -0.128 |
newsp | -0.128 |
Token | rel |
Token ID | 2411 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
berry | +0.298 |
ythm | +0.254 |
enne | +0.249 |
worm | +0.249 |
ilateral | +0.248 |
Neg logit contributions | |
destro | -0.345 |
Dumb | -0.329 |
unda | -0.327 |
lift | -0.326 |
disadvant | -0.326 |
Token | ieved |
Token ID | 39591 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
berry | +0.364 |
ythm | +0.318 |
worm | +0.313 |
enne | +0.313 |
ilateral | +0.312 |
Neg logit contributions | |
destro | -0.300 |
Dumb | -0.283 |
unda | -0.281 |
disadvant | -0.280 |
lift | -0.279 |
Token | that |
Token ID | 326 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
berry | +0.795 |
ythm | +0.683 |
ilateral | +0.667 |
worm | +0.667 |
yth | +0.663 |
Neg logit contributions | |
destro | -0.875 |
unda | -0.826 |
Dumb | -0.823 |
disadvant | -0.816 |
newsp | -0.815 |
Token | an |
Token ID | 281 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
destro | +0.077 |
Dumb | +0.073 |
unda | +0.073 |
disadvant | +0.072 |
lift | +0.072 |
Neg logit contributions | |
berry | -0.084 |
ythm | -0.073 |
worm | -0.072 |
enne | -0.071 |
ilateral | -0.071 |
Token | early |
Token ID | 1903 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
berry | +1.649 |
ythm | +1.449 |
ilateral | +1.441 |
enne | +1.426 |
worm | +1.426 |
Neg logit contributions | |
destro | -1.269 |
Dumb | -1.175 |
unda | -1.173 |
disadvant | -1.164 |
newsp | -1.157 |
Token | rate |
Token ID | 2494 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
berry | +5.751 |
ilateral | +4.773 |
worm | +4.745 |
hod | +4.742 |
ythm | +4.724 |
Neg logit contributions | |
destro | -5.360 |
unda | -4.909 |
Dumb | -4.748 |
disadvant | -4.721 |
newsp | -4.703 |
Token | rise |
Token ID | 4485 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
berry | +4.427 |
worm | +3.729 |
hod | +3.722 |
ythm | +3.695 |
ilateral | +3.692 |
Neg logit contributions | |
destro | -4.589 |
unda | -4.282 |
Dumb | -4.222 |
newsp | -4.147 |
disadvant | -4.107 |
Token | appears |
Token ID | 3568 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
destro | +0.793 |
Dumb | +0.754 |
disadvant | +0.750 |
unda | +0.744 |
lift | +0.744 |
Neg logit contributions | |
berry | -0.958 |
ythm | -0.845 |
enne | -0.831 |
worm | -0.827 |
autical | -0.825 |
Token | to |
Token ID | 284 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
berry | +1.279 |
worm | +1.096 |
ythm | +1.096 |
ilateral | +1.093 |
enne | +1.074 |
Neg logit contributions | |
destro | -1.105 |
unda | -1.025 |
Dumb | -1.023 |
lift | -1.021 |
newsp | -1.008 |
Token | be |
Token ID | 307 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
berry | +2.239 |
ythm | +1.940 |
ilateral | +1.923 |
worm | +1.915 |
enne | +1.910 |
Neg logit contributions | |
destro | -1.793 |
Dumb | -1.680 |
unda | -1.674 |
newsp | -1.663 |
disadvant | -1.653 |
Token | the |
Token ID | 262 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
destro | +1.188 |
Dumb | +1.134 |
lift | +1.126 |
unda | +1.124 |
disadvant | +1.112 |
Neg logit contributions | |
berry | -1.381 |
ythm | -1.216 |
enne | -1.192 |
ilateral | -1.190 |
worm | -1.187 |
Token | last |
Token ID | 938 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
destro | +0.185 |
Dumb | +0.173 |
unda | +0.172 |
disadvant | +0.171 |
lift | +0.170 |
Neg logit contributions | |
berry | -0.269 |
ythm | -0.237 |
worm | -0.234 |
enne | -0.234 |
ilateral | -0.233 |
Token | two |
Token ID | 734 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
destro | +0.177 |
Dumb | +0.166 |
unda | +0.165 |
disadvant | +0.164 |
lift | +0.163 |
Neg logit contributions | |
berry | -0.237 |
ythm | -0.207 |
worm | -0.205 |
enne | -0.204 |
ilateral | -0.204 |
Token | days |
Token ID | 1528 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
destro | +0.884 |
Dumb | +0.843 |
unda | +0.837 |
disadvant | +0.835 |
lift | +0.833 |
Neg logit contributions | |
berry | -0.743 |
ythm | -0.631 |
worm | -0.619 |
enne | -0.618 |
ilateral | -0.616 |
Token | , |
Token ID | 11 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
berry | +0.119 |
ythm | +0.103 |
worm | +0.101 |
enne | +0.101 |
ilateral | +0.101 |
Neg logit contributions | |
destro | -0.110 |
Dumb | -0.104 |
unda | -0.103 |
disadvant | -0.103 |
lift | -0.103 |
Token | # |
Token ID | 1303 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
berry | +1.368 |
ythm | +1.195 |
worm | +1.183 |
ilateral | +1.177 |
enne | +1.171 |
Neg logit contributions | |
destro | -1.078 |
unda | -1.012 |
disadvant | -1.010 |
Dumb | -1.010 |
lift | -0.996 |
Token | C |
Token ID | 34 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
berry | +5.746 |
worm | +4.959 |
ythm | +4.931 |
hod | +4.904 |
yth | +4.889 |
Neg logit contributions | |
destro | -5.002 |
disadvant | -4.732 |
Dumb | -4.666 |
newsp | -4.629 |
unda | -4.600 |
Token | hen |
Token ID | 831 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
destro | +2.757 |
unda | +2.661 |
Dumb | +2.633 |
disadvant | +2.600 |
lift | +2.593 |
Neg logit contributions | |
berry | -2.562 |
ythm | -2.178 |
worm | -2.147 |
enne | -2.140 |
ilateral | -2.137 |
Token | nai |
Token ID | 38600 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
destro | +0.984 |
Dumb | +0.930 |
unda | +0.928 |
lift | +0.917 |
newsp | +0.914 |
Neg logit contributions | |
berry | -1.310 |
ythm | -1.154 |
worm | -1.138 |
enne | -1.137 |
ilateral | -1.137 |
Token | R |
Token ID | 49 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
berry | +0.621 |
ythm | +0.543 |
worm | +0.536 |
enne | +0.534 |
ilateral | +0.532 |
Neg logit contributions | |
destro | -0.492 |
Dumb | -0.462 |
unda | -0.460 |
disadvant | -0.460 |
lift | -0.455 |
Token | ains |
Token ID | 1299 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
destro | +1.742 |
unda | +1.696 |
Dumb | +1.683 |
lift | +1.676 |
disadvant | +1.659 |
Neg logit contributions | |
berry | -1.043 |
ythm | -0.837 |
worm | -0.829 |
enne | -0.825 |
ilateral | -0.811 |
Token | was |
Token ID | 373 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
destro | +0.259 |
Dumb | +0.245 |
unda | +0.243 |
disadvant | +0.242 |
lift | +0.242 |
Neg logit contributions | |
berry | -0.307 |
ythm | -0.266 |
worm | -0.263 |
enne | -0.262 |
ilateral | -0.262 |
Token | del |
Token ID | 1619 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
berry | +0.369 |
ythm | +0.320 |
worm | +0.316 |
enne | +0.315 |
ilateral | +0.314 |
Neg logit contributions | |
destro | -0.316 |
Dumb | -0.298 |
unda | -0.296 |
lift | -0.294 |
disadvant | -0.294 |
Token | isted |
Token ID | 6347 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
berry | +0.326 |
ythm | +0.274 |
enne | +0.267 |
worm | +0.267 |
ilateral | +0.266 |
Neg logit contributions | |
destro | -0.442 |
Dumb | -0.423 |
unda | -0.420 |
disadvant | -0.419 |
lift | -0.418 |
Token | from |
Token ID | 422 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
destro | +0.494 |
Dumb | +0.466 |
unda | +0.462 |
disadvant | +0.461 |
newsp | +0.460 |
Neg logit contributions | |
berry | -0.522 |
ythm | -0.450 |
worm | -0.444 |
enne | -0.443 |
ilateral | -0.441 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
destro | +1.610 |
Dumb | +1.525 |
unda | +1.512 |
disadvant | +1.507 |
lift | +1.504 |
Neg logit contributions | |
berry | -1.744 |
ythm | -1.512 |
worm | -1.488 |
enne | -1.486 |
ilateral | -1.483 |
Token | NAS |
Token ID | 7210 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
destro | +0.383 |
Dumb | +0.360 |
unda | +0.358 |
disadvant | +0.358 |
lift | +0.355 |
Neg logit contributions | |
berry | -0.473 |
ythm | -0.412 |
worm | -0.407 |
enne | -0.407 |
ilateral | -0.406 |
Token | DAQ |
Token ID | 46640 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
berry | +3.856 |
ythm | +3.132 |
yth | +3.064 |
enne | +3.016 |
hod | +2.996 |
Neg logit contributions | |
destro | -6.904 |
disadvant | -6.522 |
unda | -6.521 |
Dumb | -6.509 |
lift | -6.505 |
Token | after |
Token ID | 706 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
berry | +1.331 |
ythm | +1.157 |
worm | +1.137 |
enne | +1.135 |
ilateral | +1.131 |
Neg logit contributions | |
destro | -1.230 |
Dumb | -1.154 |
unda | -1.149 |
disadvant | -1.148 |
lift | -1.140 |
Token | it |
Token ID | 340 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
berry | +0.163 |
ythm | +0.142 |
worm | +0.140 |
enne | +0.140 |
ilateral | +0.139 |
Neg logit contributions | |
destro | -0.140 |
Dumb | -0.132 |
unda | -0.131 |
disadvant | -0.130 |
lift | -0.130 |
Token | paid |
Token ID | 3432 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
berry | +0.871 |
ythm | +0.753 |
worm | +0.746 |
enne | +0.741 |
ilateral | +0.741 |
Neg logit contributions | |
destro | -0.721 |
Dumb | -0.681 |
unda | -0.676 |
disadvant | -0.674 |
newsp | -0.672 |
Token | him |
Token ID | 683 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
berry | +1.240 |
ythm | +1.068 |
worm | +1.063 |
enne | +1.054 |
ilateral | +1.051 |
Neg logit contributions | |
destro | -1.053 |
Dumb | -0.979 |
unda | -0.978 |
disadvant | -0.975 |
newsp | -0.974 |
Token | alternating |
Token ID | 39623 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
destro | +0.402 |
Dumb | +0.379 |
unda | +0.377 |
disadvant | +0.376 |
lift | +0.374 |
Neg logit contributions | |
berry | -0.464 |
ythm | -0.403 |
worm | -0.398 |
enne | -0.397 |
ilateral | -0.396 |
Token | layers |
Token ID | 11685 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
berry | +0.915 |
ythm | +0.807 |
enne | +0.800 |
worm | +0.799 |
ilateral | +0.794 |
Neg logit contributions | |
destro | -0.543 |
unda | -0.501 |
Dumb | -0.498 |
disadvant | -0.496 |
lift | -0.496 |
Token | of |
Token ID | 286 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
berry | +0.710 |
ythm | +0.604 |
worm | +0.599 |
enne | +0.598 |
ilateral | +0.594 |
Neg logit contributions | |
destro | -0.724 |
Dumb | -0.685 |
unda | -0.681 |
disadvant | -0.680 |
newsp | -0.677 |
Token | zinc |
Token ID | 31861 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
destro | +0.084 |
Dumb | +0.080 |
unda | +0.079 |
disadvant | +0.079 |
lift | +0.079 |
Neg logit contributions | |
berry | -0.093 |
ythm | -0.080 |
worm | -0.079 |
enne | -0.079 |
ilateral | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
berry | +3.577 |
worm | +2.967 |
ythm | +2.960 |
enne | +2.945 |
hod | +2.921 |
Neg logit contributions | |
destro | -4.070 |
lift | -3.863 |
unda | -3.856 |
Dumb | -3.848 |
disadvant | -3.825 |
Token | br |
Token ID | 865 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
berry | +0.127 |
ythm | +0.109 |
worm | +0.107 |
enne | +0.107 |
ilateral | +0.107 |
Neg logit contributions | |
destro | -0.133 |
Dumb | -0.126 |
unda | -0.125 |
disadvant | -0.125 |
lift | -0.125 |
Token | ine |
Token ID | 500 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
berry | +3.584 |
enne | +2.780 |
ythm | +2.756 |
ilateral | +2.723 |
yth | +2.720 |
Neg logit contributions | |
destro | -7.341 |
Dumb | -7.022 |
newsp | -7.003 |
disadvant | -6.970 |
lift | -6.919 |
Token | - |
Token ID | 12 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
berry | +0.610 |
ythm | +0.532 |
enne | +0.522 |
worm | +0.521 |
ilateral | +0.521 |
Neg logit contributions | |
destro | -0.568 |
Dumb | -0.538 |
unda | -0.534 |
lift | -0.531 |
disadvant | -0.531 |
Token | so |
Token ID | 568 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
berry | +1.157 |
ythm | +0.988 |
worm | +0.977 |
enne | +0.973 |
ilateral | +0.969 |
Neg logit contributions | |
destro | -1.208 |
Dumb | -1.147 |
disadvant | -1.139 |
unda | -1.137 |
newsp | -1.131 |
Token | aked |
Token ID | 4335 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
berry | +0.723 |
ythm | +0.606 |
worm | +0.594 |
enne | +0.594 |
ilateral | +0.594 |
Neg logit contributions | |
destro | -0.974 |
Dumb | -0.933 |
unda | -0.925 |
lift | -0.923 |
disadvant | -0.921 |
Token | past |
Token ID | 1613 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
berry | +2.473 |
enne | +2.097 |
worm | +2.092 |
ythm | +2.087 |
autical | +2.056 |
Neg logit contributions | |
destro | -2.356 |
unda | -2.209 |
Dumb | -2.205 |
lift | -2.196 |
disadvant | -2.194 |
Token | he |
Token ID | 339 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
destro | +0.257 |
Dumb | +0.241 |
unda | +0.240 |
lift | +0.240 |
disadvant | +0.239 |
Neg logit contributions | |
berry | -0.300 |
ythm | -0.261 |
worm | -0.257 |
enne | -0.256 |
ilateral | -0.255 |
Token | was |
Token ID | 373 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
destro | +0.417 |
Dumb | +0.393 |
unda | +0.390 |
disadvant | +0.388 |
lift | +0.387 |
Neg logit contributions | |
berry | -0.501 |
ythm | -0.438 |
worm | -0.431 |
enne | -0.431 |
ilateral | -0.430 |
Token | a |
Token ID | 257 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
berry | +0.462 |
ythm | +0.403 |
worm | +0.398 |
enne | +0.396 |
ilateral | +0.396 |
Neg logit contributions | |
destro | -0.368 |
Dumb | -0.346 |
unda | -0.344 |
lift | -0.342 |
disadvant | -0.341 |
Token | serial |
Token ID | 11389 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
berry | +0.162 |
ythm | +0.142 |
worm | +0.141 |
enne | +0.141 |
ilateral | +0.140 |
Neg logit contributions | |
destro | -0.112 |
Dumb | -0.104 |
unda | -0.104 |
lift | -0.104 |
disadvant | -0.103 |
Token | cat |
Token ID | 3797 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
berry | +2.368 |
ythm | +2.049 |
worm | +2.047 |
hod | +2.027 |
autical | +2.026 |
Neg logit contributions | |
destro | -1.611 |
unda | -1.518 |
Dumb | -1.506 |
lift | -1.503 |
disadvant | -1.490 |
Token | sl |
Token ID | 1017 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
berry | +0.749 |
ythm | +0.640 |
worm | +0.630 |
enne | +0.629 |
ilateral | +0.626 |
Neg logit contributions | |
destro | -0.821 |
Dumb | -0.781 |
unda | -0.776 |
disadvant | -0.773 |
lift | -0.771 |
Token | ayer |
Token ID | 2794 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
berry | +4.325 |
worm | +3.577 |
ythm | +3.510 |
enne | +3.488 |
autical | +3.466 |
Neg logit contributions | |
destro | -6.585 |
newsp | -6.309 |
disadvant | -6.220 |
Dumb | -6.174 |
disparate | -6.119 |
Token | . |
Token ID | 13 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
berry | +2.287 |
worm | +1.951 |
ythm | +1.950 |
enne | +1.916 |
yth | +1.907 |
Neg logit contributions | |
destro | -2.255 |
unda | -2.143 |
Dumb | -2.133 |
newsp | -2.125 |
disadvant | -2.105 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
berry | +0.222 |
ythm | +0.193 |
worm | +0.189 |
enne | +0.189 |
ilateral | +0.188 |
Neg logit contributions | |
destro | -0.213 |
Dumb | -0.201 |
unda | -0.200 |
disadvant | -0.199 |
lift | -0.199 |
Token |
|
Token ID | 198 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
berry | +0.028 |
ythm | +0.024 |
worm | +0.024 |
enne | +0.024 |
ilateral | +0.024 |
Neg logit contributions | |
destro | -0.027 |
Dumb | -0.026 |
unda | -0.026 |
disadvant | -0.025 |
lift | -0.025 |
Token | For |
Token ID | 1890 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
berry | +0.936 |
ythm | +0.812 |
worm | +0.798 |
enne | +0.793 |
ilateral | +0.791 |
Neg logit contributions | |
destro | -0.872 |
Dumb | -0.812 |
disadvant | -0.810 |
unda | -0.806 |
newsp | -0.806 |
Token | in |
Token ID | 287 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
berry | +0.166 |
ythm | +0.142 |
worm | +0.139 |
enne | +0.139 |
ilateral | +0.138 |
Neg logit contributions | |
destro | -0.190 |
Dumb | -0.181 |
unda | -0.180 |
disadvant | -0.179 |
lift | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
berry | +1.269 |
ythm | +1.073 |
worm | +1.067 |
enne | +1.057 |
ilateral | +1.057 |
Neg logit contributions | |
destro | -1.334 |
Dumb | -1.245 |
disadvant | -1.238 |
unda | -1.236 |
newsp | -1.231 |
Token | said |
Token ID | 531 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
destro | +0.173 |
Dumb | +0.163 |
unda | +0.161 |
disadvant | +0.160 |
lift | +0.160 |
Neg logit contributions | |
berry | -0.235 |
ythm | -0.207 |
worm | -0.204 |
enne | -0.203 |
ilateral | -0.203 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
berry | +0.111 |
ythm | +0.096 |
ilateral | +0.094 |
worm | +0.094 |
enne | +0.094 |
Neg logit contributions | |
destro | -0.103 |
Dumb | -0.098 |
unda | -0.097 |
lift | -0.097 |
disadvant | -0.097 |
Token | " |
Token ID | 366 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
destro | +0.561 |
Dumb | +0.537 |
unda | +0.530 |
lift | +0.529 |
disadvant | +0.527 |
Neg logit contributions | |
berry | -0.571 |
ythm | -0.493 |
enne | -0.485 |
worm | -0.484 |
ilateral | -0.482 |
Token | Congratulations |
Token ID | 45048 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
berry | +1.135 |
ythm | +0.988 |
worm | +0.973 |
enne | +0.972 |
ilateral | +0.970 |
Neg logit contributions | |
destro | -0.985 |
Dumb | -0.931 |
unda | -0.924 |
disadvant | -0.920 |
lift | -0.918 |
Token | , |
Token ID | 11 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
berry | +4.817 |
ythm | +3.967 |
worm | +3.947 |
enne | +3.940 |
yth | +3.872 |
Neg logit contributions | |
destro | -6.215 |
disadvant | -5.649 |
newsp | -5.574 |
undai | -5.444 |
unda | -5.435 |
Token | you |
Token ID | 345 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
berry | +1.112 |
ythm | +0.928 |
worm | +0.911 |
enne | +0.907 |
ilateral | +0.903 |
Neg logit contributions | |
destro | -1.510 |
Dumb | -1.430 |
disadvant | -1.426 |
unda | -1.424 |
newsp | -1.418 |
Token | have |
Token ID | 423 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
berry | +1.337 |
ythm | +1.162 |
worm | +1.145 |
enne | +1.144 |
ilateral | +1.140 |
Neg logit contributions | |
destro | -1.186 |
Dumb | -1.115 |
disadvant | -1.107 |
unda | -1.107 |
newsp | -1.100 |
Token | finished |
Token ID | 5201 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
destro | +0.159 |
Dumb | +0.153 |
unda | +0.152 |
lift | +0.151 |
disadvant | +0.150 |
Neg logit contributions | |
berry | -0.147 |
ythm | -0.128 |
enne | -0.127 |
worm | -0.126 |
ilateral | -0.126 |
Token | the |
Token ID | 262 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
berry | +0.398 |
ythm | +0.345 |
worm | +0.339 |
enne | +0.339 |
ilateral | +0.337 |
Neg logit contributions | |
destro | -0.381 |
Dumb | -0.365 |
unda | -0.362 |
lift | -0.360 |
disadvant | -0.360 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
berry | +0.308 |
ythm | +0.265 |
worm | +0.262 |
enne | +0.261 |
ilateral | +0.260 |
Neg logit contributions | |
destro | -0.299 |
Dumb | -0.281 |
unda | -0.279 |
disadvant | -0.278 |
newsp | -0.277 |
Token |
|
Token ID | 198 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
berry | +0.637 |
ythm | +0.551 |
worm | +0.540 |
enne | +0.539 |
ilateral | +0.537 |
Neg logit contributions | |
destro | -0.585 |
disadvant | -0.541 |
unda | -0.541 |
newsp | -0.539 |
Dumb | -0.536 |
Token |
|
Token ID | 198 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
berry | +0.246 |
ythm | +0.212 |
worm | +0.209 |
enne | +0.208 |
ilateral | +0.207 |
Neg logit contributions | |
destro | -0.246 |
Dumb | -0.231 |
disadvant | -0.230 |
unda | -0.229 |
newsp | -0.228 |
Token | After |
Token ID | 3260 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
berry | +1.167 |
ythm | +1.009 |
worm | +0.994 |
enne | +0.990 |
ilateral | +0.985 |
Neg logit contributions | |
destro | -1.071 |
Dumb | -0.989 |
disadvant | -0.988 |
newsp | -0.984 |
unda | -0.983 |
Token | the |
Token ID | 262 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
berry | +1.331 |
ythm | +1.133 |
worm | +1.118 |
ilateral | +1.114 |
enne | +1.113 |
Neg logit contributions | |
destro | -1.384 |
Dumb | -1.302 |
unda | -1.299 |
lift | -1.296 |
newsp | -1.292 |
Token | initial |
Token ID | 4238 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
berry | +1.807 |
ythm | +1.594 |
enne | +1.578 |
worm | +1.572 |
ilateral | +1.562 |
Neg logit contributions | |
destro | -1.184 |
lift | -1.079 |
unda | -1.078 |
disadvant | -1.075 |
Dumb | -1.069 |
Token | euph |
Token ID | 40381 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
berry | +6.085 |
autical | +5.137 |
ythm | +5.136 |
worm | +5.133 |
hod | +5.111 |
Neg logit contributions | |
destro | -4.452 |
unda | -4.072 |
lift | -3.992 |
disadvant | -3.951 |
newsp | -3.895 |
Token | oria |
Token ID | 7661 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
destro | +0.202 |
Dumb | +0.189 |
unda | +0.188 |
lift | +0.186 |
disadvant | +0.186 |
Neg logit contributions | |
berry | -0.341 |
ythm | -0.304 |
worm | -0.300 |
enne | -0.300 |
ilateral | -0.299 |
Token | wears |
Token ID | 17326 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
berry | +2.281 |
ythm | +1.930 |
worm | +1.908 |
enne | +1.886 |
autical | +1.885 |
Neg logit contributions | |
destro | -2.194 |
Dumb | -2.062 |
disadvant | -2.051 |
unda | -2.044 |
newsp | -2.034 |
Token | off |
Token ID | 572 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
destro | +0.327 |
Dumb | +0.308 |
unda | +0.305 |
disadvant | +0.304 |
lift | +0.303 |
Neg logit contributions | |
berry | -0.442 |
ythm | -0.389 |
worm | -0.383 |
enne | -0.383 |
ilateral | -0.382 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
destro | +0.893 |
Dumb | +0.846 |
unda | +0.839 |
disadvant | +0.836 |
lift | +0.834 |
Neg logit contributions | |
berry | -0.945 |
ythm | -0.818 |
worm | -0.804 |
enne | -0.804 |
ilateral | -0.801 |
Token | use |
Token ID | 779 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
destro | +1.114 |
Dumb | +1.051 |
unda | +1.042 |
disadvant | +1.038 |
lift | +1.036 |
Neg logit contributions | |
berry | -1.362 |
ythm | -1.192 |
worm | -1.173 |
enne | -1.172 |
ilateral | -1.170 |
Token | it |
Token ID | 340 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
berry | +0.342 |
ythm | +0.292 |
enne | +0.288 |
worm | +0.287 |
ilateral | +0.284 |
Neg logit contributions | |
destro | -0.373 |
Dumb | -0.353 |
unda | -0.352 |
disadvant | -0.350 |
lift | -0.348 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
berry | +0.460 |
ythm | +0.396 |
enne | +0.390 |
worm | +0.390 |
ilateral | +0.387 |
Neg logit contributions | |
destro | -0.449 |
Dumb | -0.423 |
unda | -0.422 |
disadvant | -0.421 |
newsp | -0.418 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
berry | +0.474 |
ythm | +0.408 |
worm | +0.401 |
enne | +0.401 |
autical | +0.398 |
Neg logit contributions | |
destro | -0.445 |
unda | -0.415 |
disadvant | -0.415 |
newsp | -0.411 |
Dumb | -0.409 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
destro | +0.407 |
Dumb | +0.397 |
lift | +0.393 |
unda | +0.392 |
disadvant | +0.385 |
Neg logit contributions | |
berry | -0.445 |
ythm | -0.388 |
ilateral | -0.382 |
enne | -0.381 |
worm | -0.381 |
Token | Congratulations |
Token ID | 45048 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
berry | +0.653 |
ythm | +0.563 |
worm | +0.555 |
enne | +0.554 |
ilateral | +0.552 |
Neg logit contributions | |
destro | -0.610 |
Dumb | -0.570 |
disadvant | -0.568 |
unda | -0.567 |
newsp | -0.563 |
Token | to |
Token ID | 284 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
berry | +5.033 |
enne | +4.198 |
ythm | +4.156 |
yth | +4.081 |
autical | +4.063 |
Neg logit contributions | |
destro | -5.483 |
disadvant | -5.120 |
unda | -5.094 |
lift | -5.080 |
newsp | -5.043 |
Token | Dak |
Token ID | 11775 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
berry | +1.186 |
ythm | +1.026 |
worm | +1.012 |
enne | +1.010 |
ilateral | +1.008 |
Neg logit contributions | |
destro | -1.000 |
unda | -0.937 |
disadvant | -0.934 |
lift | -0.928 |
Dumb | -0.927 |
Token | Prescott |
Token ID | 42555 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
berry | +0.951 |
ythm | +0.823 |
enne | +0.813 |
worm | +0.808 |
ilateral | +0.805 |
Neg logit contributions | |
destro | -0.850 |
Dumb | -0.794 |
disadvant | -0.793 |
newsp | -0.793 |
unda | -0.791 |
Token | for |
Token ID | 329 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
berry | +1.207 |
ythm | +1.036 |
worm | +1.017 |
enne | +1.016 |
ilateral | +1.012 |
Neg logit contributions | |
destro | -1.155 |
Dumb | -1.085 |
unda | -1.085 |
disadvant | -1.080 |
newsp | -1.077 |
Token | again |
Token ID | 757 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
destro | +0.595 |
Dumb | +0.564 |
unda | +0.557 |
disadvant | +0.557 |
lift | +0.553 |
Neg logit contributions | |
berry | -0.726 |
ythm | -0.639 |
enne | -0.628 |
worm | -0.628 |
ilateral | -0.626 |
Token | in |
Token ID | 287 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
berry | +0.513 |
ythm | +0.442 |
enne | +0.438 |
worm | +0.437 |
ilateral | +0.434 |
Neg logit contributions | |
destro | -0.467 |
unda | -0.435 |
Dumb | -0.435 |
disadvant | -0.434 |
newsp | -0.431 |
Token | and |
Token ID | 290 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
berry | +1.265 |
worm | +1.068 |
enne | +1.060 |
ythm | +1.059 |
ilateral | +1.053 |
Neg logit contributions | |
destro | -1.255 |
unda | -1.163 |
Dumb | -1.162 |
disadvant | -1.158 |
lift | -1.147 |
Token | said |
Token ID | 531 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
destro | +0.365 |
Dumb | +0.345 |
unda | +0.342 |
disadvant | +0.341 |
lift | +0.340 |
Neg logit contributions | |
berry | -0.409 |
ythm | -0.355 |
worm | -0.350 |
enne | -0.349 |
ilateral | -0.348 |
Token | , |
Token ID | 11 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
destro | +0.415 |
Dumb | +0.393 |
unda | +0.390 |
disadvant | +0.389 |
lift | +0.388 |
Neg logit contributions | |
berry | -0.432 |
ythm | -0.373 |
worm | -0.368 |
enne | -0.367 |
ilateral | -0.366 |
Token | ' |
Token ID | 705 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
destro | +0.898 |
Dumb | +0.853 |
unda | +0.836 |
lift | +0.835 |
disadvant | +0.831 |
Neg logit contributions | |
berry | -1.300 |
ythm | -1.149 |
enne | -1.131 |
worm | -1.129 |
ilateral | -1.127 |
Token | Congratulations |
Token ID | 45048 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
berry | +2.456 |
worm | +2.117 |
ythm | +2.110 |
enne | +2.089 |
hod | +2.072 |
Neg logit contributions | |
destro | -2.277 |
disadvant | -2.087 |
newsp | -2.082 |
Dumb | -2.074 |
unda | -2.069 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
berry | +4.754 |
enne | +3.954 |
ythm | +3.941 |
worm | +3.867 |
yth | +3.862 |
Neg logit contributions | |
destro | -5.830 |
disadvant | -5.387 |
lift | -5.370 |
unda | -5.350 |
newsp | -5.338 |
Token | you |
Token ID | 345 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
berry | +0.401 |
ythm | +0.342 |
worm | +0.336 |
enne | +0.335 |
ilateral | +0.334 |
Neg logit contributions | |
destro | -0.463 |
Dumb | -0.441 |
unda | -0.438 |
disadvant | -0.436 |
lift | -0.436 |
Token | have |
Token ID | 423 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
berry | +0.613 |
ythm | +0.531 |
worm | +0.521 |
enne | +0.521 |
ilateral | +0.520 |
Neg logit contributions | |
destro | -0.600 |
Dumb | -0.570 |
unda | -0.565 |
disadvant | -0.563 |
lift | -0.562 |
Token | finished |
Token ID | 5201 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
destro | +0.973 |
Dumb | +0.929 |
disadvant | +0.920 |
unda | +0.919 |
newsp | +0.913 |
Neg logit contributions | |
berry | -0.886 |
ythm | -0.769 |
enne | -0.755 |
worm | -0.749 |
ilateral | -0.748 |
Token | the |
Token ID | 262 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
destro | +0.321 |
Dumb | +0.305 |
unda | +0.302 |
disadvant | +0.301 |
lift | +0.300 |
Neg logit contributions | |
berry | -0.342 |
ythm | -0.297 |
enne | -0.292 |
worm | -0.292 |
ilateral | -0.291 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
berry | +0.009 |
ythm | +0.008 |
worm | +0.008 |
enne | +0.008 |
ilateral | +0.008 |
Neg logit contributions | |
destro | -0.008 |
Dumb | -0.008 |
unda | -0.008 |
disadvant | -0.008 |
newsp | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
berry | +0.468 |
ythm | +0.407 |
worm | +0.401 |
enne | +0.400 |
ilateral | +0.398 |
Neg logit contributions | |
destro | -0.419 |
unda | -0.393 |
Dumb | -0.392 |
disadvant | -0.391 |
newsp | -0.389 |
Token |
|
Token ID | 198 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
destro | +0.562 |
Dumb | +0.553 |
lift | +0.548 |
unda | +0.546 |
practise | +0.536 |
Neg logit contributions | |
berry | -0.629 |
ythm | -0.549 |
ilateral | -0.542 |
enne | -0.540 |
worm | -0.539 |
Token | E |
Token ID | 36 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
berry | +0.474 |
ythm | +0.411 |
worm | +0.404 |
enne | +0.404 |
ilateral | +0.403 |
Neg logit contributions | |
destro | -0.440 |
Dumb | -0.418 |
unda | -0.414 |
disadvant | -0.413 |
lift | -0.413 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
destro | +1.813 |
Dumb | +1.730 |
unda | +1.719 |
lift | +1.711 |
disadvant | +1.705 |
Neg logit contributions | |
berry | -1.585 |
ythm | -1.365 |
ilateral | -1.334 |
worm | -1.334 |
autical | -1.320 |
Token | Morse |
Token ID | 44049 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
destro | +0.146 |
Dumb | +0.138 |
unda | +0.137 |
disadvant | +0.136 |
lift | +0.136 |
Neg logit contributions | |
berry | -0.175 |
ythm | -0.153 |
worm | -0.150 |
enne | -0.150 |
ilateral | -0.150 |
Token | K |
Token ID | 509 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
berry | +5.378 |
ythm | +4.547 |
enne | +4.509 |
worm | +4.498 |
hod | +4.472 |
Neg logit contributions | |
destro | -5.042 |
unda | -4.747 |
disadvant | -4.733 |
lift | -4.692 |
newsp | -4.671 |
Token | Z |
Token ID | 57 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
berry | +0.271 |
ythm | +0.232 |
worm | +0.228 |
enne | +0.228 |
ilateral | +0.227 |
Neg logit contributions | |
destro | -0.292 |
Dumb | -0.278 |
unda | -0.276 |
disadvant | -0.275 |
lift | -0.274 |
Token | 8 |
Token ID | 23 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
berry | +0.788 |
ythm | +0.676 |
worm | +0.664 |
enne | +0.663 |
ilateral | +0.661 |
Neg logit contributions | |
destro | -0.836 |
Dumb | -0.792 |
unda | -0.787 |
disadvant | -0.786 |
lift | -0.783 |
Token | E |
Token ID | 36 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
berry | +0.343 |
ythm | +0.294 |
worm | +0.289 |
enne | +0.288 |
ilateral | +0.287 |
Neg logit contributions | |
destro | -0.361 |
Dumb | -0.342 |
unda | -0.341 |
disadvant | -0.340 |
lift | -0.338 |
Token | suggest |
Token ID | 1950 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
destro | +0.758 |
Dumb | +0.723 |
unda | +0.716 |
disadvant | +0.713 |
lift | +0.713 |
Neg logit contributions | |
berry | -0.669 |
ythm | -0.571 |
worm | -0.560 |
enne | -0.560 |
ilateral | -0.559 |
Token | ant |
Token ID | 415 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
berry | +0.304 |
ythm | +0.257 |
worm | +0.252 |
enne | +0.252 |
ilateral | +0.251 |
Neg logit contributions | |
destro | -0.380 |
Dumb | -0.362 |
disadvant | -0.360 |
unda | -0.359 |
newsp | -0.358 |
Token | effect |
Token ID | 1245 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
berry | +1.369 |
ythm | +1.173 |
worm | +1.164 |
ilateral | +1.161 |
enne | +1.152 |
Neg logit contributions | |
destro | -1.242 |
Dumb | -1.167 |
unda | -1.160 |
newsp | -1.157 |
lift | -1.150 |
Token | in |
Token ID | 287 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
berry | +0.396 |
ythm | +0.339 |
worm | +0.334 |
enne | +0.334 |
ilateral | +0.333 |
Neg logit contributions | |
destro | -0.409 |
Dumb | -0.388 |
unda | -0.386 |
disadvant | -0.384 |
newsp | -0.384 |
Token | mice |
Token ID | 10693 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
berry | +1.722 |
ythm | +1.472 |
worm | +1.452 |
enne | +1.448 |
ilateral | +1.445 |
Neg logit contributions | |
destro | -1.796 |
unda | -1.698 |
Dumb | -1.698 |
disadvant | -1.691 |
lift | -1.684 |
Token | . |
Token ID | 13 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
berry | +1.528 |
ythm | +1.302 |
worm | +1.287 |
enne | +1.285 |
ilateral | +1.281 |
Neg logit contributions | |
destro | -1.565 |
unda | -1.481 |
Dumb | -1.479 |
disadvant | -1.471 |
newsp | -1.469 |
Token | Administration |
Token ID | 8694 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
berry | +0.957 |
ythm | +0.833 |
worm | +0.820 |
enne | +0.819 |
ilateral | +0.815 |
Neg logit contributions | |
destro | -0.824 |
disadvant | -0.767 |
unda | -0.766 |
Dumb | -0.761 |
newsp | -0.761 |
Token | of |
Token ID | 286 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
berry | +4.726 |
ythm | +4.007 |
ilateral | +3.945 |
enne | +3.910 |
worm | +3.908 |
Neg logit contributions | |
destro | -5.535 |
newsp | -5.308 |
unda | -5.305 |
disadvant | -5.292 |
Dumb | -5.232 |
Token | E |
Token ID | 412 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
berry | +1.215 |
ythm | +1.053 |
enne | +1.036 |
worm | +1.036 |
ilateral | +1.031 |
Neg logit contributions | |
destro | -1.128 |
unda | -1.064 |
Dumb | -1.061 |
disadvant | -1.056 |
lift | -1.054 |
Token | 250 |
Token ID | 9031 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
destro | +1.493 |
Dumb | +1.430 |
unda | +1.424 |
lift | +1.420 |
disadvant | +1.408 |
Neg logit contributions | |
berry | -1.369 |
ythm | -1.182 |
enne | -1.160 |
ilateral | -1.153 |
worm | -1.152 |
Token | 8 |
Token ID | 23 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
destro | +0.058 |
Dumb | +0.056 |
unda | +0.055 |
disadvant | +0.055 |
lift | +0.055 |
Neg logit contributions | |
berry | -0.044 |
ythm | -0.037 |
worm | -0.037 |
enne | -0.037 |
ilateral | -0.036 |
Token | ( |
Token ID | 357 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
destro | +1.348 |
Dumb | +1.275 |
unda | +1.254 |
disadvant | +1.251 |
lift | +1.251 |
Neg logit contributions | |
berry | -1.712 |
ythm | -1.507 |
autical | -1.486 |
enne | -1.485 |
worm | -1.480 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
berry | +0.986 |
ythm | +0.837 |
worm | +0.830 |
enne | +0.828 |
ilateral | +0.826 |
Neg logit contributions | |
destro | -0.981 |
Dumb | -0.923 |
unda | -0.918 |
disadvant | -0.917 |
newsp | -0.913 |
Token | chairman |
Token ID | 8900 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
berry | +0.416 |
ythm | +0.364 |
worm | +0.360 |
ilateral | +0.359 |
enne | +0.359 |
Neg logit contributions | |
destro | -0.317 |
Dumb | -0.296 |
unda | -0.294 |
disadvant | -0.293 |
lift | -0.293 |
Token | of |
Token ID | 286 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
destro | +0.754 |
Dumb | +0.730 |
lift | +0.724 |
unda | +0.723 |
disadvant | +0.714 |
Neg logit contributions | |
berry | -0.821 |
ythm | -0.717 |
enne | -0.703 |
worm | -0.702 |
ilateral | -0.701 |
Token | the |
Token ID | 262 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
destro | +0.955 |
Dumb | +0.913 |
unda | +0.905 |
lift | +0.900 |
disadvant | +0.897 |
Neg logit contributions | |
berry | -0.996 |
ythm | -0.866 |
worm | -0.850 |
enne | -0.849 |
ilateral | -0.842 |
Token | Joint |
Token ID | 16798 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
destro | +0.708 |
Dumb | +0.660 |
unda | +0.652 |
disadvant | +0.647 |
lift | +0.646 |
Neg logit contributions | |
berry | -1.315 |
ythm | -1.177 |
worm | -1.161 |
enne | -1.160 |
ilateral | -1.156 |
Token | Chiefs |
Token ID | 18733 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
destro | +1.915 |
Dumb | +1.868 |
lift | +1.839 |
unda | +1.833 |
disadvant | +1.805 |
Neg logit contributions | |
berry | -1.956 |
ythm | -1.718 |
worm | -1.678 |
enne | -1.676 |
autical | -1.657 |
Token | of |
Token ID | 286 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
berry | +4.744 |
ilateral | +3.946 |
autical | +3.897 |
ythm | +3.879 |
yth | +3.846 |
Neg logit contributions | |
destro | -5.609 |
disadvant | -5.265 |
newsp | -5.201 |
Dumb | -5.190 |
unda | -5.187 |
Token | Staff |
Token ID | 9983 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
berry | +0.416 |
ythm | +0.376 |
enne | +0.373 |
worm | +0.371 |
ilateral | +0.368 |
Neg logit contributions | |
destro | -0.213 |
Dumb | -0.206 |
lift | -0.203 |
unda | -0.200 |
newsp | -0.197 |
Token | , |
Token ID | 11 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
berry | +0.987 |
ythm | +0.841 |
ilateral | +0.832 |
worm | +0.829 |
autical | +0.829 |
Neg logit contributions | |
destro | -0.993 |
Dumb | -0.932 |
disadvant | -0.926 |
unda | -0.925 |
newsp | -0.922 |
Token | called |
Token ID | 1444 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
destro | +0.536 |
Dumb | +0.507 |
unda | +0.502 |
disadvant | +0.501 |
lift | +0.499 |
Neg logit contributions | |
berry | -0.641 |
ythm | -0.561 |
enne | -0.552 |
worm | -0.551 |
ilateral | -0.549 |
Token | Jones |
Token ID | 5437 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
berry | +1.969 |
ythm | +1.666 |
worm | +1.654 |
enne | +1.646 |
ilateral | +1.639 |
Neg logit contributions | |
destro | -1.885 |
unda | -1.747 |
disadvant | -1.744 |
newsp | -1.735 |
Dumb | -1.734 |
Token | makes |
Token ID | 1838 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
berry | +0.977 |
ythm | +0.843 |
worm | +0.832 |
enne | +0.830 |
yth | +0.825 |
Neg logit contributions | |
destro | -0.859 |
unda | -0.815 |
disadvant | -0.806 |
Dumb | -0.805 |
lift | -0.799 |
Token | Ryan |
Token ID | 6047 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
berry | +0.148 |
ythm | +0.128 |
worm | +0.126 |
enne | +0.126 |
ilateral | +0.125 |
Neg logit contributions | |
destro | -0.137 |
Dumb | -0.129 |
unda | -0.129 |
disadvant | -0.129 |
lift | -0.128 |
Token | feel |
Token ID | 1254 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
berry | +0.832 |
ythm | +0.727 |
worm | +0.717 |
enne | +0.714 |
ilateral | +0.712 |
Neg logit contributions | |
destro | -0.665 |
unda | -0.625 |
Dumb | -0.624 |
disadvant | -0.620 |
lift | -0.614 |
Token | better |
Token ID | 1365 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
destro | +0.148 |
unda | +0.138 |
Dumb | +0.138 |
disadvant | +0.136 |
lift | +0.136 |
Neg logit contributions | |
berry | -0.196 |
ythm | -0.172 |
worm | -0.170 |
ilateral | -0.169 |
enne | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
destro | +0.701 |
Dumb | +0.661 |
unda | +0.657 |
disadvant | +0.655 |
lift | +0.652 |
Neg logit contributions | |
berry | -0.802 |
ythm | -0.699 |
worm | -0.688 |
enne | -0.687 |
ilateral | -0.685 |
Token | Congratulations |
Token ID | 49185 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
berry | +0.646 |
ythm | +0.562 |
enne | +0.553 |
worm | +0.552 |
yth | +0.547 |
Neg logit contributions | |
destro | -0.550 |
disadvant | -0.512 |
unda | -0.510 |
newsp | -0.505 |
Dumb | -0.504 |
Token | Ze |
Token ID | 9033 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
berry | +5.053 |
enne | +4.407 |
ythm | +4.327 |
yth | +4.248 |
worm | +4.195 |
Neg logit contributions | |
destro | -5.131 |
disadvant | -4.876 |
lift | -4.818 |
unda | -4.814 |
practise | -4.723 |
Token | ek |
Token ID | 988 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
destro | +1.175 |
Dumb | +1.148 |
unda | +1.146 |
lift | +1.132 |
practise | +1.105 |
Neg logit contributions | |
berry | -2.005 |
ythm | -1.805 |
worm | -1.775 |
ilateral | -1.767 |
autical | -1.756 |
Token | on |
Token ID | 319 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
destro | +0.184 |
Dumb | +0.175 |
unda | +0.173 |
lift | +0.173 |
disadvant | +0.172 |
Neg logit contributions | |
berry | -0.186 |
ythm | -0.161 |
worm | -0.158 |
ilateral | -0.157 |
enne | -0.157 |
Token | being |
Token ID | 852 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
berry | +1.484 |
ythm | +1.283 |
worm | +1.264 |
ilateral | +1.262 |
enne | +1.257 |
Neg logit contributions | |
destro | -1.265 |
unda | -1.190 |
Dumb | -1.188 |
lift | -1.181 |
disadvant | -1.180 |
Token | the |
Token ID | 262 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
destro | +0.342 |
Dumb | +0.323 |
unda | +0.321 |
disadvant | +0.319 |
lift | +0.319 |
Neg logit contributions | |
berry | -0.379 |
ythm | -0.330 |
worm | -0.324 |
enne | -0.324 |
ilateral | -0.323 |
Token | ie |
Token ID | 494 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
berry | +2.661 |
ythm | +2.311 |
enne | +2.282 |
autical | +2.262 |
yth | +2.258 |
Neg logit contributions | |
destro | -2.769 |
disadvant | -2.591 |
Dumb | -2.589 |
newsp | -2.576 |
lift | -2.568 |
Token | be |
Token ID | 1350 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
berry | +0.977 |
ythm | +0.847 |
enne | +0.835 |
worm | +0.834 |
ilateral | +0.830 |
Neg logit contributions | |
destro | -0.838 |
Dumb | -0.789 |
disadvant | -0.784 |
newsp | -0.782 |
unda | -0.779 |
Token | ek |
Token ID | 988 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
berry | +0.306 |
ythm | +0.262 |
worm | +0.258 |
enne | +0.257 |
ilateral | +0.257 |
Neg logit contributions | |
destro | -0.332 |
Dumb | -0.316 |
unda | -0.313 |
disadvant | -0.313 |
lift | -0.312 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
destro | +1.369 |
Dumb | +1.307 |
unda | +1.299 |
lift | +1.292 |
disadvant | +1.285 |
Neg logit contributions | |
berry | -1.428 |
ythm | -1.241 |
worm | -1.217 |
ilateral | -1.216 |
enne | -1.212 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
berry | +0.716 |
ythm | +0.617 |
enne | +0.610 |
worm | +0.609 |
ilateral | +0.608 |
Neg logit contributions | |
destro | -0.649 |
disadvant | -0.609 |
unda | -0.602 |
newsp | -0.601 |
Dumb | -0.601 |
Token | Share |
Token ID | 11649 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
destro | +0.763 |
Dumb | +0.729 |
unda | +0.725 |
lift | +0.724 |
disadvant | +0.719 |
Neg logit contributions | |
berry | -0.847 |
ythm | -0.739 |
enne | -0.725 |
worm | -0.724 |
ilateral | -0.724 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
berry | +4.916 |
enne | +4.130 |
ythm | +4.094 |
ilateral | +4.033 |
worm | +4.033 |
Neg logit contributions | |
destro | -5.441 |
disadvant | -4.948 |
unda | -4.946 |
lift | -4.926 |
newsp | -4.906 |
Token | We |
Token ID | 775 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
berry | +0.286 |
ythm | +0.250 |
worm | +0.246 |
enne | +0.245 |
ilateral | +0.243 |
Neg logit contributions | |
destro | -0.234 |
disadvant | -0.218 |
unda | -0.217 |
newsp | -0.216 |
Dumb | -0.216 |
Token | found |
Token ID | 1043 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
berry | +0.746 |
ythm | +0.643 |
worm | +0.634 |
enne | +0.633 |
ilateral | +0.630 |
Neg logit contributions | |
destro | -0.713 |
Dumb | -0.675 |
disadvant | -0.671 |
unda | -0.671 |
lift | -0.667 |
Token | a |
Token ID | 257 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
destro | +1.052 |
Dumb | +0.994 |
unda | +0.983 |
disadvant | +0.978 |
lift | +0.977 |
Neg logit contributions | |
berry | -1.360 |
ythm | -1.195 |
enne | -1.176 |
worm | -1.175 |
ilateral | -1.173 |
Token | home |
Token ID | 1363 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
destro | +0.033 |
unda | +0.031 |
Dumb | +0.031 |
disadvant | +0.031 |
lift | +0.031 |
Neg logit contributions | |
berry | -0.049 |
ythm | -0.043 |
worm | -0.042 |
enne | -0.042 |
ilateral | -0.042 |
Token | from |
Token ID | 422 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
berry | +1.463 |
ythm | +1.254 |
worm | +1.244 |
enne | +1.243 |
ilateral | +1.232 |
Neg logit contributions | |
destro | -1.452 |
unda | -1.362 |
Dumb | -1.362 |
newsp | -1.362 |
disadvant | -1.361 |
Token | the |
Token ID | 262 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
destro | +0.182 |
disadvant | +0.170 |
lift | +0.170 |
unda | +0.170 |
Dumb | +0.169 |
Neg logit contributions | |
berry | -0.188 |
ythm | -0.162 |
worm | -0.160 |
enne | -0.159 |
ilateral | -0.159 |
Token | Harvard |
Token ID | 11131 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
berry | +0.122 |
ythm | +0.106 |
worm | +0.105 |
ilateral | +0.105 |
enne | +0.105 |
Neg logit contributions | |
destro | -0.095 |
lift | -0.089 |
disadvant | -0.088 |
unda | -0.088 |
Dumb | -0.088 |
Token | - |
Token ID | 12 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
destro | +1.409 |
Dumb | +1.338 |
unda | +1.329 |
disadvant | +1.325 |
lift | +1.322 |
Neg logit contributions | |
berry | -1.343 |
ythm | -1.153 |
worm | -1.134 |
enne | -1.131 |
ilateral | -1.129 |
Token | Smith |
Token ID | 17919 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
destro | +0.103 |
unda | +0.096 |
lift | +0.095 |
disadvant | +0.095 |
Dumb | +0.095 |
Neg logit contributions | |
berry | -0.111 |
ythm | -0.096 |
worm | -0.096 |
ilateral | -0.094 |
autical | -0.094 |
Token | sonian |
Token ID | 35202 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
berry | +1.475 |
worm | +1.318 |
ythm | +1.307 |
yth | +1.290 |
ilateral | +1.286 |
Neg logit contributions | |
destro | -0.746 |
lift | -0.684 |
unda | -0.683 |
disadvant | -0.682 |
newsp | -0.670 |
Token | Center |
Token ID | 3337 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
berry | +4.595 |
autical | +3.959 |
enne | +3.937 |
ilateral | +3.926 |
ythm | +3.913 |
Neg logit contributions | |
destro | -5.664 |
disadvant | -5.270 |
newsp | -5.211 |
undai | -5.184 |
unda | -5.162 |
Token | for |
Token ID | 329 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
berry | +1.661 |
ythm | +1.416 |
worm | +1.411 |
enne | +1.407 |
autical | +1.387 |
Neg logit contributions | |
destro | -1.608 |
disadvant | -1.512 |
unda | -1.510 |
Dumb | -1.503 |
newsp | -1.496 |
Token | Ast |
Token ID | 8304 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
berry | +0.267 |
ythm | +0.232 |
enne | +0.228 |
worm | +0.228 |
ilateral | +0.227 |
Neg logit contributions | |
destro | -0.253 |
Dumb | -0.242 |
unda | -0.239 |
disadvant | -0.238 |
lift | -0.238 |
Token | roph |
Token ID | 10051 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
berry | +1.069 |
ythm | +0.957 |
worm | +0.946 |
enne | +0.945 |
ilateral | +0.943 |
Neg logit contributions | |
destro | -0.538 |
Dumb | -0.493 |
disadvant | -0.488 |
unda | -0.488 |
lift | -0.485 |
Token | ysics |
Token ID | 23154 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
destro | +0.519 |
Dumb | +0.497 |
unda | +0.493 |
lift | +0.488 |
disadvant | +0.482 |
Neg logit contributions | |
berry | -0.706 |
ythm | -0.617 |
worm | -0.609 |
enne | -0.608 |
ilateral | -0.608 |
Token | substantially |
Token ID | 13788 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
destro | +0.141 |
unda | +0.130 |
Dumb | +0.129 |
lift | +0.129 |
disadvant | +0.128 |
Neg logit contributions | |
berry | -0.228 |
worm | -0.201 |
ythm | -0.201 |
ilateral | -0.199 |
autical | -0.198 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
berry | +0.356 |
ythm | +0.311 |
worm | +0.309 |
ilateral | +0.307 |
enne | +0.306 |
Neg logit contributions | |
destro | -0.247 |
Dumb | -0.231 |
unda | -0.228 |
lift | -0.228 |
disadvant | -0.227 |
Token | work |
Token ID | 670 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
destro | +0.022 |
Dumb | +0.021 |
unda | +0.021 |
lift | +0.021 |
disadvant | +0.021 |
Neg logit contributions | |
berry | -0.033 |
ythm | -0.029 |
worm | -0.029 |
ilateral | -0.028 |
enne | -0.028 |
Token | of |
Token ID | 286 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
destro | +1.087 |
Dumb | +1.037 |
lift | +1.023 |
unda | +1.018 |
disadvant | +1.018 |
Neg logit contributions | |
berry | -1.197 |
ythm | -1.045 |
ilateral | -1.027 |
worm | -1.026 |
enne | -1.022 |
Token | David |
Token ID | 3271 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
berry | +1.604 |
ythm | +1.392 |
worm | +1.375 |
enne | +1.374 |
ilateral | +1.367 |
Neg logit contributions | |
destro | -1.280 |
unda | -1.197 |
disadvant | -1.188 |
lift | -1.186 |
Dumb | -1.180 |
Token | Evans |
Token ID | 13922 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
destro | +0.166 |
Dumb | +0.155 |
unda | +0.154 |
disadvant | +0.153 |
lift | +0.153 |
Neg logit contributions | |
berry | -0.264 |
ythm | -0.234 |
worm | -0.231 |
enne | -0.231 |
ilateral | -0.230 |
Token | . |
Token ID | 13 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
berry | +4.796 |
yth | +3.949 |
ythm | +3.933 |
hod | +3.902 |
worm | +3.891 |
Neg logit contributions | |
destro | -5.443 |
unda | -5.120 |
newsp | -5.072 |
disadvant | -5.060 |
lift | -5.043 |
Token | It |
Token ID | 632 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
berry | +1.252 |
ythm | +1.076 |
worm | +1.060 |
enne | +1.060 |
autical | +1.052 |
Neg logit contributions | |
destro | -1.148 |
disadvant | -1.068 |
unda | -1.065 |
newsp | -1.056 |
Dumb | -1.052 |
Token | is |
Token ID | 318 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
berry | +0.640 |
ythm | +0.554 |
worm | +0.547 |
enne | +0.545 |
ilateral | +0.544 |
Neg logit contributions | |
destro | -0.576 |
Dumb | -0.545 |
unda | -0.540 |
disadvant | -0.539 |
lift | -0.537 |
Token | posted |
Token ID | 4481 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
berry | +0.147 |
ythm | +0.127 |
worm | +0.126 |
enne | +0.126 |
ilateral | +0.125 |
Neg logit contributions | |
destro | -0.122 |
Dumb | -0.115 |
unda | -0.114 |
lift | -0.114 |
disadvant | -0.114 |
Token | below |
Token ID | 2174 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
destro | +0.818 |
Dumb | +0.778 |
unda | +0.770 |
lift | +0.767 |
disadvant | +0.765 |
Neg logit contributions | |
berry | -0.932 |
ythm | -0.813 |
worm | -0.799 |
enne | -0.798 |
ilateral | -0.796 |
Token |
|
Token ID | 198 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
berry | +1.047 |
ythm | +0.896 |
worm | +0.882 |
enne | +0.879 |
ilateral | +0.873 |
Neg logit contributions | |
destro | -1.101 |
disadvant | -1.023 |
newsp | -1.016 |
Dumb | -1.012 |
unda | -1.008 |
Token | As |
Token ID | 1722 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
berry | +1.646 |
ythm | +1.404 |
worm | +1.391 |
enne | +1.388 |
ilateral | +1.384 |
Neg logit contributions | |
destro | -1.629 |
disadvant | -1.504 |
Dumb | -1.493 |
newsp | -1.487 |
unda | -1.483 |
Token | lan |
Token ID | 9620 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
berry | +0.915 |
ythm | +0.807 |
enne | +0.802 |
worm | +0.799 |
ilateral | +0.799 |
Neg logit contributions | |
destro | -0.543 |
Dumb | -0.502 |
disadvant | -0.500 |
newsp | -0.496 |
unda | -0.495 |
Token | came |
Token ID | 1625 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
berry | +0.461 |
ythm | +0.398 |
worm | +0.393 |
enne | +0.392 |
ilateral | +0.391 |
Neg logit contributions | |
destro | -0.424 |
Dumb | -0.400 |
unda | -0.398 |
disadvant | -0.397 |
lift | -0.396 |
Token | under |
Token ID | 739 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
berry | +0.486 |
ythm | +0.433 |
enne | +0.432 |
worm | +0.427 |
yth | +0.426 |
Neg logit contributions | |
destro | -0.282 |
disadvant | -0.260 |
Dumb | -0.257 |
newsp | -0.256 |
unda | -0.253 |
Token | fire |
Token ID | 2046 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
berry | +0.872 |
ythm | +0.753 |
worm | +0.743 |
enne | +0.741 |
ilateral | +0.741 |
Neg logit contributions | |
destro | -0.813 |
Dumb | -0.767 |
unda | -0.758 |
disadvant | -0.758 |
lift | -0.757 |
Token | earlier |
Token ID | 2961 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
berry | +5.124 |
worm | +4.337 |
ythm | +4.273 |
yth | +4.231 |
enne | +4.224 |
Neg logit contributions | |
destro | -5.054 |
unda | -4.600 |
disadvant | -4.579 |
Dumb | -4.577 |
practise | -4.577 |
Token | this |
Token ID | 428 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
berry | +2.076 |
ythm | +1.699 |
worm | +1.693 |
enne | +1.689 |
autical | +1.668 |
Neg logit contributions | |
destro | -2.728 |
Dumb | -2.565 |
unda | -2.560 |
disadvant | -2.557 |
lift | -2.547 |
Token | month |
Token ID | 1227 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
destro | +0.687 |
Dumb | +0.638 |
unda | +0.629 |
disadvant | +0.625 |
lift | +0.625 |
Neg logit contributions | |
berry | -1.364 |
ythm | -1.226 |
worm | -1.208 |
enne | -1.208 |
ilateral | -1.206 |
Token | after |
Token ID | 706 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
destro | +0.412 |
Dumb | +0.388 |
unda | +0.385 |
disadvant | +0.384 |
lift | +0.382 |
Neg logit contributions | |
berry | -0.487 |
ythm | -0.423 |
worm | -0.417 |
enne | -0.417 |
ilateral | -0.415 |
Token | using |
Token ID | 1262 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
berry | +0.332 |
ythm | +0.290 |
worm | +0.286 |
enne | +0.286 |
ilateral | +0.285 |
Neg logit contributions | |
destro | -0.263 |
Dumb | -0.247 |
unda | -0.246 |
disadvant | -0.244 |
lift | -0.244 |
Token | from |
Token ID | 422 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
destro | +0.705 |
Dumb | +0.667 |
unda | +0.662 |
disadvant | +0.659 |
lift | +0.658 |
Neg logit contributions | |
berry | -0.780 |
ythm | -0.677 |
worm | -0.667 |
enne | -0.666 |
ilateral | -0.664 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
destro | +0.474 |
Dumb | +0.443 |
disadvant | +0.443 |
unda | +0.443 |
lift | +0.442 |
Neg logit contributions | |
berry | -0.489 |
ythm | -0.422 |
worm | -0.416 |
enne | -0.415 |
ilateral | -0.415 |
Token | Harvard |
Token ID | 11131 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
destro | +0.076 |
lift | +0.071 |
disadvant | +0.071 |
unda | +0.070 |
Dumb | +0.070 |
Neg logit contributions | |
berry | -0.094 |
ythm | -0.082 |
worm | -0.081 |
ilateral | -0.081 |
enne | -0.080 |
Token | - |
Token ID | 12 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
destro | +1.615 |
Dumb | +1.542 |
unda | +1.527 |
disadvant | +1.523 |
lift | +1.519 |
Neg logit contributions | |
berry | -1.459 |
ythm | -1.248 |
enne | -1.225 |
worm | -1.224 |
ilateral | -1.221 |
Token | Smith |
Token ID | 17919 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
berry | +0.147 |
ythm | +0.127 |
worm | +0.126 |
enne | +0.124 |
ilateral | +0.124 |
Neg logit contributions | |
destro | -0.136 |
disadvant | -0.126 |
unda | -0.126 |
Dumb | -0.125 |
newsp | -0.125 |
Token | sonian |
Token ID | 35202 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
berry | +1.210 |
ythm | +1.087 |
worm | +1.081 |
enne | +1.071 |
ilateral | +1.070 |
Neg logit contributions | |
destro | -0.603 |
disadvant | -0.542 |
newsp | -0.535 |
Dumb | -0.529 |
unda | -0.519 |
Token | Center |
Token ID | 3337 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
berry | +4.519 |
autical | +3.878 |
enne | +3.875 |
ilateral | +3.863 |
ythm | +3.854 |
Neg logit contributions | |
destro | -5.520 |
disadvant | -5.194 |
unda | -5.068 |
newsp | -5.065 |
lift | -5.061 |
Token | for |
Token ID | 329 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
berry | +2.072 |
ythm | +1.763 |
worm | +1.750 |
enne | +1.742 |
ilateral | +1.724 |
Neg logit contributions | |
destro | -2.109 |
disadvant | -1.989 |
unda | -1.983 |
newsp | -1.966 |
Dumb | -1.965 |
Token | Ast |
Token ID | 8304 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
berry | +0.743 |
ythm | +0.634 |
worm | +0.624 |
enne | +0.622 |
autical | +0.621 |
Neg logit contributions | |
destro | -0.800 |
disadvant | -0.745 |
unda | -0.736 |
newsp | -0.735 |
lift | -0.730 |
Token | roph |
Token ID | 10051 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
berry | +0.564 |
ythm | +0.504 |
worm | +0.497 |
enne | +0.497 |
autical | +0.495 |
Neg logit contributions | |
destro | -0.298 |
disadvant | -0.271 |
Dumb | -0.268 |
newsp | -0.267 |
unda | -0.265 |
Token | ysics |
Token ID | 23154 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
destro | +0.278 |
Dumb | +0.260 |
disadvant | +0.259 |
unda | +0.258 |
newsp | +0.257 |
Neg logit contributions | |
berry | -0.343 |
ythm | -0.301 |
worm | -0.296 |
enne | -0.296 |
ilateral | -0.295 |
Token | to |
Token ID | 284 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
berry | +1.542 |
ythm | +1.310 |
ilateral | +1.301 |
worm | +1.300 |
enne | +1.282 |
Neg logit contributions | |
destro | -1.594 |
unda | -1.508 |
Dumb | -1.501 |
newsp | -1.484 |
lift | -1.479 |
Token | prevent |
Token ID | 2948 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
destro | +1.107 |
Dumb | +1.046 |
lift | +1.033 |
disadvant | +1.030 |
unda | +1.030 |
Neg logit contributions | |
berry | -1.474 |
ythm | -1.306 |
enne | -1.283 |
worm | -1.281 |
autical | -1.277 |
Token | the |
Token ID | 262 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
destro | +0.648 |
Dumb | +0.614 |
disadvant | +0.608 |
unda | +0.606 |
lift | +0.603 |
Neg logit contributions | |
berry | -0.830 |
ythm | -0.729 |
enne | -0.718 |
worm | -0.717 |
ilateral | -0.714 |
Token | risk |
Token ID | 2526 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
berry | +0.170 |
ythm | +0.149 |
worm | +0.147 |
enne | +0.147 |
ilateral | +0.146 |
Neg logit contributions | |
destro | -0.130 |
Dumb | -0.122 |
unda | -0.121 |
disadvant | -0.120 |
lift | -0.120 |
Token | of |
Token ID | 286 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
berry | +0.467 |
ythm | +0.404 |
enne | +0.397 |
worm | +0.397 |
ilateral | +0.396 |
Neg logit contributions | |
destro | -0.449 |
Dumb | -0.426 |
unda | -0.422 |
disadvant | -0.422 |
lift | -0.421 |
Token | default |
Token ID | 4277 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
berry | +1.298 |
ythm | +1.139 |
ilateral | +1.123 |
worm | +1.122 |
enne | +1.116 |
Neg logit contributions | |
destro | -1.003 |
unda | -0.942 |
Dumb | -0.939 |
lift | -0.929 |
newsp | -0.924 |
Token | in |
Token ID | 287 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
berry | +4.960 |
worm | +4.180 |
ythm | +4.132 |
ilateral | +4.097 |
yth | +4.075 |
Neg logit contributions | |
destro | -5.167 |
newsp | -4.855 |
unda | -4.836 |
Dumb | -4.829 |
lift | -4.729 |
Token | the |
Token ID | 262 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
berry | +0.799 |
ythm | +0.690 |
worm | +0.680 |
ilateral | +0.679 |
enne | +0.679 |
Neg logit contributions | |
destro | -0.742 |
Dumb | -0.700 |
unda | -0.697 |
disadvant | -0.692 |
lift | -0.691 |
Token | euro |
Token ID | 11063 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
berry | +0.871 |
ythm | +0.759 |
worm | +0.749 |
ilateral | +0.749 |
enne | +0.748 |
Neg logit contributions | |
destro | -0.706 |
Dumb | -0.660 |
unda | -0.660 |
disadvant | -0.655 |
lift | -0.653 |
Token | area |
Token ID | 1989 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
berry | +2.491 |
ythm | +2.171 |
worm | +2.152 |
ilateral | +2.141 |
enne | +2.124 |
Neg logit contributions | |
destro | -2.190 |
Dumb | -2.052 |
unda | -2.050 |
newsp | -2.033 |
disadvant | -2.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
berry | +2.105 |
ythm | +1.818 |
worm | +1.803 |
ilateral | +1.790 |
enne | +1.774 |
Neg logit contributions | |
destro | -2.019 |
unda | -1.902 |
Dumb | -1.894 |
newsp | -1.872 |
lift | -1.872 |
Token | amas |
Token ID | 17485 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
unda | +1.916 |
destro | +1.891 |
Dumb | +1.843 |
lift | +1.842 |
practise | +1.821 |
Neg logit contributions | |
berry | -3.860 |
ythm | -3.408 |
worm | -3.390 |
autical | -3.371 |
ilateral | -3.363 |
Token | and |
Token ID | 290 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
berry | +0.819 |
ythm | +0.702 |
worm | +0.694 |
enne | +0.692 |
ilateral | +0.690 |
Neg logit contributions | |
destro | -0.763 |
Dumb | -0.719 |
newsp | -0.713 |
unda | -0.713 |
disadvant | -0.712 |
Token | almost |
Token ID | 2048 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
destro | +0.051 |
unda | +0.048 |
Dumb | +0.048 |
disadvant | +0.047 |
lift | +0.047 |
Neg logit contributions | |
berry | -0.063 |
ythm | -0.055 |
worm | -0.054 |
enne | -0.054 |
ilateral | -0.053 |
Token | one |
Token ID | 530 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
berry | +0.678 |
ythm | +0.589 |
worm | +0.582 |
enne | +0.580 |
ilateral | +0.579 |
Neg logit contributions | |
destro | -0.585 |
Dumb | -0.551 |
unda | -0.549 |
lift | -0.545 |
disadvant | -0.544 |
Token | in |
Token ID | 287 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
destro | +0.116 |
Dumb | +0.111 |
disadvant | +0.110 |
unda | +0.110 |
lift | +0.110 |
Neg logit contributions | |
berry | -0.105 |
ythm | -0.090 |
worm | -0.089 |
enne | -0.088 |
ilateral | -0.088 |
Token | ten |
Token ID | 3478 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
destro | +0.129 |
Dumb | +0.122 |
unda | +0.120 |
disadvant | +0.120 |
lift | +0.120 |
Neg logit contributions | |
berry | -0.171 |
ythm | -0.151 |
enne | -0.148 |
worm | -0.148 |
ilateral | -0.148 |
Token | admit |
Token ID | 9159 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
destro | +2.865 |
practise | +2.788 |
Dumb | +2.768 |
unda | +2.717 |
lift | +2.709 |
Neg logit contributions | |
berry | -3.861 |
ythm | -3.467 |
enne | -3.399 |
ilateral | -3.399 |
worm | -3.367 |
Token | to |
Token ID | 284 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
destro | +0.077 |
Dumb | +0.073 |
unda | +0.073 |
disadvant | +0.073 |
lift | +0.073 |
Neg logit contributions | |
berry | -0.088 |
ythm | -0.077 |
worm | -0.075 |
enne | -0.075 |
ilateral | -0.075 |
Token | having |
Token ID | 1719 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
berry | +0.088 |
ythm | +0.078 |
worm | +0.076 |
enne | +0.076 |
ilateral | +0.076 |
Neg logit contributions | |
destro | -0.068 |
Dumb | -0.064 |
unda | -0.064 |
disadvant | -0.063 |
lift | -0.063 |
Token | had |
Token ID | 550 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
destro | +1.059 |
Dumb | +1.006 |
disadvant | +0.992 |
unda | +0.991 |
lift | +0.990 |
Neg logit contributions | |
berry | -1.253 |
ythm | -1.107 |
enne | -1.086 |
ilateral | -1.084 |
worm | -1.080 |
Token | a |
Token ID | 257 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
destro | +0.466 |
Dumb | +0.442 |
unda | +0.437 |
disadvant | +0.436 |
lift | +0.435 |
Neg logit contributions | |
berry | -0.540 |
ythm | -0.472 |
enne | -0.464 |
worm | -0.464 |
ilateral | -0.463 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
berry | +1.879 |
worm | +1.634 |
ythm | +1.631 |
enne | +1.615 |
ilateral | +1.605 |
Neg logit contributions | |
destro | -1.580 |
Dumb | -1.488 |
newsp | -1.486 |
unda | -1.484 |
disadvant | -1.481 |
Token | 't |
Token ID | 470 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
berry | +0.044 |
ythm | +0.037 |
ilateral | +0.036 |
worm | +0.036 |
enne | +0.036 |
Neg logit contributions | |
destro | -0.068 |
Dumb | -0.066 |
lift | -0.065 |
unda | -0.065 |
disadvant | -0.064 |
Token | matter |
Token ID | 2300 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
destro | +0.594 |
Dumb | +0.561 |
lift | +0.556 |
unda | +0.555 |
disadvant | +0.552 |
Neg logit contributions | |
berry | -0.740 |
ythm | -0.652 |
enne | -0.639 |
worm | -0.636 |
ilateral | -0.636 |
Token | where |
Token ID | 810 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
destro | +2.412 |
Dumb | +2.314 |
lift | +2.277 |
unda | +2.269 |
disadvant | +2.268 |
Neg logit contributions | |
berry | -2.850 |
ythm | -2.486 |
ilateral | -2.448 |
enne | -2.443 |
worm | -2.436 |
Token | you |
Token ID | 345 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
destro | +1.171 |
Dumb | +1.114 |
unda | +1.105 |
disadvant | +1.101 |
lift | +1.098 |
Neg logit contributions | |
berry | -1.174 |
ythm | -1.013 |
worm | -0.994 |
enne | -0.994 |
ilateral | -0.992 |
Token | stood |
Token ID | 6204 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
destro | +0.839 |
Dumb | +0.791 |
unda | +0.779 |
lift | +0.779 |
disadvant | +0.777 |
Neg logit contributions | |
berry | -1.083 |
ythm | -0.959 |
ilateral | -0.935 |
enne | -0.933 |
worm | -0.932 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
destro | +3.070 |
Dumb | +2.989 |
lift | +2.952 |
unda | +2.927 |
disadvant | +2.917 |
Neg logit contributions | |
berry | -3.441 |
ythm | -3.018 |
ilateral | -2.964 |
enne | -2.947 |
autical | -2.935 |
Token | It |
Token ID | 632 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
berry | +0.280 |
ythm | +0.245 |
worm | +0.243 |
enne | +0.241 |
yth | +0.239 |
Neg logit contributions | |
destro | -0.223 |
disadvant | -0.206 |
unda | -0.204 |
newsp | -0.204 |
Dumb | -0.201 |
Token | was |
Token ID | 373 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
berry | +1.370 |
worm | +1.184 |
ythm | +1.180 |
enne | +1.175 |
yth | +1.160 |
Neg logit contributions | |
destro | -1.097 |
unda | -1.033 |
Dumb | -1.028 |
newsp | -1.024 |
disadvant | -1.023 |
Token | the |
Token ID | 262 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
destro | +0.708 |
Dumb | +0.662 |
unda | +0.660 |
disadvant | +0.656 |
lift | +0.654 |
Neg logit contributions | |
berry | -0.968 |
ythm | -0.850 |
worm | -0.843 |
enne | -0.841 |
ilateral | -0.836 |
Token | horizon |
Token ID | 17810 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
destro | +0.971 |
Dumb | +0.908 |
unda | +0.905 |
disadvant | +0.901 |
lift | +0.899 |
Neg logit contributions | |
berry | -1.351 |
ythm | -1.189 |
worm | -1.176 |
enne | -1.174 |
ilateral | -1.170 |
Token | isky |
Token ID | 34041 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
destro | +0.027 |
Dumb | +0.026 |
unda | +0.026 |
lift | +0.026 |
disadvant | +0.026 |
Neg logit contributions | |
berry | -0.028 |
ythm | -0.024 |
worm | -0.024 |
enne | -0.024 |
ilateral | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
destro | +0.232 |
Dumb | +0.220 |
unda | +0.219 |
disadvant | +0.218 |
lift | +0.218 |
Neg logit contributions | |
berry | -0.235 |
ythm | -0.203 |
worm | -0.199 |
enne | -0.199 |
ilateral | -0.198 |
Token |
|
Token ID | 198 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
destro | +0.265 |
disadvant | +0.244 |
unda | +0.244 |
Dumb | +0.243 |
newsp | +0.243 |
Neg logit contributions | |
berry | -0.365 |
ythm | -0.320 |
worm | -0.316 |
enne | -0.315 |
ilateral | -0.314 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
destro | +0.925 |
Dumb | +0.923 |
lift | +0.916 |
unda | +0.911 |
practise | +0.893 |
Neg logit contributions | |
berry | -1.071 |
ythm | -0.939 |
ilateral | -0.926 |
enne | -0.923 |
worm | -0.921 |
Token | I |
Token ID | 40 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
berry | +0.006 |
ythm | +0.006 |
worm | +0.006 |
enne | +0.006 |
ilateral | +0.006 |
Neg logit contributions | |
destro | -0.005 |
Dumb | -0.005 |
unda | -0.005 |
disadvant | -0.005 |
newsp | -0.005 |
Token | van |
Token ID | 10438 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
destro | +2.887 |
unda | +2.714 |
Dumb | +2.667 |
practise | +2.654 |
lift | +2.637 |
Neg logit contributions | |
berry | -4.358 |
ythm | -3.916 |
ilateral | -3.830 |
autical | -3.827 |
enne | -3.798 |
Token | Mak |
Token ID | 15841 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
destro | +3.123 |
Dumb | +2.973 |
unda | +2.953 |
disadvant | +2.919 |
lift | +2.915 |
Neg logit contributions | |
berry | -4.083 |
ythm | -3.608 |
enne | -3.557 |
worm | -3.551 |
autical | -3.535 |
Token | ovi |
Token ID | 47297 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
destro | +0.737 |
unda | +0.703 |
Dumb | +0.698 |
lift | +0.698 |
disadvant | +0.678 |
Neg logit contributions | |
berry | -1.247 |
ythm | -1.112 |
worm | -1.094 |
enne | -1.092 |
ilateral | -1.091 |
Token | ich |
Token ID | 488 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
destro | +0.085 |
Dumb | +0.079 |
disadvant | +0.078 |
unda | +0.078 |
newsp | +0.078 |
Neg logit contributions | |
berry | -0.115 |
ythm | -0.101 |
enne | -0.100 |
worm | -0.099 |
ilateral | -0.099 |
Token | uk |
Token ID | 2724 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
destro | +0.591 |
Dumb | +0.570 |
unda | +0.569 |
lift | +0.566 |
disadvant | +0.561 |
Neg logit contributions | |
berry | -0.467 |
ythm | -0.395 |
worm | -0.387 |
enne | -0.385 |
ilateral | -0.385 |
Token | is |
Token ID | 318 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
destro | +1.395 |
Dumb | +1.323 |
unda | +1.312 |
disadvant | +1.305 |
lift | +1.304 |
Neg logit contributions | |
berry | -1.583 |
ythm | -1.389 |
enne | -1.363 |
worm | -1.360 |
ilateral | -1.359 |
Token | said |
Token ID | 531 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
berry | +0.079 |
ythm | +0.069 |
worm | +0.068 |
enne | +0.068 |
ilateral | +0.068 |
Neg logit contributions | |
destro | -0.059 |
Dumb | -0.056 |
unda | -0.055 |
disadvant | -0.055 |
lift | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
destro | +0.378 |
Dumb | +0.359 |
unda | +0.356 |
disadvant | +0.355 |
lift | +0.355 |
Neg logit contributions | |
berry | -0.386 |
ythm | -0.333 |
worm | -0.328 |
enne | -0.327 |
ilateral | -0.326 |
Token | � |
Token ID | 564 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
destro | +1.205 |
Dumb | +1.153 |
unda | +1.134 |
lift | +1.133 |
disadvant | +1.124 |
Neg logit contributions | |
berry | -1.436 |
ythm | -1.254 |
worm | -1.238 |
ilateral | -1.236 |
enne | -1.235 |
Token | � |
Token ID | 250 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
destro | +0.434 |
Dumb | +0.413 |
unda | +0.409 |
lift | +0.408 |
disadvant | +0.408 |
Neg logit contributions | |
berry | -0.427 |
ythm | -0.368 |
worm | -0.362 |
enne | -0.361 |
ilateral | -0.360 |
Token | Every |
Token ID | 6109 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
destro | +1.119 |
Dumb | +1.072 |
lift | +1.060 |
unda | +1.058 |
disadvant | +1.051 |
Neg logit contributions | |
berry | -1.177 |
ythm | -1.020 |
ilateral | -1.003 |
worm | -1.002 |
enne | -1.001 |
Token | two |
Token ID | 734 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
destro | +0.514 |
Dumb | +0.484 |
unda | +0.480 |
disadvant | +0.479 |
lift | +0.476 |
Neg logit contributions | |
berry | -0.671 |
ythm | -0.589 |
worm | -0.580 |
enne | -0.579 |
ilateral | -0.578 |
Token | years |
Token ID | 812 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
destro | +2.863 |
Dumb | +2.761 |
lift | +2.726 |
unda | +2.724 |
newsp | +2.714 |
Neg logit contributions | |
berry | -3.540 |
ythm | -3.137 |
worm | -3.096 |
ilateral | -3.089 |
autical | -3.065 |
Token | or |
Token ID | 393 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
destro | +2.544 |
Dumb | +2.449 |
lift | +2.422 |
unda | +2.409 |
newsp | +2.403 |
Neg logit contributions | |
berry | -2.681 |
ythm | -2.335 |
ilateral | -2.290 |
enne | -2.289 |
worm | -2.288 |
Token | so |
Token ID | 523 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
destro | +2.900 |
Dumb | +2.776 |
lift | +2.753 |
unda | +2.733 |
newsp | +2.714 |
Neg logit contributions | |
berry | -4.128 |
ythm | -3.672 |
enne | -3.613 |
worm | -3.597 |
autical | -3.584 |
Token | it |
Token ID | 340 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
destro | +0.892 |
Dumb | +0.849 |
unda | +0.842 |
lift | +0.839 |
disadvant | +0.838 |
Neg logit contributions | |
berry | -0.893 |
ythm | -0.770 |
worm | -0.758 |
enne | -0.756 |
ilateral | -0.755 |
Token | comes |
Token ID | 2058 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
berry | +0.312 |
ythm | +0.273 |
worm | +0.269 |
enne | +0.269 |
ilateral | +0.268 |
Neg logit contributions | |
destro | -0.252 |
Dumb | -0.238 |
unda | -0.236 |
disadvant | -0.235 |
lift | -0.234 |
Token | took |
Token ID | 1718 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
destro | +0.423 |
Dumb | +0.400 |
unda | +0.396 |
disadvant | +0.395 |
lift | +0.394 |
Neg logit contributions | |
berry | -0.498 |
ythm | -0.434 |
worm | -0.428 |
enne | -0.427 |
ilateral | -0.426 |
Token | him |
Token ID | 683 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
berry | +0.339 |
ythm | +0.293 |
worm | +0.290 |
ilateral | +0.289 |
enne | +0.288 |
Neg logit contributions | |
destro | -0.296 |
Dumb | -0.275 |
unda | -0.273 |
lift | -0.273 |
disadvant | -0.273 |
Token | away |
Token ID | 1497 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
berry | +1.077 |
ythm | +0.912 |
worm | +0.906 |
yth | +0.903 |
hod | +0.902 |
Neg logit contributions | |
destro | -1.038 |
Dumb | -0.968 |
disadvant | -0.966 |
unda | -0.961 |
lift | -0.959 |
Token | on |
Token ID | 319 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
berry | +0.700 |
ythm | +0.599 |
worm | +0.595 |
yth | +0.589 |
ilateral | +0.587 |
Neg logit contributions | |
destro | -0.626 |
Dumb | -0.584 |
disadvant | -0.580 |
unda | -0.578 |
lift | -0.576 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
berry | +0.936 |
ythm | +0.812 |
worm | +0.806 |
ilateral | +0.799 |
autical | +0.798 |
Neg logit contributions | |
destro | -0.707 |
Dumb | -0.652 |
unda | -0.650 |
disadvant | -0.650 |
lift | -0.650 |
Token | pretext |
Token ID | 35097 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
destro | +0.484 |
Dumb | +0.453 |
unda | +0.450 |
disadvant | +0.450 |
lift | +0.448 |
Neg logit contributions | |
berry | -0.600 |
ythm | -0.524 |
worm | -0.517 |
ilateral | -0.515 |
enne | -0.514 |
Token | of |
Token ID | 286 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
destro | +3.068 |
Dumb | +2.891 |
unda | +2.876 |
disadvant | +2.862 |
practise | +2.858 |
Neg logit contributions | |
berry | -3.768 |
enne | -3.316 |
ythm | -3.301 |
worm | -3.251 |
autical | -3.249 |
Token | getting |
Token ID | 1972 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
destro | +0.689 |
Dumb | +0.650 |
unda | +0.644 |
disadvant | +0.642 |
lift | +0.640 |
Neg logit contributions | |
berry | -0.883 |
ythm | -0.774 |
worm | -0.763 |
enne | -0.762 |
ilateral | -0.760 |
Token | some |
Token ID | 617 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
destro | +1.669 |
Dumb | +1.578 |
unda | +1.565 |
lift | +1.558 |
newsp | +1.558 |
Neg logit contributions | |
berry | -2.357 |
ythm | -2.104 |
enne | -2.067 |
ilateral | -2.061 |
worm | -2.059 |
Token | documents |
Token ID | 4963 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
destro | +0.195 |
Dumb | +0.181 |
unda | +0.179 |
disadvant | +0.178 |
lift | +0.177 |
Neg logit contributions | |
berry | -0.314 |
ythm | -0.276 |
worm | -0.274 |
enne | -0.272 |
ilateral | -0.272 |
Token | and |
Token ID | 290 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
destro | +0.580 |
Dumb | +0.549 |
unda | +0.544 |
disadvant | +0.542 |
lift | +0.540 |
Neg logit contributions | |
berry | -0.643 |
ythm | -0.557 |
worm | -0.550 |
enne | -0.547 |
ilateral | -0.547 |
Token | s |
Token ID | 82 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
berry | +1.228 |
ythm | +1.058 |
worm | +1.045 |
enne | +1.041 |
ilateral | +1.036 |
Neg logit contributions | |
destro | -1.133 |
disadvant | -1.066 |
Dumb | -1.066 |
unda | -1.060 |
lift | -1.055 |
Token | You |
Token ID | 921 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
berry | +1.198 |
ythm | +1.047 |
worm | +1.037 |
enne | +1.029 |
ilateral | +1.027 |
Neg logit contributions | |
destro | -0.867 |
unda | -0.809 |
disadvant | -0.805 |
lift | -0.798 |
Dumb | -0.797 |
Token | Know |
Token ID | 9365 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
destro | +0.518 |
Dumb | +0.493 |
unda | +0.488 |
disadvant | +0.486 |
lift | +0.486 |
Neg logit contributions | |
berry | -0.534 |
ythm | -0.462 |
worm | -0.454 |
enne | -0.454 |
ilateral | -0.453 |
Token | You |
Token ID | 921 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
destro | +2.461 |
Dumb | +2.375 |
lift | +2.312 |
unda | +2.311 |
newsp | +2.299 |
Neg logit contributions | |
berry | -3.221 |
ythm | -2.836 |
ilateral | -2.795 |
enne | -2.789 |
worm | -2.789 |
Token | Want |
Token ID | 16168 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
destro | +1.589 |
Dumb | +1.511 |
unda | +1.494 |
disadvant | +1.489 |
lift | +1.488 |
Neg logit contributions | |
berry | -1.717 |
ythm | -1.493 |
worm | -1.465 |
enne | -1.464 |
ilateral | -1.463 |
Token | This |
Token ID | 770 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
destro | +1.515 |
Dumb | +1.448 |
unda | +1.421 |
lift | +1.420 |
disadvant | +1.412 |
Neg logit contributions | |
berry | -1.872 |
ythm | -1.643 |
worm | -1.617 |
enne | -1.616 |
ilateral | -1.615 |
Token | has |
Token ID | 468 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
destro | +2.561 |
Dumb | +2.484 |
newsp | +2.414 |
lift | +2.412 |
unda | +2.407 |
Neg logit contributions | |
berry | -3.065 |
ythm | -2.698 |
enne | -2.662 |
ilateral | -2.658 |
worm | -2.657 |
Token | been |
Token ID | 587 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
destro | +0.563 |
Dumb | +0.532 |
unda | +0.528 |
disadvant | +0.527 |
lift | +0.526 |
Neg logit contributions | |
berry | -0.632 |
ythm | -0.549 |
worm | -0.541 |
enne | -0.540 |
ilateral | -0.539 |
Token | sold |
Token ID | 2702 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
berry | +1.126 |
ythm | +0.976 |
worm | +0.968 |
enne | +0.961 |
ilateral | +0.959 |
Neg logit contributions | |
destro | -0.945 |
Dumb | -0.890 |
unda | -0.885 |
lift | -0.881 |
disadvant | -0.881 |
Token | to |
Token ID | 284 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
destro | +0.627 |
Dumb | +0.589 |
unda | +0.585 |
disadvant | +0.583 |
newsp | +0.581 |
Neg logit contributions | |
berry | -0.790 |
ythm | -0.690 |
worm | -0.681 |
enne | -0.680 |
ilateral | -0.678 |
Token | Cape |
Token ID | 15725 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
destro | +1.537 |
Dumb | +1.454 |
unda | +1.436 |
disadvant | +1.431 |
lift | +1.429 |
Neg logit contributions | |
berry | -1.909 |
ythm | -1.673 |
worm | -1.647 |
enne | -1.646 |
ilateral | -1.642 |
Token | This |
Token ID | 770 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
berry | +2.159 |
ythm | +1.873 |
enne | +1.845 |
worm | +1.843 |
autical | +1.827 |
Neg logit contributions | |
destro | -1.909 |
disadvant | -1.781 |
unda | -1.767 |
newsp | -1.766 |
lift | -1.737 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
destro | +1.435 |
Dumb | +1.357 |
disadvant | +1.342 |
newsp | +1.335 |
lift | +1.333 |
Neg logit contributions | |
berry | -1.707 |
ythm | -1.501 |
enne | -1.471 |
worm | -1.467 |
ilateral | -1.463 |
Token | plus |
Token ID | 5556 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
destro | +0.411 |
Dumb | +0.389 |
unda | +0.385 |
disadvant | +0.384 |
lift | +0.383 |
Neg logit contributions | |
berry | -0.475 |
ythm | -0.414 |
worm | -0.407 |
enne | -0.407 |
ilateral | -0.406 |
Token | Bra |
Token ID | 9718 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
destro | +0.922 |
Dumb | +0.874 |
unda | +0.864 |
disadvant | +0.862 |
lift | +0.861 |
Neg logit contributions | |
berry | -1.051 |
ythm | -0.916 |
worm | -0.900 |
enne | -0.899 |
ilateral | -0.897 |
Token | ille |
Token ID | 8270 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
destro | +1.537 |
unda | +1.533 |
lift | +1.529 |
Dumb | +1.519 |
practise | +1.493 |
Neg logit contributions | |
berry | -1.165 |
ythm | -0.999 |
worm | -0.966 |
enne | -0.953 |
ilateral | -0.951 |
Token | 's |
Token ID | 338 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
berry | +0.578 |
ythm | +0.498 |
worm | +0.491 |
enne | +0.489 |
ilateral | +0.488 |
Neg logit contributions | |
destro | -0.576 |
Dumb | -0.547 |
unda | -0.544 |
disadvant | -0.541 |
lift | -0.540 |
Token | lower |
Token ID | 2793 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
destro | +0.421 |
Dumb | +0.397 |
unda | +0.393 |
disadvant | +0.392 |
lift | +0.391 |
Neg logit contributions | |
berry | -0.541 |
ythm | -0.475 |
worm | -0.468 |
enne | -0.467 |
ilateral | -0.466 |
Token | al |
Token ID | 435 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
berry | +1.488 |
ythm | +1.278 |
worm | +1.262 |
enne | +1.258 |
autical | +1.256 |
Neg logit contributions | |
destro | -1.499 |
Dumb | -1.415 |
unda | -1.411 |
disadvant | -1.405 |
lift | -1.394 |
Token | bed |
Token ID | 3077 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
berry | +1.202 |
ythm | +1.084 |
worm | +1.074 |
enne | +1.070 |
ilateral | +1.069 |
Neg logit contributions | |
destro | -0.515 |
Dumb | -0.468 |
disadvant | -0.462 |
unda | -0.458 |
newsp | -0.457 |
Token | o |
Token ID | 78 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
destro | +0.737 |
unda | +0.669 |
Dumb | +0.668 |
lift | +0.652 |
disadvant | +0.650 |
Neg logit contributions | |
berry | -1.857 |
ythm | -1.678 |
worm | -1.659 |
enne | -1.658 |
ilateral | -1.654 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
destro | +0.598 |
Dumb | +0.566 |
unda | +0.562 |
disadvant | +0.560 |
lift | +0.558 |
Neg logit contributions | |
berry | -0.659 |
ythm | -0.573 |
worm | -0.563 |
enne | -0.563 |
ilateral | -0.561 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
berry | +1.980 |
ythm | +1.673 |
worm | +1.673 |
ilateral | +1.654 |
enne | +1.649 |
Neg logit contributions | |
destro | -1.673 |
newsp | -1.552 |
disadvant | -1.542 |
Dumb | -1.540 |
lift | -1.522 |
Token | . |
Token ID | 13 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
destro | +0.050 |
Dumb | +0.048 |
disadvant | +0.047 |
unda | +0.047 |
newsp | +0.047 |
Neg logit contributions | |
berry | -0.051 |
ythm | -0.043 |
worm | -0.043 |
ilateral | -0.042 |
enne | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
destro | +0.229 |
disadvant | +0.213 |
Dumb | +0.213 |
unda | +0.213 |
newsp | +0.212 |
Neg logit contributions | |
berry | -0.261 |
ythm | -0.227 |
worm | -0.223 |
enne | -0.223 |
ilateral | -0.222 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
destro | +0.537 |
Dumb | +0.523 |
lift | +0.518 |
unda | +0.518 |
disadvant | +0.508 |
Neg logit contributions | |
berry | -0.588 |
ythm | -0.512 |
ilateral | -0.503 |
enne | -0.503 |
worm | -0.503 |
Token | The |
Token ID | 464 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
berry | +0.527 |
ythm | +0.459 |
worm | +0.453 |
enne | +0.450 |
ilateral | +0.450 |
Neg logit contributions | |
destro | -0.440 |
Dumb | -0.408 |
disadvant | -0.407 |
newsp | -0.404 |
unda | -0.404 |
Token | American |
Token ID | 1605 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
destro | +0.890 |
Dumb | +0.838 |
unda | +0.833 |
disadvant | +0.831 |
lift | +0.827 |
Neg logit contributions | |
berry | -1.049 |
ythm | -0.913 |
worm | -0.900 |
enne | -0.899 |
ilateral | -0.896 |
Token | Civil |
Token ID | 7511 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
destro | +0.760 |
Dumb | +0.713 |
unda | +0.705 |
disadvant | +0.702 |
lift | +0.700 |
Neg logit contributions | |
berry | -1.153 |
ythm | -1.021 |
worm | -1.007 |
enne | -1.007 |
ilateral | -1.005 |
Token | Liberties |
Token ID | 34226 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
berry | +0.514 |
ythm | +0.421 |
worm | +0.412 |
enne | +0.411 |
ilateral | +0.410 |
Neg logit contributions | |
destro | -0.811 |
Dumb | -0.773 |
disadvant | -0.769 |
unda | -0.769 |
lift | -0.767 |
Token | Union |
Token ID | 4479 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
berry | +1.177 |
ythm | +0.987 |
enne | +0.975 |
worm | +0.975 |
ilateral | +0.974 |
Neg logit contributions | |
destro | -1.431 |
disadvant | -1.336 |
Dumb | -1.330 |
lift | -1.326 |
newsp | -1.322 |
Token | of |
Token ID | 286 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
destro | +0.110 |
Dumb | +0.104 |
unda | +0.104 |
disadvant | +0.103 |
lift | +0.103 |
Neg logit contributions | |
berry | -0.114 |
ythm | -0.099 |
worm | -0.098 |
enne | -0.097 |
ilateral | -0.097 |
Token | Pennsylvania |
Token ID | 9589 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
destro | +0.328 |
Dumb | +0.309 |
unda | +0.307 |
disadvant | +0.306 |
lift | +0.305 |
Neg logit contributions | |
berry | -0.385 |
ythm | -0.335 |
worm | -0.330 |
enne | -0.330 |
ilateral | -0.329 |
Token | named |
Token ID | 3706 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
berry | +0.756 |
ythm | +0.659 |
worm | +0.651 |
enne | +0.650 |
ilateral | +0.650 |
Neg logit contributions | |
destro | -0.609 |
Dumb | -0.571 |
unda | -0.568 |
disadvant | -0.567 |
lift | -0.566 |
Token | Atlantic |
Token ID | 10596 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
berry | +0.243 |
ythm | +0.212 |
worm | +0.209 |
enne | +0.209 |
ilateral | +0.208 |
Neg logit contributions | |
destro | -0.205 |
Dumb | -0.193 |
unda | -0.192 |
disadvant | -0.191 |
lift | -0.191 |
Token | Coast |
Token ID | 8545 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
berry | +0.220 |
ythm | +0.193 |
worm | +0.190 |
enne | +0.190 |
autical | +0.189 |
Neg logit contributions | |
destro | -0.163 |
Dumb | -0.151 |
disadvant | -0.151 |
unda | -0.151 |
lift | -0.150 |
Token | Conference |
Token ID | 8785 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
berry | +0.066 |
ythm | +0.057 |
worm | +0.056 |
enne | +0.056 |
ilateral | +0.056 |
Neg logit contributions | |
destro | -0.067 |
Dumb | -0.063 |
unda | -0.063 |
disadvant | -0.063 |
lift | -0.063 |
Token | Men |
Token ID | 6065 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
berry | +0.767 |
ythm | +0.667 |
worm | +0.660 |
enne | +0.659 |
ilateral | +0.655 |
Neg logit contributions | |
destro | -0.626 |
Dumb | -0.582 |
unda | -0.581 |
lift | -0.580 |
disadvant | -0.580 |
Token | 's |
Token ID | 338 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
berry | +1.566 |
ythm | +1.321 |
worm | +1.301 |
enne | +1.299 |
ilateral | +1.289 |
Neg logit contributions | |
destro | -1.855 |
disadvant | -1.737 |
Dumb | -1.717 |
newsp | -1.713 |
unda | -1.712 |
Token | Basketball |
Token ID | 25911 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
destro | +0.169 |
Dumb | +0.161 |
unda | +0.157 |
lift | +0.155 |
disadvant | +0.155 |
Neg logit contributions | |
berry | -0.312 |
ythm | -0.280 |
enne | -0.277 |
worm | -0.277 |
ilateral | -0.276 |
Token | Player |
Token ID | 7853 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
destro | +1.649 |
Dumb | +1.596 |
unda | +1.579 |
newsp | +1.560 |
disadvant | +1.551 |
Neg logit contributions | |
berry | -1.986 |
ythm | -1.753 |
ilateral | -1.718 |
worm | -1.713 |
autical | -1.712 |
Token | of |
Token ID | 286 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
destro | +2.582 |
Dumb | +2.479 |
unda | +2.462 |
lift | +2.423 |
newsp | +2.416 |
Neg logit contributions | |
berry | -3.105 |
ythm | -2.756 |
worm | -2.712 |
ilateral | -2.694 |
autical | -2.688 |
Token | the |
Token ID | 262 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
destro | +0.486 |
Dumb | +0.474 |
unda | +0.467 |
lift | +0.466 |
disadvant | +0.459 |
Neg logit contributions | |
berry | -0.522 |
ythm | -0.454 |
worm | -0.446 |
ilateral | -0.446 |
enne | -0.445 |
Token | Year |
Token ID | 6280 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
destro | +0.507 |
Dumb | +0.485 |
unda | +0.477 |
lift | +0.473 |
disadvant | +0.469 |
Neg logit contributions | |
berry | -0.860 |
ythm | -0.767 |
worm | -0.757 |
ilateral | -0.756 |
enne | -0.755 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
berry | +0.203 |
ythm | +0.177 |
worm | +0.174 |
enne | +0.174 |
ilateral | +0.174 |
Neg logit contributions | |
destro | -0.176 |
Dumb | -0.166 |
unda | -0.165 |
disadvant | -0.164 |
lift | -0.164 |
Token | � |
Token ID | 564 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
berry | +0.426 |
ythm | +0.371 |
worm | +0.367 |
enne | +0.366 |
ilateral | +0.365 |
Neg logit contributions | |
destro | -0.344 |
Dumb | -0.323 |
unda | -0.322 |
disadvant | -0.320 |
lift | -0.320 |
Token | � |
Token ID | 250 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
berry | +0.590 |
ythm | +0.509 |
worm | +0.500 |
enne | +0.500 |
ilateral | +0.498 |
Neg logit contributions | |
destro | -0.584 |
Dumb | -0.554 |
unda | -0.550 |
disadvant | -0.548 |
lift | -0.547 |
Token | Har |
Token ID | 13587 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
berry | +1.195 |
ythm | +1.026 |
worm | +1.012 |
ilateral | +1.010 |
enne | +1.009 |
Neg logit contributions | |
destro | -1.224 |
Dumb | -1.159 |
disadvant | -1.150 |
unda | -1.149 |
lift | -1.145 |
Token | lem |
Token ID | 10671 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
destro | +2.075 |
Dumb | +1.964 |
unda | +1.955 |
lift | +1.934 |
disadvant | +1.932 |
Neg logit contributions | |
berry | -2.574 |
ythm | -2.263 |
ilateral | -2.228 |
enne | -2.222 |
worm | -2.222 |
Token | Shake |
Token ID | 41113 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
destro | +1.323 |
Dumb | +1.254 |
unda | +1.236 |
disadvant | +1.226 |
lift | +1.220 |
Neg logit contributions | |
berry | -1.884 |
ythm | -1.669 |
enne | -1.644 |
worm | -1.644 |
ilateral | -1.642 |
Token | � |
Token ID | 447 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
destro | +0.731 |
Dumb | +0.691 |
unda | +0.685 |
disadvant | +0.682 |
lift | +0.681 |
Neg logit contributions | |
berry | -0.856 |
ythm | -0.747 |
worm | -0.735 |
enne | -0.735 |
ilateral | -0.733 |
Token | � |
Token ID | 251 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
destro | +0.046 |
Dumb | +0.044 |
unda | +0.044 |
lift | +0.043 |
disadvant | +0.043 |
Neg logit contributions | |
berry | -0.045 |
ythm | -0.039 |
worm | -0.038 |
enne | -0.038 |
ilateral | -0.038 |
Token | bl |
Token ID | 698 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
berry | +1.568 |
ythm | +1.350 |
worm | +1.343 |
ilateral | +1.332 |
enne | +1.327 |
Neg logit contributions | |
destro | -1.410 |
Dumb | -1.337 |
disadvant | -1.335 |
unda | -1.325 |
newsp | -1.319 |
Token | ares |
Token ID | 3565 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
berry | +2.196 |
ythm | +1.890 |
ilateral | +1.868 |
worm | +1.857 |
enne | +1.854 |
Neg logit contributions | |
destro | -2.247 |
disadvant | -2.131 |
Dumb | -2.129 |
newsp | -2.121 |
lift | -2.088 |
Token | in |
Token ID | 287 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
destro | +2.985 |
Dumb | +2.863 |
lift | +2.808 |
unda | +2.797 |
disadvant | +2.791 |
Neg logit contributions | |
berry | -3.537 |
ythm | -3.157 |
ilateral | -3.105 |
enne | -3.099 |
worm | -3.056 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
berry | +0.667 |
ythm | +0.570 |
worm | +0.562 |
enne | +0.559 |
ilateral | +0.557 |
Neg logit contributions | |
destro | -0.673 |
unda | -0.635 |
Dumb | -0.632 |
newsp | -0.626 |
lift | -0.625 |
Token | many |
Token ID | 867 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
berry | +0.055 |
ythm | +0.048 |
worm | +0.047 |
ilateral | +0.047 |
enne | +0.047 |
Neg logit contributions | |
destro | -0.044 |
Dumb | -0.041 |
unda | -0.041 |
lift | -0.041 |
disadvant | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
berry | +0.098 |
ythm | +0.085 |
worm | +0.084 |
enne | +0.083 |
ilateral | +0.083 |
Neg logit contributions | |
destro | -0.093 |
Dumb | -0.088 |
unda | -0.088 |
lift | -0.087 |
newsp | -0.087 |
Token | which |
Token ID | 543 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
destro | +1.119 |
Dumb | +1.050 |
unda | +1.037 |
disadvant | +1.035 |
lift | +1.032 |
Neg logit contributions | |
berry | -1.731 |
ythm | -1.537 |
worm | -1.515 |
enne | -1.514 |
ilateral | -1.512 |
Token | are |
Token ID | 389 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
destro | +1.669 |
Dumb | +1.584 |
disadvant | +1.565 |
unda | +1.554 |
lift | +1.553 |
Neg logit contributions | |
berry | -1.936 |
ythm | -1.704 |
worm | -1.666 |
enne | -1.665 |
ilateral | -1.665 |
Token | mentioned |
Token ID | 4750 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
berry | +0.022 |
ythm | +0.020 |
worm | +0.019 |
enne | +0.019 |
ilateral | +0.019 |
Neg logit contributions | |
destro | -0.016 |
Dumb | -0.015 |
unda | -0.015 |
lift | -0.015 |
newsp | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
berry | +2.309 |
ythm | +1.966 |
worm | +1.952 |
enne | +1.939 |
ilateral | +1.930 |
Neg logit contributions | |
destro | -2.294 |
Dumb | -2.157 |
unda | -2.154 |
disadvant | -2.128 |
newsp | -2.127 |
Token | this |
Token ID | 428 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
destro | +0.764 |
Dumb | +0.723 |
unda | +0.716 |
disadvant | +0.713 |
lift | +0.712 |
Neg logit contributions | |
berry | -0.912 |
ythm | -0.797 |
worm | -0.785 |
enne | -0.784 |
ilateral | -0.781 |
Token | column |
Token ID | 5721 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
destro | +0.514 |
Dumb | +0.477 |
unda | +0.474 |
disadvant | +0.473 |
lift | +0.471 |
Neg logit contributions | |
berry | -0.832 |
ythm | -0.736 |
worm | -0.727 |
enne | -0.727 |
ilateral | -0.725 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
berry | +0.028 |
ythm | +0.024 |
worm | +0.024 |
enne | +0.024 |
ilateral | +0.024 |
Neg logit contributions | |
destro | -0.027 |
Dumb | -0.026 |
unda | -0.025 |
disadvant | -0.025 |
lift | -0.025 |
Token | Autom |
Token ID | 17406 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
berry | +0.761 |
ythm | +0.659 |
worm | +0.648 |
enne | +0.647 |
ilateral | +0.644 |
Neg logit contributions | |
destro | -0.681 |
unda | -0.634 |
disadvant | -0.634 |
Dumb | -0.630 |
newsp | -0.630 |
Token | my |
Token ID | 616 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
berry | +0.208 |
ythm | +0.180 |
worm | +0.178 |
enne | +0.178 |
ilateral | +0.177 |
Neg logit contributions | |
destro | -0.178 |
Dumb | -0.168 |
unda | -0.167 |
disadvant | -0.166 |
lift | -0.166 |
Token | main |
Token ID | 1388 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
destro | +0.090 |
Dumb | +0.085 |
unda | +0.085 |
disadvant | +0.084 |
lift | +0.084 |
Neg logit contributions | |
berry | -0.120 |
ythm | -0.105 |
worm | -0.104 |
enne | -0.103 |
ilateral | -0.103 |
Token | speakers |
Token ID | 11636 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
destro | +0.360 |
Dumb | +0.340 |
unda | +0.337 |
disadvant | +0.336 |
lift | +0.335 |
Neg logit contributions | |
berry | -0.420 |
ythm | -0.366 |
worm | -0.360 |
enne | -0.360 |
ilateral | -0.359 |
Token | . |
Token ID | 13 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
berry | +1.063 |
ythm | +0.914 |
worm | +0.900 |
enne | +0.898 |
ilateral | +0.895 |
Neg logit contributions | |
destro | -1.033 |
Dumb | -0.976 |
unda | -0.973 |
disadvant | -0.968 |
newsp | -0.963 |
Token | To |
Token ID | 1675 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
berry | +1.399 |
ythm | +1.202 |
worm | +1.181 |
enne | +1.178 |
ilateral | +1.166 |
Neg logit contributions | |
destro | -1.338 |
disadvant | -1.249 |
unda | -1.245 |
newsp | -1.237 |
Dumb | -1.221 |
Token | make |
Token ID | 787 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
berry | +1.000 |
ythm | +0.872 |
enne | +0.862 |
worm | +0.857 |
ilateral | +0.855 |
Neg logit contributions | |
destro | -0.818 |
disadvant | -0.770 |
Dumb | -0.769 |
unda | -0.767 |
lift | -0.762 |
Token | a |
Token ID | 257 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
berry | +1.541 |
ythm | +1.319 |
worm | +1.303 |
enne | +1.303 |
ilateral | +1.298 |
Neg logit contributions | |
destro | -1.566 |
unda | -1.480 |
Dumb | -1.470 |
disadvant | -1.468 |
lift | -1.458 |
Token | long |
Token ID | 890 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
destro | +0.138 |
Dumb | +0.129 |
unda | +0.129 |
disadvant | +0.128 |
lift | +0.128 |
Neg logit contributions | |
berry | -0.193 |
ythm | -0.169 |
worm | -0.167 |
enne | -0.167 |
ilateral | -0.166 |
Token | story |
Token ID | 1621 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
destro | +1.222 |
Dumb | +1.147 |
unda | +1.131 |
lift | +1.128 |
disadvant | +1.127 |
Neg logit contributions | |
berry | -1.876 |
ythm | -1.669 |
enne | -1.644 |
worm | -1.639 |
ilateral | -1.639 |
Token | short |
Token ID | 1790 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
berry | +0.912 |
ythm | +0.764 |
worm | +0.760 |
ilateral | +0.756 |
autical | +0.747 |
Neg logit contributions | |
destro | -1.073 |
Dumb | -1.012 |
unda | -1.008 |
disadvant | -1.007 |
lift | -1.005 |
Token | I |
Token ID | 314 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
destro | +0.853 |
Dumb | +0.811 |
unda | +0.803 |
disadvant | +0.800 |
lift | +0.800 |
Neg logit contributions | |
berry | -0.891 |
ythm | -0.773 |
worm | -0.759 |
enne | -0.758 |
ilateral | -0.757 |
Token | philanthrop |
Token ID | 28150 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
destro | +1.017 |
Dumb | +0.955 |
unda | +0.944 |
disadvant | +0.940 |
lift | +0.939 |
Neg logit contributions | |
berry | -1.474 |
ythm | -1.306 |
worm | -1.287 |
enne | -1.287 |
ilateral | -1.282 |
Token | ist |
Token ID | 396 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
destro | +0.539 |
unda | +0.515 |
Dumb | +0.515 |
lift | +0.512 |
disadvant | +0.510 |
Neg logit contributions | |
berry | -0.401 |
ythm | -0.335 |
enne | -0.327 |
worm | -0.327 |
ilateral | -0.326 |
Token | Herbert |
Token ID | 28648 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
destro | +1.367 |
Dumb | +1.293 |
unda | +1.278 |
disadvant | +1.273 |
lift | +1.271 |
Neg logit contributions | |
berry | -1.774 |
ythm | -1.558 |
worm | -1.535 |
enne | -1.534 |
ilateral | -1.531 |
Token | Hale |
Token ID | 35056 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
destro | +0.483 |
Dumb | +0.452 |
unda | +0.450 |
disadvant | +0.449 |
lift | +0.447 |
Neg logit contributions | |
berry | -0.602 |
ythm | -0.527 |
worm | -0.519 |
enne | -0.518 |
ilateral | -0.518 |
Token | Williams |
Token ID | 6484 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
berry | +1.335 |
ythm | +1.143 |
worm | +1.126 |
enne | +1.126 |
hod | +1.117 |
Neg logit contributions | |
destro | -1.289 |
Dumb | -1.209 |
disadvant | -1.207 |
unda | -1.203 |
newsp | -1.202 |
Token | , |
Token ID | 11 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
berry | +1.365 |
ythm | +1.158 |
worm | +1.141 |
enne | +1.135 |
ilateral | +1.134 |
Neg logit contributions | |
destro | -1.405 |
unda | -1.319 |
Dumb | -1.319 |
disadvant | -1.318 |
newsp | -1.311 |
Token | who |
Token ID | 508 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
berry | +0.090 |
ythm | +0.078 |
worm | +0.077 |
enne | +0.077 |
ilateral | +0.077 |
Neg logit contributions | |
destro | -0.073 |
Dumb | -0.069 |
unda | -0.069 |
lift | -0.068 |
disadvant | -0.068 |
Token | is |
Token ID | 318 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
berry | +0.819 |
ythm | +0.706 |
worm | +0.698 |
enne | +0.695 |
ilateral | +0.694 |
Neg logit contributions | |
destro | -0.718 |
Dumb | -0.678 |
unda | -0.675 |
disadvant | -0.672 |
lift | -0.670 |
Token | better |
Token ID | 1365 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
berry | +0.305 |
ythm | +0.266 |
worm | +0.263 |
enne | +0.262 |
ilateral | +0.262 |
Neg logit contributions | |
destro | -0.247 |
Dumb | -0.232 |
unda | -0.231 |
lift | -0.230 |
disadvant | -0.229 |
Token | known |
Token ID | 1900 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
destro | +0.631 |
Dumb | +0.593 |
unda | +0.588 |
disadvant | +0.585 |
lift | +0.583 |
Neg logit contributions | |
berry | -0.873 |
ythm | -0.771 |
worm | -0.759 |
enne | -0.759 |
ilateral | -0.758 |
Token | for |
Token ID | 329 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
berry | +0.143 |
ythm | +0.124 |
enne | +0.122 |
worm | +0.122 |
ilateral | +0.121 |
Neg logit contributions | |
destro | -0.133 |
Dumb | -0.126 |
unda | -0.125 |
disadvant | -0.125 |
newsp | -0.124 |
Token | goes |
Token ID | 2925 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
destro | +0.121 |
Dumb | +0.114 |
unda | +0.113 |
disadvant | +0.113 |
lift | +0.113 |
Neg logit contributions | |
berry | -0.133 |
ythm | -0.115 |
worm | -0.113 |
enne | -0.113 |
ilateral | -0.113 |
Token | acidic |
Token ID | 42987 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
destro | +0.464 |
Dumb | +0.439 |
unda | +0.436 |
disadvant | +0.434 |
lift | +0.433 |
Neg logit contributions | |
berry | -0.531 |
ythm | -0.463 |
worm | -0.455 |
enne | -0.455 |
ilateral | -0.454 |
Token | . |
Token ID | 13 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
berry | +2.474 |
worm | +2.067 |
ythm | +2.064 |
enne | +2.037 |
autical | +2.022 |
Neg logit contributions | |
destro | -2.391 |
Dumb | -2.258 |
newsp | -2.238 |
unda | -2.232 |
lift | -2.226 |
Token |
|
Token ID | 198 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
berry | +0.775 |
ythm | +0.670 |
worm | +0.661 |
enne | +0.658 |
autical | +0.652 |
Neg logit contributions | |
destro | -0.670 |
disadvant | -0.621 |
unda | -0.620 |
newsp | -0.617 |
Dumb | -0.610 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
berry | +0.087 |
ythm | +0.075 |
worm | +0.074 |
enne | +0.074 |
ilateral | +0.074 |
Neg logit contributions | |
destro | -0.085 |
Dumb | -0.081 |
unda | -0.080 |
disadvant | -0.080 |
lift | -0.080 |
Token | And |
Token ID | 1870 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
berry | +0.900 |
ythm | +0.777 |
worm | +0.769 |
enne | +0.764 |
ilateral | +0.760 |
Neg logit contributions | |
destro | -0.820 |
Dumb | -0.762 |
disadvant | -0.760 |
newsp | -0.757 |
unda | -0.757 |
Token | ers |
Token ID | 364 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
berry | +0.038 |
ythm | +0.033 |
worm | +0.033 |
enne | +0.033 |
ilateral | +0.032 |
Neg logit contributions | |
destro | -0.035 |
Dumb | -0.033 |
unda | -0.032 |
disadvant | -0.032 |
newsp | -0.032 |
Token | 's |
Token ID | 338 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
destro | +0.421 |
Dumb | +0.397 |
unda | +0.394 |
disadvant | +0.392 |
lift | +0.391 |
Neg logit contributions | |
berry | -0.502 |
ythm | -0.439 |
worm | -0.432 |
enne | -0.431 |
ilateral | -0.431 |
Token | hop |
Token ID | 1725 |
Feature activation | +7.95e-03 |
Pos logit contributions | |
destro | +0.266 |
Dumb | +0.249 |
unda | +0.249 |
disadvant | +0.247 |
lift | +0.247 |
Neg logit contributions | |
berry | -0.362 |
ythm | -0.317 |
worm | -0.314 |
enne | -0.312 |
ilateral | -0.311 |
Token | garden |
Token ID | 11376 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
destro | +0.019 |
Dumb | +0.018 |
unda | +0.018 |
disadvant | +0.018 |
lift | +0.018 |
Neg logit contributions | |
berry | -0.020 |
ythm | -0.018 |
worm | -0.017 |
enne | -0.017 |
ilateral | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
berry | +0.245 |
ythm | +0.212 |
worm | +0.210 |
enne | +0.209 |
ilateral | +0.208 |
Neg logit contributions | |
destro | -0.216 |
Dumb | -0.205 |
unda | -0.203 |
disadvant | -0.202 |
lift | -0.202 |
Token | C |
Token ID | 327 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
destro | +0.992 |
Dumb | +0.942 |
unda | +0.935 |
disadvant | +0.932 |
lift | +0.929 |
Neg logit contributions | |
berry | -1.004 |
ythm | -0.866 |
worm | -0.852 |
enne | -0.851 |
ilateral | -0.849 |
Token | iti |
Token ID | 8846 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
berry | +0.673 |
ythm | +0.541 |
ilateral | +0.535 |
enne | +0.527 |
worm | +0.523 |
Neg logit contributions | |
destro | -1.167 |
Dumb | -1.112 |
lift | -1.109 |
disadvant | -1.108 |
newsp | -1.098 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
berry | +0.165 |
ythm | +0.143 |
enne | +0.140 |
worm | +0.140 |
ilateral | +0.140 |
Neg logit contributions | |
destro | -0.158 |
Dumb | -0.149 |
unda | -0.148 |
disadvant | -0.147 |
lift | -0.147 |
Token | Chase |
Token ID | 16346 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
destro | +0.057 |
Dumb | +0.053 |
unda | +0.053 |
disadvant | +0.053 |
lift | +0.053 |
Neg logit contributions | |
berry | -0.060 |
ythm | -0.052 |
worm | -0.051 |
enne | -0.051 |
ilateral | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
berry | +1.357 |
ythm | +1.163 |
worm | +1.142 |
enne | +1.140 |
ilateral | +1.140 |
Neg logit contributions | |
destro | -1.313 |
Dumb | -1.235 |
unda | -1.231 |
disadvant | -1.226 |
lift | -1.225 |
Token | Wells |
Token ID | 18292 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
berry | +0.069 |
ythm | +0.060 |
worm | +0.059 |
ilateral | +0.058 |
enne | +0.058 |
Neg logit contributions | |
destro | -0.066 |
Dumb | -0.062 |
unda | -0.061 |
disadvant | -0.061 |
newsp | -0.061 |
Token | Fargo |
Token ID | 28125 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
berry | +1.735 |
ythm | +1.531 |
ilateral | +1.509 |
enne | +1.504 |
worm | +1.500 |
Neg logit contributions | |
destro | -1.067 |
newsp | -0.953 |
disadvant | -0.953 |
unda | -0.951 |
Dumb | -0.939 |
Token | , |
Token ID | 11 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
destro | +0.321 |
Dumb | +0.305 |
unda | +0.302 |
disadvant | +0.301 |
lift | +0.300 |
Neg logit contributions | |
berry | -0.341 |
ythm | -0.296 |
worm | -0.291 |
enne | -0.291 |
ilateral | -0.290 |
Token | and |
Token ID | 290 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
destro | +0.220 |
Dumb | +0.207 |
unda | +0.206 |
disadvant | +0.205 |
newsp | +0.205 |
Neg logit contributions | |
berry | -0.235 |
ythm | -0.204 |
worm | -0.200 |
ilateral | -0.200 |
enne | -0.200 |
Token | Ally |
Token ID | 43039 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
berry | +1.368 |
ythm | +1.189 |
ilateral | +1.160 |
enne | +1.154 |
worm | +1.154 |
Neg logit contributions | |
destro | -1.269 |
unda | -1.181 |
newsp | -1.174 |
Dumb | -1.171 |
disadvant | -1.171 |
Token | Bank |
Token ID | 5018 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
berry | +0.526 |
ythm | +0.454 |
ilateral | +0.450 |
enne | +0.447 |
worm | +0.445 |
Neg logit contributions | |
destro | -0.445 |
unda | -0.416 |
Dumb | -0.416 |
lift | -0.414 |
disadvant | -0.413 |
Token | and |
Token ID | 290 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
destro | +0.403 |
Dumb | +0.381 |
unda | +0.378 |
disadvant | +0.377 |
lift | +0.376 |
Neg logit contributions | |
berry | -0.451 |
ythm | -0.393 |
worm | -0.386 |
enne | -0.386 |
ilateral | -0.385 |
Token | make |
Token ID | 787 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
destro | +0.345 |
Dumb | +0.326 |
unda | +0.324 |
disadvant | +0.323 |
lift | +0.322 |
Neg logit contributions | |
berry | -0.391 |
ythm | -0.340 |
worm | -0.335 |
enne | -0.334 |
ilateral | -0.334 |
Token | sure |
Token ID | 1654 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
berry | +1.273 |
ythm | +1.100 |
ilateral | +1.095 |
worm | +1.093 |
enne | +1.083 |
Neg logit contributions | |
destro | -1.111 |
Dumb | -1.035 |
unda | -1.032 |
disadvant | -1.030 |
newsp | -1.023 |
Token | the |
Token ID | 262 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
destro | +0.697 |
Dumb | +0.660 |
unda | +0.655 |
disadvant | +0.652 |
lift | +0.651 |
Neg logit contributions | |
berry | -0.779 |
ythm | -0.678 |
worm | -0.667 |
enne | -0.666 |
ilateral | -0.664 |
Token | Air |
Token ID | 3701 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
destro | +0.860 |
Dumb | +0.809 |
unda | +0.803 |
disadvant | +0.801 |
lift | +0.798 |
Neg logit contributions | |
berry | -1.061 |
ythm | -0.927 |
worm | -0.915 |
enne | -0.913 |
ilateral | -0.911 |
Token | Force |
Token ID | 5221 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
berry | +0.692 |
ythm | +0.584 |
worm | +0.577 |
enne | +0.574 |
ilateral | +0.570 |
Neg logit contributions | |
destro | -0.790 |
Dumb | -0.745 |
unda | -0.745 |
disadvant | -0.744 |
newsp | -0.740 |
Token | has |
Token ID | 468 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
berry | +3.363 |
worm | +2.862 |
autical | +2.842 |
ythm | +2.819 |
ilateral | +2.815 |
Neg logit contributions | |
destro | -3.217 |
unda | -3.093 |
disadvant | -3.069 |
Dumb | -3.056 |
newsp | -3.047 |
Token | 1 |
Token ID | 352 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
destro | +0.259 |
Dumb | +0.244 |
unda | +0.242 |
disadvant | +0.241 |
lift | +0.241 |
Neg logit contributions | |
berry | -0.321 |
ythm | -0.280 |
worm | -0.277 |
enne | -0.276 |
ilateral | -0.276 |
Token | , |
Token ID | 11 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
destro | +0.107 |
Dumb | +0.102 |
unda | +0.101 |
disadvant | +0.100 |
lift | +0.100 |
Neg logit contributions | |
berry | -0.114 |
ythm | -0.098 |
worm | -0.097 |
enne | -0.097 |
ilateral | -0.096 |
Token | 200 |
Token ID | 2167 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
destro | +1.280 |
Dumb | +1.233 |
unda | +1.220 |
lift | +1.216 |
practise | +1.196 |
Neg logit contributions | |
berry | -1.206 |
ythm | -1.039 |
enne | -1.026 |
worm | -1.021 |
ilateral | -1.017 |
Token | fighter |
Token ID | 10543 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
destro | +0.257 |
Dumb | +0.241 |
unda | +0.241 |
disadvant | +0.240 |
lift | +0.238 |
Neg logit contributions | |
berry | -0.325 |
ythm | -0.284 |
worm | -0.281 |
enne | -0.281 |
ilateral | -0.279 |
Token | A |
Token ID | 317 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
destro | +1.548 |
Dumb | +1.482 |
unda | +1.455 |
disadvant | +1.450 |
lift | +1.445 |
Neg logit contributions | |
berry | -1.700 |
ythm | -1.495 |
worm | -1.459 |
enne | -1.459 |
autical | -1.454 |
Token | three |
Token ID | 1115 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
destro | +0.201 |
Dumb | +0.191 |
unda | +0.190 |
disadvant | +0.189 |
lift | +0.189 |
Neg logit contributions | |
berry | -0.205 |
ythm | -0.176 |
enne | -0.173 |
worm | -0.173 |
ilateral | -0.173 |
Token | - |
Token ID | 12 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
destro | +1.023 |
Dumb | +0.978 |
unda | +0.970 |
disadvant | +0.967 |
lift | +0.967 |
Neg logit contributions | |
berry | -0.850 |
ythm | -0.732 |
enne | -0.714 |
worm | -0.713 |
ilateral | -0.708 |
Token | year |
Token ID | 1941 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
berry | +1.422 |
worm | +1.239 |
ythm | +1.239 |
ilateral | +1.234 |
enne | +1.228 |
Neg logit contributions | |
destro | -1.006 |
Dumb | -0.936 |
disadvant | -0.931 |
newsp | -0.930 |
unda | -0.928 |
Token | , |
Token ID | 11 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
berry | +2.375 |
worm | +1.976 |
ilateral | +1.972 |
enne | +1.937 |
ythm | +1.937 |
Neg logit contributions | |
destro | -2.637 |
unda | -2.507 |
disadvant | -2.496 |
lift | -2.470 |
Dumb | -2.469 |
Token | $ |
Token ID | 720 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
berry | +0.905 |
ythm | +0.772 |
worm | +0.768 |
ilateral | +0.768 |
enne | +0.765 |
Neg logit contributions | |
destro | -0.855 |
Dumb | -0.803 |
unda | -0.801 |
disadvant | -0.801 |
lift | -0.796 |
Token | 15 |
Token ID | 1314 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
berry | +2.807 |
ythm | +2.300 |
worm | +2.292 |
enne | +2.261 |
yth | +2.255 |
Neg logit contributions | |
destro | -3.721 |
disadvant | -3.482 |
newsp | -3.462 |
Dumb | -3.349 |
unda | -3.343 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
destro | +1.492 |
Dumb | +1.409 |
unda | +1.386 |
lift | +1.384 |
disadvant | +1.384 |
Neg logit contributions | |
berry | -2.040 |
ythm | -1.820 |
enne | -1.787 |
worm | -1.776 |
ilateral | -1.770 |
Token | 75 |
Token ID | 2425 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
destro | +0.593 |
Dumb | +0.575 |
lift | +0.570 |
unda | +0.570 |
disadvant | +0.562 |
Neg logit contributions | |
berry | -0.416 |
ythm | -0.350 |
ilateral | -0.342 |
enne | -0.341 |
worm | -0.341 |
Token | million |
Token ID | 1510 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
destro | +0.187 |
Dumb | +0.174 |
unda | +0.172 |
disadvant | +0.171 |
lift | +0.171 |
Neg logit contributions | |
berry | -0.326 |
ythm | -0.291 |
worm | -0.287 |
enne | -0.287 |
ilateral | -0.286 |
Token | contract |
Token ID | 2775 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
destro | +1.880 |
Dumb | +1.789 |
unda | +1.773 |
disadvant | +1.768 |
lift | +1.766 |
Neg logit contributions | |
berry | -1.835 |
ythm | -1.596 |
enne | -1.557 |
worm | -1.557 |
ilateral | -1.550 |
Token | his |
Token ID | 465 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
berry | +0.239 |
ythm | +0.206 |
enne | +0.204 |
ilateral | +0.204 |
worm | +0.203 |
Neg logit contributions | |
destro | -0.217 |
Dumb | -0.201 |
unda | -0.201 |
lift | -0.201 |
disadvant | -0.201 |
Token | address |
Token ID | 2209 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
destro | +0.295 |
Dumb | +0.274 |
lift | +0.273 |
disadvant | +0.273 |
unda | +0.272 |
Neg logit contributions | |
berry | -0.401 |
ythm | -0.351 |
enne | -0.348 |
ilateral | -0.347 |
worm | -0.346 |
Token | to |
Token ID | 284 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
berry | +1.310 |
ythm | +1.130 |
enne | +1.117 |
worm | +1.115 |
ilateral | +1.113 |
Neg logit contributions | |
destro | -1.237 |
Dumb | -1.163 |
unda | -1.153 |
disadvant | -1.151 |
lift | -1.149 |
Token | the |
Token ID | 262 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
destro | +0.062 |
Dumb | +0.058 |
disadvant | +0.058 |
unda | +0.058 |
lift | +0.058 |
Neg logit contributions | |
berry | -0.071 |
ythm | -0.062 |
ilateral | -0.061 |
enne | -0.061 |
worm | -0.061 |
Token | Liberal |
Token ID | 12266 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
berry | +0.790 |
ythm | +0.692 |
ilateral | +0.686 |
enne | +0.686 |
worm | +0.682 |
Neg logit contributions | |
destro | -0.582 |
lift | -0.541 |
disadvant | -0.536 |
Dumb | -0.535 |
unda | -0.532 |
Token | convention |
Token ID | 9831 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
destro | +0.871 |
Dumb | +0.822 |
unda | +0.816 |
disadvant | +0.810 |
newsp | +0.807 |
Neg logit contributions | |
berry | -1.228 |
ythm | -1.085 |
worm | -1.067 |
enne | -1.066 |
ilateral | -1.063 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
berry | +3.821 |
enne | +3.253 |
ythm | +3.192 |
worm | +3.174 |
ilateral | +3.168 |
Neg logit contributions | |
destro | -4.300 |
Dumb | -3.997 |
disadvant | -3.973 |
lift | -3.972 |
newsp | -3.941 |
Token | Ign |
Token ID | 16583 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
berry | +0.329 |
ythm | +0.287 |
enne | +0.284 |
ilateral | +0.284 |
worm | +0.283 |
Neg logit contributions | |
destro | -0.272 |
Dumb | -0.254 |
unda | -0.253 |
lift | -0.253 |
disadvant | -0.252 |
Token | at |
Token ID | 265 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
berry | +0.039 |
ythm | +0.032 |
worm | +0.031 |
enne | +0.031 |
ilateral | +0.031 |
Neg logit contributions | |
destro | -0.064 |
Dumb | -0.062 |
unda | -0.061 |
lift | -0.061 |
disadvant | -0.061 |
Token | ie |
Token ID | 494 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
destro | +0.257 |
Dumb | +0.238 |
unda | +0.235 |
disadvant | +0.235 |
newsp | +0.233 |
Neg logit contributions | |
berry | -0.423 |
ythm | -0.376 |
worm | -0.371 |
enne | -0.371 |
ilateral | -0.370 |
Token | ff |
Token ID | 487 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
berry | +0.533 |
ythm | +0.340 |
enne | +0.327 |
worm | +0.324 |
ilateral | +0.315 |
Neg logit contributions | |
destro | -2.133 |
Dumb | -2.040 |
disadvant | -2.040 |
newsp | -2.037 |
unda | -2.024 |
Token | T |
Token ID | 309 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
berry | +0.410 |
ythm | +0.358 |
worm | +0.353 |
enne | +0.353 |
ilateral | +0.352 |
Neg logit contributions | |
destro | -0.328 |
Dumb | -0.308 |
unda | -0.306 |
disadvant | -0.305 |
lift | -0.304 |
Token | Z |
Token ID | 57 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
berry | +0.858 |
ythm | +0.742 |
worm | +0.728 |
enne | +0.727 |
ilateral | +0.727 |
Neg logit contributions | |
destro | -0.838 |
Dumb | -0.790 |
disadvant | -0.782 |
lift | -0.780 |
newsp | -0.778 |
Token | , |
Token ID | 11 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
berry | +1.447 |
ythm | +1.251 |
enne | +1.233 |
worm | +1.230 |
ilateral | +1.227 |
Neg logit contributions | |
destro | -1.349 |
Dumb | -1.274 |
unda | -1.264 |
disadvant | -1.262 |
lift | -1.259 |
Token | Reuters |
Token ID | 8428 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
berry | +0.961 |
ythm | +0.831 |
worm | +0.819 |
ilateral | +0.818 |
enne | +0.818 |
Neg logit contributions | |
destro | -0.823 |
unda | -0.772 |
disadvant | -0.769 |
Dumb | -0.769 |
lift | -0.767 |
Token | , |
Token ID | 11 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
berry | +2.377 |
ythm | +2.024 |
enne | +2.019 |
ilateral | +2.003 |
worm | +1.994 |
Neg logit contributions | |
destro | -2.368 |
disadvant | -2.234 |
Dumb | -2.234 |
unda | -2.226 |
lift | -2.218 |
Token | Times |
Token ID | 3782 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
destro | +0.075 |
Dumb | +0.071 |
unda | +0.070 |
disadvant | +0.070 |
lift | +0.070 |
Neg logit contributions | |
berry | -0.088 |
ythm | -0.076 |
worm | -0.075 |
enne | -0.075 |
ilateral | -0.075 |
Token | of |
Token ID | 286 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
berry | +3.568 |
ilateral | +2.987 |
ythm | +2.957 |
worm | +2.949 |
enne | +2.929 |
Neg logit contributions | |
destro | -3.808 |
disadvant | -3.615 |
unda | -3.595 |
Dumb | -3.575 |
lift | -3.550 |
Token | Israel |
Token ID | 2692 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
berry | +0.438 |
ythm | +0.372 |
ilateral | +0.366 |
enne | +0.364 |
worm | +0.361 |
Neg logit contributions | |
destro | -0.546 |
disadvant | -0.510 |
unda | -0.510 |
newsp | -0.507 |
lift | -0.507 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
destro | +1.249 |
Dumb | +1.187 |
unda | +1.175 |
newsp | +1.173 |
lift | +1.168 |
Neg logit contributions | |
berry | -1.436 |
ythm | -1.253 |
worm | -1.232 |
ilateral | -1.228 |
enne | -1.226 |
Token | St |
Token ID | 1273 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
destro | +0.920 |
Dumb | +0.880 |
unda | +0.875 |
lift | +0.875 |
disadvant | +0.867 |
Neg logit contributions | |
berry | -1.019 |
ythm | -0.889 |
enne | -0.873 |
ilateral | -0.871 |
worm | -0.870 |
Token | ress |
Token ID | 601 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
destro | +2.381 |
Dumb | +2.307 |
unda | +2.301 |
lift | +2.271 |
disadvant | +2.263 |
Neg logit contributions | |
berry | -2.474 |
ythm | -2.140 |
worm | -2.120 |
ilateral | -2.095 |
autical | -2.091 |
Token | of |
Token ID | 286 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
berry | +0.459 |
ythm | +0.398 |
worm | +0.393 |
enne | +0.392 |
ilateral | +0.390 |
Neg logit contributions | |
destro | -0.420 |
Dumb | -0.397 |
unda | -0.394 |
disadvant | -0.393 |
lift | -0.391 |
Token | ranged |
Token ID | 17929 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
berry | +0.158 |
ythm | +0.137 |
worm | +0.136 |
enne | +0.135 |
ilateral | +0.135 |
Neg logit contributions | |
destro | -0.140 |
unda | -0.132 |
Dumb | -0.131 |
disadvant | -0.131 |
lift | -0.131 |
Token | attacks |
Token ID | 3434 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
destro | +0.410 |
Dumb | +0.386 |
unda | +0.383 |
disadvant | +0.381 |
lift | +0.380 |
Neg logit contributions | |
berry | -0.539 |
ythm | -0.473 |
worm | -0.467 |
enne | -0.466 |
ilateral | -0.465 |
Token | so |
Token ID | 523 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
destro | +0.495 |
Dumb | +0.468 |
unda | +0.466 |
newsp | +0.463 |
lift | +0.462 |
Neg logit contributions | |
berry | -0.532 |
ythm | -0.460 |
worm | -0.454 |
enne | -0.453 |
ilateral | -0.451 |
Token | folks |
Token ID | 7974 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
berry | +0.029 |
ythm | +0.025 |
worm | +0.025 |
enne | +0.025 |
ilateral | +0.024 |
Neg logit contributions | |
destro | -0.027 |
Dumb | -0.025 |
unda | -0.025 |
disadvant | -0.025 |
newsp | -0.025 |
Token | like |
Token ID | 588 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
berry | +1.255 |
ythm | +1.080 |
enne | +1.071 |
worm | +1.070 |
ilateral | +1.058 |
Neg logit contributions | |
destro | -1.174 |
Dumb | -1.109 |
unda | -1.106 |
newsp | -1.104 |
disadvant | -1.100 |
Token | Nick |
Token ID | 8047 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
berry | +3.237 |
enne | +2.803 |
worm | +2.799 |
ythm | +2.774 |
yth | +2.725 |
Neg logit contributions | |
destro | -2.863 |
unda | -2.731 |
newsp | -2.707 |
disadvant | -2.700 |
lift | -2.663 |
Token | Fury |
Token ID | 18427 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
berry | +0.424 |
ythm | +0.372 |
worm | +0.367 |
enne | +0.367 |
ilateral | +0.366 |
Neg logit contributions | |
destro | -0.322 |
Dumb | -0.302 |
unda | -0.301 |
disadvant | -0.300 |
lift | -0.298 |
Token | who |
Token ID | 508 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
berry | +0.991 |
ythm | +0.848 |
worm | +0.843 |
enne | +0.841 |
ilateral | +0.831 |
Neg logit contributions | |
destro | -0.944 |
Dumb | -0.892 |
unda | -0.889 |
newsp | -0.887 |
disadvant | -0.886 |
Token | see |
Token ID | 766 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
destro | +0.197 |
Dumb | +0.187 |
unda | +0.185 |
disadvant | +0.184 |
lift | +0.184 |
Neg logit contributions | |
berry | -0.231 |
ythm | -0.202 |
worm | -0.198 |
enne | -0.198 |
ilateral | -0.198 |
Token | through |
Token ID | 832 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
destro | +1.241 |
Dumb | +1.180 |
unda | +1.157 |
lift | +1.156 |
disadvant | +1.156 |
Neg logit contributions | |
berry | -1.531 |
ythm | -1.343 |
ilateral | -1.319 |
autical | -1.317 |
worm | -1.314 |