Token | wrap |
Token ID | 37150 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
IDER | +2.407 |
Random | +2.266 |
rl | +2.142 |
Rough | +2.093 |
acco | +2.093 |
Neg logit contributions | |
aciously | -2.313 |
prevail | -2.290 |
elia | -2.152 |
Nadu | -2.123 |
itions | -2.052 |
Token | ()) |
Token ID | 32865 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
IDER | +1.363 |
Random | +1.259 |
rl | +1.169 |
Rough | +1.165 |
ylum | +1.141 |
Neg logit contributions | |
aciously | -1.634 |
prevail | -1.602 |
elia | -1.522 |
Nadu | -1.510 |
itions | -1.466 |
Token | } |
Token ID | 1782 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
aciously | +3.628 |
prevail | +3.611 |
elia | +3.319 |
Nadu | +3.254 |
itions | +3.243 |
Neg logit contributions | |
IDER | -5.379 |
Random | -5.004 |
ylum | -4.817 |
rl | -4.747 |
acco | -4.747 |
Token | } |
Token ID | 1782 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
aciously | +1.889 |
prevail | +1.879 |
elia | +1.673 |
Nadu | +1.648 |
itions | +1.615 |
Neg logit contributions | |
IDER | -4.486 |
Random | -4.200 |
ylum | -4.050 |
rl | -4.033 |
acco | -4.021 |
Token | pub |
Token ID | 2240 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
aciously | +2.497 |
prevail | +2.459 |
elia | +2.253 |
Nadu | +2.227 |
itions | +2.189 |
Neg logit contributions | |
IDER | -3.945 |
Random | -3.680 |
ylum | -3.501 |
rl | -3.481 |
acco | -3.469 |
Token | fn |
Token ID | 24714 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
aciously | +5.914 |
prevail | +5.842 |
elia | +5.453 |
Nadu | +5.331 |
ged | +5.319 |
Neg logit contributions | |
IDER | -6.648 |
Random | -6.045 |
ylum | -5.856 |
asions | -5.722 |
rl | -5.683 |
Token | apply |
Token ID | 4174 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
prevail | +6.983 |
aciously | +6.686 |
ged | +5.838 |
Nadu | +5.738 |
ging | +5.717 |
Neg logit contributions | |
IDER | -11.274 |
Random | -10.243 |
ylum | -10.230 |
afort | -10.132 |
Rap | -10.003 |
Token | _ |
Token ID | 62 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
IDER | +0.240 |
Random | +0.221 |
acco | +0.209 |
ylum | +0.208 |
Rough | +0.208 |
Neg logit contributions | |
aciously | -0.230 |
prevail | -0.224 |
elia | -0.216 |
Nadu | -0.209 |
itions | -0.207 |
Token | move |
Token ID | 21084 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
aciously | +2.254 |
prevail | +2.159 |
elia | +2.022 |
Nadu | +1.948 |
ged | +1.921 |
Neg logit contributions | |
IDER | -4.349 |
Random | -4.075 |
Rough | -3.885 |
ylum | -3.867 |
rl | -3.865 |
Token | ( |
Token ID | 357 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
IDER | +2.570 |
Random | +2.420 |
rl | +2.274 |
Rough | +2.237 |
ylum | +2.159 |
Neg logit contributions | |
aciously | -3.212 |
prevail | -3.168 |
Nadu | -2.972 |
elia | -2.950 |
eness | -2.882 |
Token | & |
Token ID | 1222 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
aciously | +4.444 |
prevail | +4.379 |
elia | +4.131 |
Nadu | +4.062 |
itions | +4.027 |
Neg logit contributions | |
IDER | -4.616 |
Random | -4.170 |
ylum | -4.099 |
acco | -3.979 |
asions | -3.930 |
Token | Guard |
Token ID | 4932 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
prevail | +6.300 |
aciously | +6.208 |
Nadu | +5.904 |
ged | +5.814 |
elia | +5.754 |
Neg logit contributions | |
IDER | -7.067 |
Random | -6.312 |
acco | -6.239 |
afort | -6.233 |
asions | -6.200 |
Token | { |
Token ID | 1391 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
IDER | +0.532 |
Random | +0.500 |
rl | +0.474 |
Rough | +0.474 |
ylum | +0.470 |
Neg logit contributions | |
aciously | -0.344 |
prevail | -0.333 |
elia | -0.312 |
Nadu | -0.306 |
itions | -0.297 |
Token | ... |
Token ID | 2644 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
prevail | +5.007 |
aciously | +4.903 |
Nadu | +4.569 |
elia | +4.482 |
itions | +4.437 |
Neg logit contributions | |
IDER | -6.234 |
Random | -5.617 |
ylum | -5.473 |
acco | -5.465 |
asions | -5.460 |
Token | } |
Token ID | 1782 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
aciously | +2.140 |
prevail | +2.119 |
elia | +1.949 |
Nadu | +1.943 |
ged | +1.898 |
Neg logit contributions | |
IDER | -3.052 |
Random | -2.814 |
ylum | -2.693 |
rl | -2.687 |
acco | -2.674 |
Token | pub |
Token ID | 2240 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
aciously | +1.273 |
prevail | +1.260 |
elia | +1.161 |
Nadu | +1.156 |
itions | +1.126 |
Neg logit contributions | |
IDER | -1.668 |
Random | -1.557 |
rl | -1.466 |
acco | -1.465 |
ylum | -1.463 |
Token | fn |
Token ID | 24714 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
prevail | +5.425 |
aciously | +5.392 |
Nadu | +4.903 |
elia | +4.881 |
ged | +4.823 |
Neg logit contributions | |
IDER | -7.565 |
Random | -6.853 |
ylum | -6.708 |
asions | -6.660 |
acco | -6.582 |
Token | pin |
Token ID | 6757 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
prevail | +7.958 |
aciously | +7.610 |
Nadu | +6.871 |
ged | +6.870 |
ging | +6.842 |
Neg logit contributions | |
IDER | -9.398 |
Random | -8.441 |
ylum | -8.408 |
afort | -8.377 |
acco | -8.262 |
Token | () |
Token ID | 7499 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
aciously | +0.646 |
prevail | +0.631 |
elia | +0.601 |
Nadu | +0.592 |
itions | +0.580 |
Neg logit contributions | |
IDER | -0.606 |
Random | -0.559 |
rl | -0.523 |
Rough | -0.522 |
ylum | -0.516 |
Token | -> |
Token ID | 4613 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
aciously | +3.138 |
prevail | +3.106 |
elia | +2.944 |
Nadu | +2.883 |
itions | +2.870 |
Neg logit contributions | |
IDER | -2.616 |
Random | -2.358 |
ylum | -2.275 |
acco | -2.221 |
rl | -2.180 |
Token | Guard |
Token ID | 4932 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
aciously | +0.563 |
prevail | +0.554 |
elia | +0.520 |
Nadu | +0.515 |
itions | +0.505 |
Neg logit contributions | |
IDER | -0.612 |
Random | -0.563 |
rl | -0.531 |
ylum | -0.531 |
acco | -0.528 |
Token | ; |
Token ID | 2162 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
aciously | +0.728 |
prevail | +0.711 |
elia | +0.668 |
Nadu | +0.653 |
ged | +0.638 |
Neg logit contributions | |
IDER | -1.246 |
Random | -1.161 |
ylum | -1.130 |
rl | -1.118 |
acco | -1.118 |
Token | is |
Token ID | 318 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
prevail | +2.474 |
aciously | +2.444 |
elia | +2.246 |
ged | +2.238 |
ging | +2.207 |
Neg logit contributions | |
IDER | -2.711 |
Random | -2.522 |
rl | -2.387 |
asions | -2.359 |
acco | -2.318 |
Token | changed |
Token ID | 3421 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
aciously | +0.288 |
prevail | +0.284 |
elia | +0.265 |
Nadu | +0.260 |
ged | +0.257 |
Neg logit contributions | |
IDER | -0.300 |
Random | -0.278 |
rl | -0.261 |
Rough | -0.258 |
acco | -0.257 |
Token | to |
Token ID | 284 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
IDER | +1.695 |
Random | +1.577 |
rl | +1.484 |
Rough | +1.481 |
ylum | +1.466 |
Neg logit contributions | |
aciously | -1.543 |
prevail | -1.501 |
elia | -1.429 |
Nadu | -1.402 |
itions | -1.368 |
Token | substantially |
Token ID | 13788 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
IDER | +0.248 |
Random | +0.232 |
rl | +0.220 |
ylum | +0.218 |
Rough | +0.218 |
Neg logit contributions | |
aciously | -0.170 |
prevail | -0.168 |
elia | -0.154 |
Nadu | -0.152 |
itions | -0.149 |
Token | increase |
Token ID | 2620 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
IDER | +4.105 |
Random | +3.854 |
Rough | +3.667 |
rl | +3.640 |
ylum | +3.609 |
Neg logit contributions | |
aciously | -3.024 |
prevail | -2.897 |
elia | -2.787 |
Nadu | -2.718 |
itions | -2.643 |
Token | density |
Token ID | 12109 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
IDER | +1.937 |
Random | +1.801 |
rl | +1.694 |
Rough | +1.693 |
ylum | +1.675 |
Neg logit contributions | |
aciously | -1.742 |
prevail | -1.694 |
elia | -1.611 |
Nadu | -1.583 |
itions | -1.545 |
Token | . |
Token ID | 13 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
prevail | +7.037 |
aciously | +6.821 |
itions | +6.164 |
elia | +6.099 |
eness | +6.098 |
Neg logit contributions | |
IDER | -10.087 |
Random | -9.300 |
afort | -9.103 |
ylum | -8.936 |
arted | -8.912 |
Token | The |
Token ID | 383 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
aciously | +0.460 |
prevail | +0.457 |
elia | +0.431 |
Nadu | +0.429 |
ged | +0.419 |
Neg logit contributions | |
IDER | -0.519 |
Random | -0.482 |
acco | -0.457 |
ylum | -0.455 |
rl | -0.455 |
Token | second |
Token ID | 1218 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
aciously | +0.396 |
prevail | +0.391 |
elia | +0.364 |
Nadu | +0.358 |
itions | +0.351 |
Neg logit contributions | |
IDER | -0.555 |
Random | -0.520 |
rl | -0.494 |
ylum | -0.490 |
acco | -0.488 |
Token | proposal |
Token ID | 6961 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
IDER | +2.104 |
Random | +1.952 |
Rough | +1.837 |
rl | +1.834 |
ylum | +1.816 |
Neg logit contributions | |
aciously | -2.008 |
prevail | -1.947 |
elia | -1.856 |
Nadu | -1.828 |
itions | -1.785 |
Token | , |
Token ID | 11 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
aciously | +1.272 |
prevail | +1.255 |
elia | +1.180 |
Nadu | +1.159 |
ged | +1.151 |
Neg logit contributions | |
IDER | -1.350 |
Random | -1.245 |
rl | -1.168 |
Rough | -1.154 |
asions | -1.150 |
Token | state |
Token ID | 5219 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
aciously | +2.139 |
prevail | +2.010 |
elia | +1.988 |
ged | +1.908 |
ging | +1.855 |
Neg logit contributions | |
IDER | -4.337 |
Random | -3.949 |
Rough | -3.879 |
acco | -3.810 |
ylum | -3.808 |
Token | ); |
Token ID | 5619 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
IDER | +1.813 |
Random | +1.678 |
Rough | +1.559 |
rl | +1.559 |
ylum | +1.526 |
Neg logit contributions | |
aciously | -2.094 |
prevail | -2.033 |
elia | -1.943 |
Nadu | -1.921 |
itions | -1.865 |
Token | ... |
Token ID | 2644 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
prevail | +3.029 |
aciously | +2.962 |
elia | +2.720 |
Nadu | +2.712 |
itions | +2.708 |
Neg logit contributions | |
IDER | -4.362 |
Random | -3.975 |
ylum | -3.871 |
acco | -3.807 |
rl | -3.801 |
Token | } |
Token ID | 1782 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
prevail | +1.839 |
aciously | +1.836 |
elia | +1.647 |
Nadu | +1.608 |
itions | +1.596 |
Neg logit contributions | |
IDER | -3.769 |
Random | -3.505 |
ylum | -3.387 |
rl | -3.355 |
acco | -3.341 |
Token | pub |
Token ID | 2240 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
aciously | +1.603 |
prevail | +1.570 |
elia | +1.458 |
Nadu | +1.432 |
itions | +1.406 |
Neg logit contributions | |
IDER | -2.328 |
Random | -2.173 |
rl | -2.059 |
ylum | -2.056 |
acco | -2.043 |
Token | fn |
Token ID | 24714 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
aciously | +5.364 |
prevail | +5.287 |
elia | +5.003 |
Nadu | +4.866 |
ged | +4.838 |
Neg logit contributions | |
IDER | -5.648 |
Random | -5.156 |
ylum | -4.938 |
rl | -4.838 |
Rough | -4.828 |
Token | undo |
Token ID | 23981 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
prevail | +5.858 |
aciously | +5.612 |
ged | +4.825 |
Nadu | +4.794 |
ging | +4.650 |
Neg logit contributions | |
IDER | -11.545 |
Random | -10.588 |
ylum | -10.550 |
afort | -10.437 |
Rap | -10.381 |
Token | _ |
Token ID | 62 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
aciously | +1.417 |
prevail | +1.361 |
elia | +1.329 |
ged | +1.310 |
Nadu | +1.286 |
Neg logit contributions | |
IDER | -1.589 |
Random | -1.467 |
acco | -1.403 |
ylum | -1.400 |
Rough | -1.398 |
Token | move |
Token ID | 21084 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
aciously | +1.528 |
prevail | +1.399 |
elia | +1.352 |
ged | +1.341 |
ging | +1.283 |
Neg logit contributions | |
IDER | -3.884 |
Random | -3.604 |
Rough | -3.501 |
acco | -3.468 |
ylum | -3.442 |
Token | ( |
Token ID | 357 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
IDER | +2.271 |
Random | +2.114 |
rl | +1.974 |
Rough | +1.944 |
ylum | +1.884 |
Neg logit contributions | |
aciously | -2.845 |
prevail | -2.788 |
Nadu | -2.630 |
elia | -2.595 |
eness | -2.530 |
Token | & |
Token ID | 1222 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
aciously | +4.129 |
prevail | +4.046 |
elia | +3.848 |
Nadu | +3.788 |
itions | +3.720 |
Neg logit contributions | |
IDER | -3.779 |
Random | -3.470 |
ylum | -3.250 |
rl | -3.240 |
Rough | -3.237 |
Token | issue |
Token ID | 2071 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
aciously | +0.462 |
prevail | +0.454 |
elia | +0.422 |
Nadu | +0.421 |
eness | +0.410 |
Neg logit contributions | |
IDER | -0.544 |
Random | -0.502 |
rl | -0.479 |
acco | -0.474 |
Rough | -0.468 |
Token | independently |
Token ID | 14799 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
IDER | +2.794 |
Random | +2.608 |
Rough | +2.464 |
rl | +2.460 |
ylum | +2.443 |
Neg logit contributions | |
aciously | -2.278 |
prevail | -2.209 |
elia | -2.107 |
Nadu | -2.066 |
itions | -2.013 |
Token | , |
Token ID | 11 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
IDER | +1.926 |
Random | +1.798 |
rl | +1.705 |
Rough | +1.702 |
ylum | +1.688 |
Neg logit contributions | |
aciously | -1.535 |
prevail | -1.479 |
elia | -1.415 |
Nadu | -1.393 |
itions | -1.347 |
Token | perhaps |
Token ID | 3737 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
IDER | +0.956 |
Random | +0.890 |
rl | +0.836 |
Rough | +0.828 |
acco | +0.826 |
Neg logit contributions | |
aciously | -0.886 |
prevail | -0.871 |
elia | -0.813 |
Nadu | -0.806 |
itions | -0.788 |
Token | in |
Token ID | 287 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
IDER | +4.204 |
Random | +3.914 |
Rough | +3.698 |
rl | +3.670 |
ylum | +3.648 |
Neg logit contributions | |
aciously | -3.886 |
prevail | -3.765 |
elia | -3.616 |
Nadu | -3.539 |
itions | -3.467 |
Token | coordination |
Token ID | 19877 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
aciously | +0.597 |
prevail | +0.581 |
elia | +0.547 |
Nadu | +0.536 |
ged | +0.524 |
Neg logit contributions | |
IDER | -0.809 |
Random | -0.754 |
rl | -0.713 |
ylum | -0.707 |
Rough | -0.707 |
Token | with |
Token ID | 351 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
aciously | +7.184 |
prevail | +7.125 |
elia | +6.553 |
Nadu | +6.347 |
itions | +6.332 |
Neg logit contributions | |
IDER | -9.912 |
Random | -9.285 |
rl | -8.815 |
aders | -8.729 |
acco | -8.720 |
Token | the |
Token ID | 262 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
aciously | +0.435 |
prevail | +0.424 |
elia | +0.400 |
Nadu | +0.393 |
itions | +0.383 |
Neg logit contributions | |
IDER | -0.534 |
Random | -0.499 |
rl | -0.469 |
Rough | -0.466 |
ylum | -0.464 |
Token | Ministry |
Token ID | 9475 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
aciously | +0.218 |
prevail | +0.213 |
elia | +0.199 |
Nadu | +0.197 |
ged | +0.191 |
Neg logit contributions | |
IDER | -0.286 |
Random | -0.268 |
rl | -0.252 |
acco | -0.250 |
ylum | -0.250 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
aciously | +0.657 |
prevail | +0.634 |
elia | +0.602 |
Nadu | +0.585 |
ged | +0.565 |
Neg logit contributions | |
IDER | -0.995 |
Random | -0.943 |
Rough | -0.902 |
rl | -0.892 |
acco | -0.888 |
Token | Foreign |
Token ID | 8708 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
IDER | +0.382 |
Random | +0.355 |
rl | +0.336 |
Rough | +0.333 |
acco | +0.332 |
Neg logit contributions | |
aciously | -0.295 |
prevail | -0.287 |
elia | -0.271 |
Nadu | -0.266 |
itions | -0.260 |
Token | - |
Token ID | 12 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
IDER | +2.132 |
Random | +1.984 |
rl | +1.862 |
Rough | +1.852 |
ylum | +1.839 |
Neg logit contributions | |
aciously | -2.059 |
prevail | -2.011 |
elia | -1.906 |
Nadu | -1.876 |
itions | -1.834 |
Token | aligned |
Token ID | 41634 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
IDER | +0.752 |
Random | +0.714 |
rl | +0.677 |
ylum | +0.668 |
Rough | +0.667 |
Neg logit contributions | |
aciously | -0.534 |
prevail | -0.524 |
elia | -0.488 |
Nadu | -0.483 |
eness | -0.464 |
Token | countries |
Token ID | 2678 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
IDER | +0.175 |
Random | +0.162 |
rl | +0.152 |
Rough | +0.152 |
acco | +0.151 |
Neg logit contributions | |
aciously | -0.154 |
prevail | -0.151 |
elia | -0.142 |
Nadu | -0.140 |
itions | -0.137 |
Token | must |
Token ID | 1276 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
IDER | +3.528 |
Random | +3.239 |
rl | +3.043 |
Rough | +3.032 |
ylum | +3.005 |
Neg logit contributions | |
aciously | -4.148 |
prevail | -3.999 |
elia | -3.905 |
Nadu | -3.829 |
itions | -3.734 |
Token | strengthen |
Token ID | 12160 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
aciously | +0.334 |
prevail | +0.329 |
elia | +0.302 |
Nadu | +0.297 |
itions | +0.291 |
Neg logit contributions | |
IDER | -0.481 |
Random | -0.452 |
rl | -0.426 |
Rough | -0.426 |
ylum | -0.422 |
Token | solidarity |
Token ID | 17803 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
aciously | +0.710 |
prevail | +0.693 |
elia | +0.651 |
Nadu | +0.641 |
itions | +0.630 |
Neg logit contributions | |
IDER | -0.814 |
Random | -0.756 |
rl | -0.709 |
Rough | -0.707 |
acco | -0.701 |
Token | with |
Token ID | 351 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
prevail | +6.738 |
aciously | +6.734 |
itions | +6.121 |
ging | +5.747 |
Nadu | +5.722 |
Neg logit contributions | |
IDER | -9.949 |
Random | -9.517 |
rl | -8.890 |
Rough | -8.800 |
ylum | -8.799 |
Token | the |
Token ID | 262 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
aciously | +0.181 |
prevail | +0.177 |
elia | +0.166 |
Nadu | +0.164 |
itions | +0.160 |
Neg logit contributions | |
IDER | -0.222 |
Random | -0.207 |
rl | -0.195 |
Rough | -0.194 |
ylum | -0.193 |
Token | anti |
Token ID | 3098 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
aciously | +0.170 |
prevail | +0.166 |
elia | +0.155 |
Nadu | +0.152 |
itions | +0.149 |
Neg logit contributions | |
IDER | -0.226 |
Random | -0.211 |
rl | -0.199 |
Rough | -0.198 |
acco | -0.198 |
Token | - |
Token ID | 12 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
aciously | +0.823 |
prevail | +0.789 |
elia | +0.764 |
Nadu | +0.749 |
itions | +0.734 |
Neg logit contributions | |
IDER | -1.072 |
Random | -0.985 |
Rough | -0.940 |
rl | -0.925 |
acco | -0.925 |
Token | war |
Token ID | 5767 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
aciously | +0.759 |
prevail | +0.739 |
elia | +0.705 |
Nadu | +0.692 |
itions | +0.679 |
Neg logit contributions | |
IDER | -0.761 |
Random | -0.702 |
Rough | -0.658 |
rl | -0.657 |
ylum | -0.651 |
Token |
|
Token ID | 198 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
aciously | +0.145 |
prevail | +0.139 |
elia | +0.134 |
ged | +0.131 |
Nadu | +0.130 |
Neg logit contributions | |
IDER | -0.217 |
Random | -0.202 |
acco | -0.195 |
ylum | -0.195 |
Rough | -0.191 |
Token | Good |
Token ID | 10248 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
IDER | +0.159 |
Random | +0.144 |
Rough | +0.135 |
ylum | +0.134 |
rl | +0.133 |
Neg logit contributions | |
aciously | -0.213 |
prevail | -0.207 |
elia | -0.200 |
Nadu | -0.197 |
ged | -0.195 |
Token | suggested |
Token ID | 5220 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
IDER | +0.736 |
Random | +0.685 |
rl | +0.643 |
Rough | +0.642 |
ylum | +0.638 |
Neg logit contributions | |
aciously | -0.649 |
prevail | -0.632 |
elia | -0.599 |
Nadu | -0.588 |
itions | -0.577 |
Token | that |
Token ID | 326 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
IDER | +2.937 |
Random | +2.747 |
Rough | +2.595 |
rl | +2.578 |
acco | +2.545 |
Neg logit contributions | |
aciously | -2.601 |
prevail | -2.527 |
elia | -2.389 |
Nadu | -2.355 |
ged | -2.284 |
Token | close |
Token ID | 1969 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
IDER | +2.120 |
Random | +1.981 |
rl | +1.873 |
Rough | +1.872 |
ylum | +1.854 |
Neg logit contributions | |
aciously | -1.627 |
prevail | -1.580 |
elia | -1.491 |
Nadu | -1.463 |
itions | -1.426 |
Token | coordination |
Token ID | 19877 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
aciously | +0.636 |
prevail | +0.619 |
elia | +0.587 |
Nadu | +0.575 |
itions | +0.564 |
Neg logit contributions | |
IDER | -0.749 |
Random | -0.698 |
rl | -0.656 |
Rough | -0.654 |
ylum | -0.649 |
Token | with |
Token ID | 351 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
prevail | +6.692 |
aciously | +6.330 |
itions | +5.924 |
eness | +5.765 |
elia | +5.715 |
Neg logit contributions | |
IDER | -9.818 |
Random | -9.482 |
asions | -8.867 |
rl | -8.855 |
arted | -8.834 |
Token | the |
Token ID | 262 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
aciously | +0.811 |
prevail | +0.795 |
elia | +0.745 |
Nadu | +0.733 |
ged | +0.716 |
Neg logit contributions | |
IDER | -1.121 |
Random | -1.049 |
rl | -0.989 |
ylum | -0.981 |
Rough | -0.976 |
Token | DEN |
Token ID | 37692 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
aciously | +0.462 |
prevail | +0.452 |
elia | +0.425 |
Nadu | +0.419 |
ged | +0.410 |
Neg logit contributions | |
IDER | -0.627 |
Random | -0.586 |
rl | -0.552 |
ylum | -0.548 |
asions | -0.544 |
Token | R |
Token ID | 49 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
aciously | +3.203 |
prevail | +3.195 |
elia | +3.043 |
Nadu | +2.974 |
itions | +2.967 |
Neg logit contributions | |
IDER | -2.445 |
Random | -2.289 |
ylum | -2.114 |
arted | -2.100 |
asions | -2.091 |
Token | and |
Token ID | 290 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
IDER | +0.162 |
Random | +0.152 |
rl | +0.142 |
Rough | +0.141 |
ylum | +0.140 |
Neg logit contributions | |
aciously | -0.151 |
prevail | -0.149 |
elia | -0.139 |
Nadu | -0.139 |
itions | -0.135 |
Token | development |
Token ID | 2478 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
IDER | +2.568 |
Random | +2.383 |
rl | +2.244 |
Rough | +2.239 |
ylum | +2.217 |
Neg logit contributions | |
aciously | -2.326 |
prevail | -2.261 |
elia | -2.154 |
Nadu | -2.115 |
itions | -2.063 |
Token | and |
Token ID | 290 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
aciously | +1.101 |
prevail | +1.083 |
elia | +1.018 |
Nadu | +1.002 |
itions | +0.991 |
Neg logit contributions | |
IDER | -1.201 |
Random | -1.129 |
ylum | -1.049 |
Rough | -1.047 |
rl | -1.046 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
aciously | +0.168 |
prevail | +0.166 |
elia | +0.155 |
Nadu | +0.153 |
itions | +0.150 |
Neg logit contributions | |
IDER | -0.193 |
Random | -0.179 |
rl | -0.168 |
Rough | -0.168 |
acco | -0.166 |
Token | elimination |
Token ID | 21472 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
aciously | +0.204 |
prevail | +0.200 |
elia | +0.189 |
Nadu | +0.185 |
ged | +0.181 |
Neg logit contributions | |
IDER | -0.259 |
Random | -0.243 |
rl | -0.229 |
ylum | -0.227 |
Rough | -0.227 |
Token | of |
Token ID | 286 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
aciously | +1.140 |
prevail | +1.101 |
elia | +1.038 |
Nadu | +1.017 |
itions | +0.975 |
Neg logit contributions | |
IDER | -1.818 |
Random | -1.710 |
rl | -1.623 |
Rough | -1.623 |
ylum | -1.616 |
Token | blight |
Token ID | 42514 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
IDER | +1.216 |
Random | +1.135 |
rl | +1.070 |
Rough | +1.065 |
ylum | +1.058 |
Neg logit contributions | |
aciously | -0.995 |
prevail | -0.972 |
elia | -0.916 |
Nadu | -0.901 |
itions | -0.878 |
Token | � |
Token ID | 447 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
aciously | +6.886 |
prevail | +6.885 |
ged | +6.382 |
Nadu | +6.377 |
elia | +6.342 |
Neg logit contributions | |
IDER | -9.406 |
Random | -8.934 |
afort | -8.475 |
ylum | -8.337 |
Rough | -8.276 |
Token | � |
Token ID | 251 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
aciously | +0.873 |
prevail | +0.852 |
elia | +0.807 |
Nadu | +0.793 |
itions | +0.777 |
Neg logit contributions | |
IDER | -0.955 |
Random | -0.887 |
Rough | -0.831 |
rl | -0.831 |
acco | -0.824 |
Token | — |
Token ID | 851 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
aciously | +2.042 |
prevail | +2.013 |
elia | +1.923 |
Nadu | +1.885 |
itions | +1.861 |
Neg logit contributions | |
IDER | -2.125 |
Random | -1.983 |
Rough | -1.838 |
ylum | -1.820 |
rl | -1.813 |
Token | but |
Token ID | 475 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
aciously | +2.550 |
prevail | +2.523 |
elia | +2.389 |
Nadu | +2.354 |
itions | +2.318 |
Neg logit contributions | |
IDER | -2.717 |
Random | -2.528 |
rl | -2.359 |
ylum | -2.358 |
arted | -2.334 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
IDER | +0.627 |
Random | +0.585 |
rl | +0.548 |
ylum | +0.545 |
Rough | +0.541 |
Neg logit contributions | |
aciously | -0.564 |
prevail | -0.558 |
elia | -0.526 |
Nadu | -0.518 |
itions | -0.506 |
Token | ereo |
Token ID | 32934 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
IDER | +1.390 |
Random | +1.295 |
rl | +1.221 |
Rough | +1.211 |
acco | +1.209 |
Neg logit contributions | |
aciously | -1.215 |
prevail | -1.205 |
elia | -1.123 |
Nadu | -1.120 |
itions | -1.078 |
Token | Master |
Token ID | 5599 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
aciously | +0.467 |
prevail | +0.456 |
elia | +0.434 |
Nadu | +0.427 |
itions | +0.418 |
Neg logit contributions | |
IDER | -0.471 |
Random | -0.436 |
rl | -0.409 |
Rough | -0.406 |
ylum | -0.404 |
Token | Bus |
Token ID | 5869 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
IDER | +0.606 |
Random | +0.565 |
rl | +0.532 |
Rough | +0.531 |
ylum | +0.527 |
Neg logit contributions | |
aciously | -0.516 |
prevail | -0.503 |
elia | -0.476 |
Nadu | -0.467 |
itions | -0.456 |
Token | that |
Token ID | 326 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
aciously | +0.703 |
prevail | +0.684 |
elia | +0.650 |
Nadu | +0.637 |
ged | +0.627 |
Neg logit contributions | |
IDER | -0.789 |
Random | -0.733 |
rl | -0.690 |
Rough | -0.684 |
acco | -0.683 |
Token | features |
Token ID | 3033 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
IDER | +0.375 |
Random | +0.346 |
rl | +0.326 |
ylum | +0.323 |
Rough | +0.323 |
Neg logit contributions | |
aciously | -0.363 |
prevail | -0.354 |
elia | -0.336 |
Nadu | -0.330 |
itions | -0.324 |
Token | Tone |
Token ID | 45362 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
aciously | +0.638 |
prevail | +0.622 |
elia | +0.587 |
Nadu | +0.578 |
ged | +0.566 |
Neg logit contributions | |
IDER | -0.746 |
Random | -0.690 |
rl | -0.652 |
ylum | -0.648 |
acco | -0.646 |
Token | controls |
Token ID | 6973 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
aciously | +7.512 |
prevail | +7.351 |
ged | +6.841 |
ging | +6.785 |
elia | +6.772 |
Neg logit contributions | |
IDER | -8.818 |
Random | -7.997 |
ylum | -7.816 |
acco | -7.726 |
arted | -7.622 |
Token | , |
Token ID | 11 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
IDER | +2.048 |
Random | +1.903 |
Rough | +1.784 |
rl | +1.772 |
ylum | +1.744 |
Neg logit contributions | |
aciously | -2.176 |
prevail | -2.117 |
elia | -2.024 |
Nadu | -1.998 |
itions | -1.944 |
Token | Analog |
Token ID | 50088 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
aciously | +0.947 |
prevail | +0.922 |
elia | +0.870 |
Nadu | +0.854 |
itions | +0.834 |
Neg logit contributions | |
IDER | -1.198 |
Random | -1.117 |
rl | -1.056 |
Rough | -1.051 |
ylum | -1.046 |
Token | Tape |
Token ID | 40849 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
aciously | +3.022 |
prevail | +2.940 |
elia | +2.791 |
Nadu | +2.743 |
ged | +2.682 |
Neg logit contributions | |
IDER | -3.461 |
Random | -3.216 |
rl | -3.027 |
ylum | -3.004 |
Rough | -3.000 |
Token | S |
Token ID | 311 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
IDER | +0.892 |
Random | +0.839 |
Rough | +0.799 |
rl | +0.784 |
aders | +0.776 |
Neg logit contributions | |
aciously | -0.772 |
prevail | -0.752 |
elia | -0.707 |
Nadu | -0.695 |
ged | -0.676 |
Token |
|
Token ID | 198 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
aciously | +0.041 |
prevail | +0.039 |
elia | +0.038 |
ged | +0.037 |
Nadu | +0.036 |
Neg logit contributions | |
IDER | -0.062 |
Random | -0.057 |
acco | -0.055 |
ylum | -0.055 |
Rough | -0.054 |
Token | impl |
Token ID | 23928 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
IDER | +0.146 |
Random | +0.134 |
Rough | +0.125 |
rl | +0.125 |
ylum | +0.124 |
Neg logit contributions | |
aciously | -0.171 |
prevail | -0.166 |
elia | -0.160 |
Nadu | -0.157 |
ged | -0.154 |
Token | Board |
Token ID | 5926 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
aciously | +0.540 |
prevail | +0.526 |
elia | +0.493 |
Nadu | +0.486 |
ged | +0.474 |
Neg logit contributions | |
IDER | -0.820 |
Random | -0.765 |
rl | -0.729 |
ylum | -0.725 |
acco | -0.723 |
Token | { |
Token ID | 1391 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
aciously | +0.702 |
prevail | +0.682 |
elia | +0.643 |
Nadu | +0.631 |
ged | +0.616 |
Neg logit contributions | |
IDER | -1.031 |
Random | -0.959 |
rl | -0.920 |
ylum | -0.916 |
acco | -0.911 |
Token | pub |
Token ID | 2240 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
prevail | +4.439 |
aciously | +4.406 |
Nadu | +4.033 |
elia | +3.995 |
ged | +3.974 |
Neg logit contributions | |
IDER | -5.366 |
Random | -4.861 |
ylum | -4.782 |
asions | -4.739 |
acco | -4.709 |
Token | fn |
Token ID | 24714 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
aciously | +4.310 |
prevail | +4.267 |
elia | +3.951 |
Nadu | +3.908 |
ged | +3.862 |
Neg logit contributions | |
IDER | -5.105 |
Random | -4.567 |
ylum | -4.555 |
asions | -4.497 |
afort | -4.385 |
Token | copy |
Token ID | 4866 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
prevail | +6.247 |
aciously | +6.032 |
ged | +5.260 |
ging | +5.195 |
Nadu | +5.171 |
Neg logit contributions | |
IDER | -10.120 |
ylum | -9.343 |
Random | -9.259 |
afort | -9.197 |
acco | -9.096 |
Token | _ |
Token ID | 62 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
aciously | +0.128 |
prevail | +0.125 |
elia | +0.118 |
Nadu | +0.117 |
itions | +0.114 |
Neg logit contributions | |
IDER | -0.132 |
Random | -0.124 |
Rough | -0.115 |
rl | -0.115 |
ylum | -0.113 |
Token | board |
Token ID | 3526 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
aciously | +2.229 |
prevail | +2.141 |
elia | +2.053 |
Nadu | +1.983 |
ged | +1.981 |
Neg logit contributions | |
IDER | -2.687 |
Random | -2.465 |
Rough | -2.337 |
ylum | -2.334 |
acco | -2.329 |
Token | ( |
Token ID | 357 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
IDER | +1.178 |
Random | +1.095 |
Rough | +1.024 |
rl | +1.021 |
ylum | +1.003 |
Neg logit contributions | |
aciously | -1.170 |
prevail | -1.137 |
elia | -1.076 |
Nadu | -1.065 |
itions | -1.036 |
Token | & |
Token ID | 1222 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
aciously | +3.467 |
prevail | +3.416 |
elia | +3.224 |
Nadu | +3.174 |
itions | +3.150 |
Neg logit contributions | |
IDER | -3.675 |
Random | -3.315 |
ylum | -3.227 |
acco | -3.142 |
asions | -3.129 |
Token | ereo |
Token ID | 32934 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
aciously | +0.200 |
prevail | +0.195 |
elia | +0.185 |
Nadu | +0.182 |
itions | +0.178 |
Neg logit contributions | |
IDER | -0.227 |
Random | -0.211 |
rl | -0.199 |
Rough | -0.198 |
ylum | -0.196 |
Token | Mix |
Token ID | 15561 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
aciously | +1.178 |
prevail | +1.153 |
elia | +1.095 |
Nadu | +1.078 |
ged | +1.052 |
Neg logit contributions | |
IDER | -1.355 |
Random | -1.259 |
rl | -1.186 |
ylum | -1.181 |
acco | -1.176 |
Token | B |
Token ID | 347 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
aciously | +2.895 |
prevail | +2.818 |
elia | +2.708 |
ged | +2.609 |
itions | +2.604 |
Neg logit contributions | |
IDER | -3.446 |
Random | -3.185 |
ylum | -2.989 |
asions | -2.986 |
rl | -2.985 |
Token | uses |
Token ID | 2664 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
aciously | +2.939 |
prevail | +2.799 |
elia | +2.707 |
ged | +2.637 |
Nadu | +2.635 |
Neg logit contributions | |
IDER | -2.815 |
Random | -2.603 |
rl | -2.426 |
ylum | -2.419 |
Rough | -2.411 |
Token | featuring |
Token ID | 9593 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
IDER | +0.305 |
Random | +0.284 |
rl | +0.267 |
Rough | +0.266 |
ylum | +0.265 |
Neg logit contributions | |
aciously | -0.271 |
prevail | -0.265 |
elia | -0.251 |
Nadu | -0.246 |
ged | -0.241 |
Token | Tone |
Token ID | 45362 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
aciously | +0.197 |
prevail | +0.192 |
elia | +0.182 |
Nadu | +0.179 |
ged | +0.175 |
Neg logit contributions | |
IDER | -0.226 |
Random | -0.210 |
rl | -0.198 |
ylum | -0.197 |
Rough | -0.197 |
Token | controls |
Token ID | 6973 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
aciously | +7.636 |
prevail | +7.484 |
ged | +7.314 |
elia | +7.300 |
ging | +7.134 |
Neg logit contributions | |
IDER | -8.032 |
Random | -7.249 |
acco | -6.993 |
asions | -6.942 |
ylum | -6.916 |
Token | , |
Token ID | 11 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
IDER | +2.866 |
Random | +2.670 |
Rough | +2.507 |
rl | +2.503 |
ylum | +2.465 |
Neg logit contributions | |
aciously | -2.730 |
prevail | -2.650 |
elia | -2.529 |
Nadu | -2.490 |
itions | -2.429 |
Token | Comp |
Token ID | 3082 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
aciously | +0.914 |
prevail | +0.893 |
elia | +0.837 |
Nadu | +0.829 |
ged | +0.812 |
Neg logit contributions | |
IDER | -1.043 |
Random | -0.964 |
rl | -0.911 |
acco | -0.906 |
ylum | -0.905 |
Token | ression |
Token ID | 2234 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
IDER | +0.307 |
Random | +0.281 |
rl | +0.259 |
Rough | +0.259 |
ylum | +0.256 |
Neg logit contributions | |
aciously | -0.413 |
prevail | -0.404 |
elia | -0.387 |
Nadu | -0.382 |
itions | -0.375 |
Token | , |
Token ID | 11 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
aciously | +2.093 |
prevail | +2.051 |
elia | +1.918 |
Nadu | +1.892 |
itions | +1.878 |
Neg logit contributions | |
IDER | -2.269 |
Random | -2.082 |
rl | -1.972 |
ylum | -1.970 |
acco | -1.956 |
Token | < |
Token ID | 1279 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
aciously | +0.834 |
prevail | +0.808 |
elia | +0.759 |
Nadu | +0.749 |
itions | +0.727 |
Neg logit contributions | |
IDER | -1.233 |
Random | -1.151 |
rl | -1.098 |
Rough | -1.093 |
ylum | -1.089 |
Token | T |
Token ID | 309 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
aciously | +1.527 |
prevail | +1.513 |
Nadu | +1.368 |
elia | +1.357 |
itions | +1.311 |
Neg logit contributions | |
IDER | -3.048 |
Random | -2.843 |
ylum | -2.745 |
rl | -2.731 |
acco | -2.729 |
Token | > |
Token ID | 1875 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
aciously | +3.407 |
prevail | +3.333 |
elia | +3.192 |
Nadu | +3.127 |
ged | +3.105 |
Neg logit contributions | |
IDER | -3.984 |
Random | -3.685 |
ylum | -3.509 |
rl | -3.470 |
acco | -3.466 |
Token | { |
Token ID | 1391 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
aciously | +1.136 |
prevail | +1.106 |
elia | +1.037 |
Nadu | +1.031 |
ged | +1.010 |
Neg logit contributions | |
IDER | -1.470 |
Random | -1.362 |
rl | -1.298 |
ylum | -1.295 |
acco | -1.294 |
Token | pub |
Token ID | 2240 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
aciously | +2.806 |
prevail | +2.800 |
elia | +2.547 |
Nadu | +2.534 |
itions | +2.496 |
Neg logit contributions | |
IDER | -3.517 |
Random | -3.201 |
ylum | -3.103 |
asions | -3.077 |
arted | -3.043 |
Token | fn |
Token ID | 24714 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
prevail | +4.119 |
aciously | +4.101 |
elia | +3.741 |
Nadu | +3.737 |
ged | +3.679 |
Neg logit contributions | |
IDER | -5.001 |
Random | -4.519 |
ylum | -4.464 |
asions | -4.420 |
rl | -4.348 |
Token | new |
Token ID | 649 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
prevail | +7.044 |
aciously | +6.850 |
ged | +6.181 |
Nadu | +6.153 |
ging | +6.051 |
Neg logit contributions | |
IDER | -8.918 |
ylum | -7.950 |
Random | -7.911 |
afort | -7.809 |
acco | -7.727 |
Token | ( |
Token ID | 357 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
IDER | +1.232 |
Random | +1.167 |
Rough | +1.074 |
rl | +1.069 |
Rap | +1.048 |
Neg logit contributions | |
aciously | -1.282 |
prevail | -1.251 |
elia | -1.185 |
Nadu | -1.164 |
itions | -1.139 |
Token | t |
Token ID | 256 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
aciously | +3.374 |
prevail | +3.323 |
elia | +3.133 |
Nadu | +3.117 |
itions | +3.062 |
Neg logit contributions | |
IDER | -3.690 |
Random | -3.310 |
ylum | -3.263 |
asions | -3.162 |
rl | -3.138 |
Token | : |
Token ID | 1058 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
aciously | +2.015 |
prevail | +1.961 |
elia | +1.859 |
Nadu | +1.819 |
itions | +1.784 |
Neg logit contributions | |
IDER | -2.950 |
Random | -2.732 |
Rough | -2.591 |
acco | -2.589 |
ylum | -2.586 |
Token | T |
Token ID | 309 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
aciously | +2.247 |
prevail | +2.245 |
Nadu | +2.085 |
elia | +2.020 |
itions | +1.998 |
Neg logit contributions | |
IDER | -3.488 |
Random | -3.195 |
ylum | -3.078 |
rl | -3.073 |
Rap | -3.054 |
Token | 12 |
Token ID | 1105 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
IDER | +1.381 |
Random | +1.291 |
rl | +1.218 |
Rough | +1.211 |
acco | +1.208 |
Neg logit contributions | |
aciously | -1.078 |
prevail | -1.055 |
elia | -0.988 |
Nadu | -0.972 |
ged | -0.953 |
Token | June |
Token ID | 2795 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
IDER | +0.876 |
Random | +0.828 |
rl | +0.792 |
Rough | +0.789 |
acco | +0.786 |
Neg logit contributions | |
aciously | -0.394 |
prevail | -0.379 |
elia | -0.348 |
Nadu | -0.338 |
itions | -0.327 |
Token | 1967 |
Token ID | 15904 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
aciously | +1.416 |
prevail | +1.400 |
elia | +1.227 |
Nadu | +1.226 |
ged | +1.182 |
Neg logit contributions | |
IDER | -3.388 |
Random | -3.194 |
rl | -3.071 |
acco | -3.047 |
ylum | -3.040 |
Token | ) |
Token ID | 8 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
aciously | +0.955 |
prevail | +0.935 |
elia | +0.878 |
Nadu | +0.873 |
itions | +0.859 |
Neg logit contributions | |
IDER | -1.034 |
Random | -0.962 |
rl | -0.901 |
Rough | -0.895 |
acco | -0.893 |
Token | by |
Token ID | 416 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
aciously | +0.491 |
prevail | +0.484 |
elia | +0.447 |
Nadu | +0.443 |
itions | +0.436 |
Neg logit contributions | |
IDER | -0.640 |
Random | -0.600 |
rl | -0.564 |
Rough | -0.560 |
acco | -0.560 |
Token | joint |
Token ID | 6466 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
aciously | +2.623 |
prevail | +2.606 |
elia | +2.411 |
Nadu | +2.353 |
itions | +2.343 |
Neg logit contributions | |
IDER | -3.563 |
Random | -3.296 |
rl | -3.153 |
asions | -3.121 |
ylum | -3.119 |
Token | - |
Token ID | 12 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
aciously | +6.931 |
prevail | +6.759 |
itions | +6.566 |
ging | +6.540 |
ged | +6.394 |
Neg logit contributions | |
IDER | -8.718 |
Random | -7.831 |
ylum | -7.520 |
acco | -7.511 |
asions | -7.418 |
Token | iss |
Token ID | 747 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
aciously | +4.198 |
prevail | +4.089 |
elia | +3.906 |
ging | +3.879 |
itions | +3.860 |
Neg logit contributions | |
IDER | -4.322 |
Random | -3.877 |
Rough | -3.646 |
ylum | -3.623 |
acco | -3.600 |
Token | uing |
Token ID | 4250 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
IDER | +3.999 |
Random | +3.716 |
rl | +3.607 |
ylum | +3.596 |
asions | +3.545 |
Neg logit contributions | |
aciously | -2.538 |
prevail | -2.504 |
Nadu | -2.325 |
elia | -2.314 |
itions | -2.186 |
Token | commemor |
Token ID | 28723 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
IDER | +0.902 |
Random | +0.838 |
rl | +0.787 |
Rough | +0.785 |
ylum | +0.778 |
Neg logit contributions | |
aciously | -0.828 |
prevail | -0.808 |
elia | -0.766 |
Nadu | -0.753 |
itions | -0.737 |
Token | ative |
Token ID | 876 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
aciously | +1.543 |
prevail | +1.465 |
elia | +1.385 |
itions | +1.359 |
ged | +1.329 |
Neg logit contributions | |
IDER | -2.392 |
Random | -2.240 |
ylum | -2.118 |
Rough | -2.117 |
rl | -2.106 |
Token | relationship |
Token ID | 2776 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
aciously | +3.135 |
prevail | +3.043 |
elia | +2.830 |
ged | +2.778 |
eness | +2.775 |
Neg logit contributions | |
IDER | -4.165 |
Random | -3.893 |
rl | -3.659 |
ylum | -3.638 |
asions | -3.625 |
Token | with |
Token ID | 351 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
aciously | +1.808 |
prevail | +1.770 |
elia | +1.660 |
Nadu | +1.628 |
itions | +1.602 |
Neg logit contributions | |
IDER | -2.158 |
Random | -2.015 |
rl | -1.899 |
Rough | -1.888 |
ylum | -1.882 |
Token | Love |
Token ID | 5896 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
aciously | +0.082 |
prevail | +0.080 |
elia | +0.075 |
Nadu | +0.074 |
itions | +0.072 |
Neg logit contributions | |
IDER | -0.102 |
Random | -0.095 |
rl | -0.090 |
ylum | -0.089 |
Rough | -0.089 |
Token | conveyed |
Token ID | 33348 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
prevail | +4.321 |
aciously | +4.271 |
elia | +3.980 |
Nadu | +3.890 |
itions | +3.818 |
Neg logit contributions | |
IDER | -5.253 |
Random | -4.836 |
asions | -4.563 |
acco | -4.545 |
rl | -4.538 |
Token | through |
Token ID | 832 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
IDER | +0.988 |
Random | +0.920 |
rl | +0.866 |
Rough | +0.864 |
ylum | +0.856 |
Neg logit contributions | |
aciously | -0.860 |
prevail | -0.838 |
elia | -0.793 |
Nadu | -0.780 |
itions | -0.761 |
Token | lyr |
Token ID | 47188 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
aciously | +1.256 |
prevail | +1.220 |
elia | +1.157 |
Nadu | +1.121 |
itions | +1.115 |
Neg logit contributions | |
IDER | -1.522 |
Random | -1.423 |
ylum | -1.334 |
rl | -1.332 |
aders | -1.318 |
Token | ical |
Token ID | 605 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
aciously | +2.074 |
itions | +1.356 |
prevail | +1.290 |
elia | +1.115 |
ged | +1.092 |
Neg logit contributions | |
IDER | -14.266 |
Random | -13.523 |
ylum | -13.118 |
Rough | -12.983 |
rl | -12.910 |
Token | themes |
Token ID | 13460 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
aciously | +1.487 |
prevail | +1.464 |
elia | +1.360 |
Nadu | +1.338 |
ged | +1.330 |
Neg logit contributions | |
IDER | -1.740 |
Random | -1.632 |
rl | -1.527 |
ylum | -1.525 |
acco | -1.518 |
Token | of |
Token ID | 286 |
Feature activation | -1.29e-04 |
Pos logit contributions | |
aciously | +1.274 |
prevail | +1.254 |
elia | +1.165 |
Nadu | +1.130 |
itions | +1.120 |
Neg logit contributions | |
IDER | -1.766 |
Random | -1.663 |
rl | -1.563 |
asions | -1.554 |
Rough | -1.550 |
Token | pregnancy |
Token ID | 10241 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
IDER | +0.000 |
Random | +0.000 |
rl | +0.000 |
Rough | +0.000 |
ylum | +0.000 |
Neg logit contributions | |
aciously | -0.000 |
prevail | -0.000 |
elia | -0.000 |
Nadu | -0.000 |
itions | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
aciously | +0.169 |
prevail | +0.165 |
elia | +0.157 |
Nadu | +0.154 |
itions | +0.151 |
Neg logit contributions | |
IDER | -0.170 |
Random | -0.158 |
rl | -0.147 |
Rough | -0.147 |
ylum | -0.146 |
Token | government |
Token ID | 1230 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
aciously | +0.461 |
prevail | +0.455 |
elia | +0.422 |
Nadu | +0.417 |
ged | +0.411 |
Neg logit contributions | |
IDER | -0.564 |
Random | -0.527 |
rl | -0.495 |
acco | -0.489 |
Rough | -0.488 |
Token | are |
Token ID | 389 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
IDER | +0.728 |
Random | +0.677 |
rl | +0.634 |
Rough | +0.632 |
acco | +0.629 |
Neg logit contributions | |
aciously | -0.650 |
prevail | -0.640 |
elia | -0.601 |
Nadu | -0.591 |
itions | -0.581 |
Token | likely |
Token ID | 1884 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
aciously | +0.882 |
prevail | +0.873 |
elia | +0.820 |
Nadu | +0.801 |
ged | +0.786 |
Neg logit contributions | |
IDER | -1.068 |
Random | -0.994 |
rl | -0.934 |
acco | -0.923 |
asions | -0.922 |
Token | to |
Token ID | 284 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
aciously | +1.264 |
prevail | +1.218 |
elia | +1.165 |
Nadu | +1.146 |
itions | +1.122 |
Neg logit contributions | |
IDER | -1.331 |
Random | -1.238 |
Rough | -1.167 |
rl | -1.167 |
ylum | -1.159 |
Token | express |
Token ID | 4911 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
aciously | +1.033 |
prevail | +1.027 |
elia | +0.940 |
Nadu | +0.921 |
ged | +0.901 |
Neg logit contributions | |
IDER | -1.531 |
Random | -1.436 |
rl | -1.350 |
Rough | -1.342 |
ylum | -1.340 |
Token | solidarity |
Token ID | 17803 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
IDER | +0.425 |
Random | +0.397 |
rl | +0.372 |
Rough | +0.370 |
acco | +0.367 |
Neg logit contributions | |
aciously | -0.372 |
prevail | -0.364 |
elia | -0.343 |
Nadu | -0.336 |
itions | -0.331 |
Token | with |
Token ID | 351 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
prevail | +6.486 |
aciously | +6.482 |
itions | +5.640 |
elia | +5.633 |
ged | +5.614 |
Neg logit contributions | |
IDER | -9.297 |
Random | -8.979 |
rl | -8.461 |
arted | -8.216 |
Rough | -8.207 |
Token | Cuba |
Token ID | 14159 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
aciously | +0.582 |
prevail | +0.572 |
elia | +0.536 |
Nadu | +0.525 |
itions | +0.516 |
Neg logit contributions | |
IDER | -0.701 |
Random | -0.655 |
rl | -0.615 |
Rough | -0.609 |
acco | -0.607 |
Token | and |
Token ID | 290 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
IDER | +2.983 |
Random | +2.729 |
Rough | +2.602 |
rl | +2.578 |
ylum | +2.558 |
Neg logit contributions | |
aciously | -3.209 |
prevail | -3.116 |
elia | -2.993 |
Nadu | -2.923 |
eness | -2.869 |
Token | perhaps |
Token ID | 3737 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
prevail | +0.772 |
aciously | +0.771 |
elia | +0.701 |
Nadu | +0.696 |
ged | +0.679 |
Neg logit contributions | |
IDER | -1.008 |
Random | -0.945 |
rl | -0.886 |
acco | -0.880 |
asions | -0.873 |
Token | seek |
Token ID | 5380 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
IDER | +1.933 |
Random | +1.806 |
rl | +1.705 |
Rough | +1.700 |
ylum | +1.686 |
Neg logit contributions | |
aciously | -1.520 |
prevail | -1.482 |
elia | -1.394 |
Nadu | -1.370 |
itions | -1.336 |
Token | U |
Token ID | 52 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
aciously | +2.684 |
prevail | +2.623 |
elia | +2.545 |
Nadu | +2.495 |
ged | +2.457 |
Neg logit contributions | |
IDER | -3.153 |
acco | -2.944 |
Random | -2.906 |
afort | -2.867 |
ylum | -2.865 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
aciously | +1.535 |
prevail | +1.499 |
elia | +1.413 |
Nadu | +1.403 |
itions | +1.377 |
Neg logit contributions | |
IDER | -1.782 |
Random | -1.668 |
acco | -1.563 |
Rough | -1.560 |
rl | -1.559 |
Token | instead |
Token ID | 2427 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
IDER | +0.318 |
Random | +0.297 |
rl | +0.279 |
Rough | +0.276 |
acco | +0.275 |
Neg logit contributions | |
aciously | -0.294 |
prevail | -0.289 |
elia | -0.269 |
Nadu | -0.268 |
itions | -0.261 |
Token | insisting |
Token ID | 23630 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
IDER | +1.250 |
Random | +1.163 |
rl | +1.094 |
Rough | +1.092 |
ylum | +1.082 |
Neg logit contributions | |
aciously | -1.107 |
prevail | -1.079 |
elia | -1.022 |
Nadu | -1.005 |
itions | -0.982 |
Token | on |
Token ID | 319 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
IDER | +0.148 |
Random | +0.137 |
rl | +0.128 |
Rough | +0.128 |
ylum | +0.127 |
Neg logit contributions | |
aciously | -0.156 |
prevail | -0.153 |
elia | -0.146 |
Nadu | -0.144 |
itions | -0.140 |
Token | unity |
Token ID | 14111 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
aciously | +0.093 |
prevail | +0.091 |
elia | +0.086 |
Nadu | +0.084 |
itions | +0.083 |
Neg logit contributions | |
IDER | -0.111 |
Random | -0.103 |
rl | -0.097 |
Rough | -0.096 |
acco | -0.096 |
Token | between |
Token ID | 1022 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
prevail | +6.322 |
aciously | +6.232 |
itions | +5.662 |
Nadu | +5.438 |
elia | +5.417 |
Neg logit contributions | |
IDER | -9.382 |
Random | -9.079 |
acco | -8.497 |
rl | -8.411 |
Rap | -8.357 |
Token | the |
Token ID | 262 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
aciously | +2.263 |
prevail | +2.208 |
elia | +2.060 |
Nadu | +2.027 |
itions | +2.012 |
Neg logit contributions | |
IDER | -2.881 |
Random | -2.701 |
rl | -2.546 |
acco | -2.515 |
ylum | -2.511 |
Token | two |
Token ID | 734 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
aciously | +0.809 |
prevail | +0.792 |
elia | +0.736 |
Nadu | +0.728 |
itions | +0.717 |
Neg logit contributions | |
IDER | -1.098 |
Random | -1.030 |
rl | -0.972 |
acco | -0.964 |
ylum | -0.962 |
Token | parties |
Token ID | 4671 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
aciously | +3.485 |
prevail | +3.466 |
Nadu | +3.131 |
itions | +3.114 |
ged | +3.101 |
Neg logit contributions | |
IDER | -4.496 |
Random | -4.199 |
acco | -3.973 |
afort | -3.929 |
rl | -3.916 |
Token | . |
Token ID | 13 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
IDER | +3.069 |
Random | +2.840 |
rl | +2.687 |
Rough | +2.682 |
ylum | +2.660 |
Neg logit contributions | |
aciously | -2.764 |
prevail | -2.664 |
elia | -2.556 |
Nadu | -2.508 |
itions | -2.433 |
Token | to |
Token ID | 284 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
aciously | +0.646 |
prevail | +0.629 |
elia | +0.598 |
ged | +0.584 |
Nadu | +0.582 |
Neg logit contributions | |
IDER | -0.871 |
Random | -0.803 |
acco | -0.770 |
rl | -0.763 |
ylum | -0.762 |
Token | a |
Token ID | 257 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
aciously | +1.653 |
prevail | +1.627 |
elia | +1.541 |
Nadu | +1.499 |
ged | +1.486 |
Neg logit contributions | |
IDER | -1.925 |
Random | -1.784 |
rl | -1.702 |
ylum | -1.686 |
acco | -1.667 |
Token | study |
Token ID | 2050 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
aciously | +1.531 |
prevail | +1.500 |
elia | +1.419 |
ged | +1.368 |
Nadu | +1.363 |
Neg logit contributions | |
IDER | -2.181 |
Random | -2.030 |
rl | -1.941 |
ylum | -1.931 |
acco | -1.925 |
Token | by |
Token ID | 416 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
IDER | +0.534 |
Random | +0.497 |
rl | +0.468 |
Rough | +0.462 |
acco | +0.462 |
Neg logit contributions | |
aciously | -0.468 |
prevail | -0.459 |
elia | -0.434 |
Nadu | -0.424 |
ged | -0.419 |
Token | consultants |
Token ID | 29597 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
aciously | +2.243 |
prevail | +2.213 |
elia | +2.096 |
Nadu | +2.039 |
ged | +2.015 |
Neg logit contributions | |
IDER | -2.697 |
Random | -2.500 |
rl | -2.396 |
ylum | -2.361 |
asions | -2.337 |
Token | Brand |
Token ID | 13512 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
aciously | +2.861 |
prevail | +2.816 |
elia | +2.661 |
Nadu | +2.608 |
itions | +2.576 |
Neg logit contributions | |
IDER | -3.323 |
Random | -3.091 |
rl | -2.969 |
ylum | -2.911 |
asions | -2.896 |
Token | Finance |
Token ID | 15007 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
aciously | +7.524 |
elia | +7.402 |
prevail | +7.393 |
ged | +7.229 |
ging | +7.205 |
Neg logit contributions | |
IDER | -7.638 |
Random | -6.845 |
acco | -6.779 |
ylum | -6.599 |
asions | -6.573 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
IDER | +1.619 |
Random | +1.506 |
rl | +1.416 |
Rough | +1.414 |
ylum | +1.400 |
Neg logit contributions | |
aciously | -1.446 |
prevail | -1.408 |
elia | -1.333 |
Nadu | -1.312 |
itions | -1.280 |
Token | Apple |
Token ID | 4196 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
aciously | +0.357 |
prevail | +0.352 |
elia | +0.335 |
Nadu | +0.332 |
ged | +0.324 |
Neg logit contributions | |
IDER | -0.411 |
Random | -0.381 |
acco | -0.361 |
ylum | -0.360 |
rl | -0.360 |
Token | is |
Token ID | 318 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
IDER | +0.753 |
Random | +0.699 |
rl | +0.658 |
ylum | +0.650 |
Rough | +0.650 |
Neg logit contributions | |
aciously | -0.748 |
prevail | -0.735 |
elia | -0.697 |
Nadu | -0.687 |
itions | -0.673 |
Token | the |
Token ID | 262 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
aciously | +0.227 |
prevail | +0.225 |
elia | +0.210 |
Nadu | +0.207 |
ged | +0.203 |
Neg logit contributions | |
IDER | -0.282 |
Random | -0.263 |
rl | -0.249 |
ylum | -0.245 |
Rough | -0.245 |
Token | sudo |
Token ID | 24032 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
IDER | +0.302 |
Random | +0.279 |
Rough | +0.265 |
ylum | +0.263 |
acco | +0.262 |
Neg logit contributions | |
aciously | -0.273 |
prevail | -0.264 |
elia | -0.254 |
Nadu | -0.248 |
ged | -0.245 |
Token | i |
Token ID | 1312 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
IDER | +2.721 |
Random | +2.542 |
rl | +2.391 |
Rough | +2.376 |
ylum | +2.338 |
Neg logit contributions | |
aciously | -2.659 |
prevail | -2.568 |
elia | -2.452 |
Nadu | -2.419 |
itions | -2.358 |
Token | w |
Token ID | 86 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
aciously | +2.344 |
prevail | +2.267 |
elia | +2.142 |
Nadu | +2.073 |
ged | +2.058 |
Neg logit contributions | |
IDER | -3.458 |
Random | -3.213 |
Rough | -3.077 |
ylum | -3.055 |
Rap | -3.010 |
Token | config |
Token ID | 11250 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
aciously | +2.109 |
prevail | +2.056 |
elia | +1.928 |
Nadu | +1.901 |
ged | +1.895 |
Neg logit contributions | |
IDER | -2.588 |
Random | -2.372 |
Rough | -2.262 |
ylum | -2.248 |
acco | -2.231 |
Token | w |
Token ID | 266 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
aciously | +0.771 |
prevail | +0.761 |
elia | +0.716 |
Nadu | +0.704 |
ged | +0.690 |
Neg logit contributions | |
IDER | -0.899 |
Random | -0.832 |
ylum | -0.784 |
Rough | -0.783 |
rl | -0.782 |
Token | lan |
Token ID | 9620 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
aciously | +2.660 |
prevail | +2.593 |
elia | +2.477 |
Nadu | +2.400 |
ged | +2.391 |
Neg logit contributions | |
IDER | -2.810 |
Random | -2.603 |
Rough | -2.460 |
acco | -2.425 |
ylum | -2.416 |
Token | 0 |
Token ID | 15 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
aciously | +5.594 |
prevail | +5.510 |
ged | +5.149 |
Nadu | +5.054 |
elia | +5.005 |
Neg logit contributions | |
IDER | -9.820 |
Random | -8.798 |
ylum | -8.702 |
acco | -8.644 |
asions | -8.614 |
Token | power |
Token ID | 1176 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
IDER | +0.495 |
Random | +0.461 |
rl | +0.433 |
Rough | +0.432 |
ylum | +0.428 |
Neg logit contributions | |
aciously | -0.441 |
prevail | -0.430 |
elia | -0.407 |
Nadu | -0.400 |
itions | -0.391 |
Token | off |
Token ID | 572 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
aciously | +1.660 |
prevail | +1.624 |
elia | +1.524 |
Nadu | +1.508 |
ged | +1.475 |
Neg logit contributions | |
IDER | -2.052 |
Random | -1.896 |
ylum | -1.796 |
Rough | -1.795 |
rl | -1.782 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
IDER | +1.379 |
Random | +1.287 |
rl | +1.214 |
Rough | +1.210 |
acco | +1.192 |
Neg logit contributions | |
aciously | -1.235 |
prevail | -1.197 |
elia | -1.138 |
Nadu | -1.116 |
itions | -1.092 |
Token |
|
Token ID | 198 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
aciously | +0.392 |
prevail | +0.372 |
elia | +0.362 |
ged | +0.355 |
Nadu | +0.348 |
Neg logit contributions | |
IDER | -0.602 |
Random | -0.555 |
ylum | -0.540 |
acco | -0.540 |
afort | -0.531 |
Token | preference |
Token ID | 12741 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
IDER | +0.822 |
Random | +0.753 |
rl | +0.699 |
ylum | +0.694 |
Rough | +0.693 |
Neg logit contributions | |
aciously | -0.996 |
prevail | -0.987 |
elia | -0.938 |
Nadu | -0.918 |
ged | -0.908 |
Token | . |
Token ID | 13 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
aciously | +1.317 |
prevail | +1.296 |
elia | +1.205 |
Nadu | +1.178 |
itions | +1.176 |
Neg logit contributions | |
IDER | -1.717 |
Random | -1.595 |
ylum | -1.508 |
acco | -1.506 |
rl | -1.505 |
Token | Still |
Token ID | 7831 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
aciously | +0.918 |
prevail | +0.902 |
elia | +0.867 |
Nadu | +0.846 |
ged | +0.833 |
Neg logit contributions | |
IDER | -1.136 |
Random | -1.046 |
acco | -1.016 |
ylum | -1.003 |
rl | -0.995 |
Token | , |
Token ID | 11 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
IDER | +0.936 |
Random | +0.869 |
rl | +0.813 |
Rough | +0.812 |
ylum | +0.801 |
Neg logit contributions | |
aciously | -0.953 |
prevail | -0.929 |
elia | -0.885 |
Nadu | -0.870 |
itions | -0.851 |
Token | I |
Token ID | 314 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
aciously | +0.960 |
prevail | +0.954 |
elia | +0.903 |
Nadu | +0.875 |
itions | +0.869 |
Neg logit contributions | |
IDER | -1.074 |
Random | -0.983 |
acco | -0.931 |
ylum | -0.927 |
rl | -0.924 |
Token | dread |
Token ID | 15157 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
prevail | +1.960 |
aciously | +1.902 |
elia | +1.762 |
Nadu | +1.744 |
ged | +1.744 |
Neg logit contributions | |
IDER | -2.004 |
Random | -1.830 |
ylum | -1.747 |
Rap | -1.745 |
Rough | -1.717 |
Token | the |
Token ID | 262 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
aciously | +6.544 |
prevail | +6.536 |
elia | +6.364 |
ging | +6.065 |
itions | +6.022 |
Neg logit contributions | |
IDER | -8.543 |
Random | -7.636 |
afort | -7.582 |
acco | -7.488 |
ylum | -7.452 |
Token | day |
Token ID | 1110 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
IDER | +0.142 |
Random | +0.131 |
rl | +0.123 |
acco | +0.123 |
ylum | +0.122 |
Neg logit contributions | |
aciously | -0.137 |
prevail | -0.134 |
elia | -0.127 |
Nadu | -0.124 |
itions | -0.123 |
Token | I |
Token ID | 314 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
IDER | +0.043 |
Random | +0.040 |
rl | +0.038 |
Rough | +0.037 |
acco | +0.037 |
Neg logit contributions | |
aciously | -0.042 |
prevail | -0.041 |
elia | -0.039 |
Nadu | -0.038 |
itions | -0.038 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
prevail | +1.117 |
aciously | +1.086 |
Nadu | +0.994 |
elia | +0.991 |
ged | +0.989 |
Neg logit contributions | |
IDER | -1.352 |
Random | -1.236 |
Rap | -1.181 |
ylum | -1.178 |
rl | -1.167 |
Token | be |
Token ID | 307 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
prevail | +2.127 |
aciously | +2.077 |
elia | +1.854 |
Nadu | +1.838 |
itions | +1.828 |
Neg logit contributions | |
IDER | -3.498 |
Random | -3.258 |
Rap | -3.108 |
ylum | -3.102 |
Rough | -3.079 |
Token | is |
Token ID | 318 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
aciously | +0.780 |
prevail | +0.763 |
elia | +0.720 |
Nadu | +0.708 |
itions | +0.699 |
Neg logit contributions | |
IDER | -0.794 |
Random | -0.736 |
rl | -0.688 |
Rough | -0.687 |
ylum | -0.679 |
Token | bearing |
Token ID | 14121 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
IDER | +0.820 |
Random | +0.763 |
rl | +0.719 |
Rough | +0.716 |
ylum | +0.709 |
Neg logit contributions | |
aciously | -0.729 |
prevail | -0.712 |
elia | -0.673 |
Nadu | -0.661 |
itions | -0.647 |
Token | witness |
Token ID | 4973 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
IDER | +1.073 |
Random | +0.996 |
rl | +0.937 |
Rough | +0.933 |
ylum | +0.928 |
Neg logit contributions | |
aciously | -0.974 |
prevail | -0.950 |
elia | -0.898 |
Nadu | -0.880 |
ged | -0.864 |
Token | , |
Token ID | 11 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
IDER | +1.062 |
Random | +0.986 |
rl | +0.929 |
Rough | +0.927 |
ylum | +0.915 |
Neg logit contributions | |
aciously | -0.980 |
prevail | -0.954 |
elia | -0.911 |
Nadu | -0.898 |
itions | -0.873 |
Token | demonstrating |
Token ID | 21135 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
IDER | +0.935 |
Random | +0.870 |
rl | +0.817 |
Rough | +0.811 |
ylum | +0.806 |
Neg logit contributions | |
aciously | -0.853 |
prevail | -0.836 |
elia | -0.786 |
Nadu | -0.774 |
itions | -0.760 |
Token | solidarity |
Token ID | 17803 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
IDER | +3.602 |
Random | +3.339 |
Rough | +3.148 |
rl | +3.141 |
Rap | +3.097 |
Neg logit contributions | |
aciously | -3.569 |
prevail | -3.448 |
elia | -3.316 |
Nadu | -3.281 |
itions | -3.189 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
prevail | +6.599 |
aciously | +6.473 |
eness | +5.844 |
elia | +5.827 |
itions | +5.754 |
Neg logit contributions | |
IDER | -8.769 |
Random | -8.335 |
arted | -7.735 |
ylum | -7.713 |
acco | -7.703 |
Token | and |
Token ID | 290 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
aciously | +0.025 |
prevail | +0.024 |
elia | +0.023 |
Nadu | +0.022 |
itions | +0.022 |
Neg logit contributions | |
IDER | -0.028 |
Random | -0.026 |
rl | -0.024 |
Rough | -0.024 |
acco | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
aciously | +0.490 |
prevail | +0.483 |
elia | +0.449 |
Nadu | +0.442 |
itions | +0.435 |
Neg logit contributions | |
IDER | -0.582 |
Random | -0.543 |
rl | -0.512 |
acco | -0.508 |
Rough | -0.508 |
Token | event |
Token ID | 1785 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
aciously | +0.065 |
prevail | +0.064 |
elia | +0.060 |
Nadu | +0.059 |
itions | +0.058 |
Neg logit contributions | |
IDER | -0.072 |
Random | -0.067 |
rl | -0.063 |
Rough | -0.062 |
acco | -0.062 |
Token | or |
Token ID | 393 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
IDER | +1.857 |
Random | +1.733 |
rl | +1.635 |
Rough | +1.632 |
ylum | +1.618 |
Neg logit contributions | |
aciously | -1.494 |
prevail | -1.454 |
elia | -1.374 |
Nadu | -1.349 |
itions | -1.316 |
Token | Hag |
Token ID | 21375 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
IDER | +0.250 |
Random | +0.231 |
Rough | +0.216 |
rl | +0.216 |
ylum | +0.213 |
Neg logit contributions | |
aciously | -0.262 |
prevail | -0.256 |
elia | -0.244 |
Nadu | -0.240 |
itions | -0.235 |
Token | el |
Token ID | 417 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
aciously | +0.069 |
elia | +0.065 |
prevail | +0.064 |
ged | +0.060 |
eness | +0.060 |
Neg logit contributions | |
IDER | -0.127 |
Random | -0.118 |
Rough | -0.114 |
ylum | -0.112 |
acco | -0.111 |
Token | as |
Token ID | 355 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
IDER | +2.049 |
Random | +1.881 |
Rough | +1.781 |
rl | +1.768 |
ylum | +1.745 |
Neg logit contributions | |
aciously | -2.191 |
prevail | -2.155 |
elia | -2.074 |
Nadu | -2.037 |
itions | -1.979 |
Token | an |
Token ID | 281 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
IDER | +0.360 |
Random | +0.334 |
rl | +0.314 |
Rough | +0.314 |
ylum | +0.311 |
Neg logit contributions | |
aciously | -0.334 |
prevail | -0.326 |
elia | -0.309 |
Nadu | -0.304 |
itions | -0.297 |
Token | " |
Token ID | 366 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
aciously | +0.689 |
prevail | +0.675 |
elia | +0.628 |
Nadu | +0.622 |
eness | +0.610 |
Neg logit contributions | |
IDER | -0.836 |
Random | -0.793 |
rl | -0.748 |
ylum | -0.743 |
acco | -0.739 |
Token | ex |
Token ID | 1069 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
IDER | +0.973 |
Random | +0.901 |
Rough | +0.848 |
rl | +0.846 |
ylum | +0.839 |
Neg logit contributions | |
aciously | -0.945 |
prevail | -0.915 |
elia | -0.876 |
Nadu | -0.857 |
itions | -0.841 |
Token | empl |
Token ID | 18856 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
IDER | +7.809 |
Random | +6.980 |
ylum | +6.863 |
arted | +6.731 |
afort | +6.731 |
Neg logit contributions | |
prevail | -10.131 |
aciously | -10.117 |
Nadu | -9.834 |
elia | -9.491 |
eness | -9.277 |
Token | ary |
Token ID | 560 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
IDER | +2.434 |
Random | +2.288 |
rl | +2.203 |
acco | +2.177 |
ylum | +2.160 |
Neg logit contributions | |
aciously | -1.828 |
prevail | -1.826 |
Nadu | -1.697 |
elia | -1.696 |
itions | -1.608 |
Token | " |
Token ID | 1 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
IDER | +2.934 |
Random | +2.736 |
Rough | +2.584 |
rl | +2.582 |
ylum | +2.552 |
Neg logit contributions | |
aciously | -2.361 |
prevail | -2.294 |
elia | -2.174 |
Nadu | -2.131 |
itions | -2.082 |
Token | Defense |
Token ID | 5947 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
IDER | +0.721 |
Random | +0.676 |
rl | +0.639 |
ylum | +0.634 |
acco | +0.634 |
Neg logit contributions | |
aciously | -0.559 |
prevail | -0.547 |
elia | -0.510 |
Nadu | -0.503 |
ged | -0.492 |
Token | secretary |
Token ID | 7705 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
IDER | +1.801 |
Random | +1.668 |
rl | +1.560 |
Rough | +1.554 |
ylum | +1.550 |
Neg logit contributions | |
aciously | -1.847 |
prevail | -1.808 |
elia | -1.718 |
Nadu | -1.691 |
ged | -1.653 |
Token | vert |
Token ID | 9421 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
aciously | +0.576 |
prevail | +0.566 |
elia | +0.534 |
Nadu | +0.524 |
itions | +0.515 |
Neg logit contributions | |
IDER | -0.660 |
Random | -0.611 |
rl | -0.576 |
Rough | -0.573 |
ylum | -0.573 |
Token | ices |
Token ID | 1063 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
aciously | +3.631 |
prevail | +3.448 |
elia | +3.281 |
itions | +3.238 |
eness | +3.213 |
Neg logit contributions | |
IDER | -5.927 |
Random | -5.520 |
acco | -5.306 |
ylum | -5.299 |
Rough | -5.245 |
Token | is |
Token ID | 318 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
IDER | +0.676 |
Random | +0.628 |
rl | +0.590 |
Rough | +0.588 |
acco | +0.584 |
Neg logit contributions | |
aciously | -0.625 |
prevail | -0.610 |
elia | -0.577 |
Nadu | -0.567 |
itions | -0.556 |
Token | called |
Token ID | 1444 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
IDER | +0.905 |
Random | +0.843 |
Rough | +0.792 |
rl | +0.792 |
acco | +0.775 |
Neg logit contributions | |
aciously | -0.842 |
prevail | -0.819 |
elia | -0.780 |
Nadu | -0.768 |
itions | -0.746 |
Token | normal |
Token ID | 3487 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
aciously | +1.708 |
prevail | +1.691 |
elia | +1.580 |
Nadu | +1.563 |
ged | +1.538 |
Neg logit contributions | |
IDER | -2.053 |
Random | -1.886 |
ylum | -1.791 |
acco | -1.781 |
rl | -1.781 |
Token | extr |
Token ID | 22820 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
IDER | +0.482 |
Random | +0.449 |
rl | +0.423 |
Rough | +0.422 |
ylum | +0.419 |
Neg logit contributions | |
aciously | -0.415 |
prevail | -0.404 |
elia | -0.382 |
Nadu | -0.376 |
itions | -0.368 |
Token | usion |
Token ID | 4241 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
IDER | +5.518 |
Random | +4.866 |
aders | +4.723 |
rl | +4.642 |
asions | +4.629 |
Neg logit contributions | |
prevail | -11.984 |
aciously | -11.818 |
Nadu | -11.562 |
elia | -11.311 |
ged | -10.707 |
Token | , |
Token ID | 11 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
IDER | +0.597 |
Random | +0.556 |
rl | +0.523 |
Rough | +0.522 |
ylum | +0.517 |
Neg logit contributions | |
aciously | -0.531 |
prevail | -0.517 |
elia | -0.490 |
Nadu | -0.482 |
itions | -0.471 |
Token | and |
Token ID | 290 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
IDER | +0.761 |
Random | +0.700 |
rl | +0.655 |
ylum | +0.650 |
acco | +0.649 |
Neg logit contributions | |
aciously | -0.838 |
prevail | -0.824 |
elia | -0.779 |
Nadu | -0.772 |
itions | -0.759 |
Token | is |
Token ID | 318 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
IDER | +0.518 |
Random | +0.479 |
ylum | +0.451 |
rl | +0.450 |
acco | +0.450 |
Neg logit contributions | |
aciously | -0.480 |
prevail | -0.473 |
elia | -0.445 |
Nadu | -0.438 |
itions | -0.431 |
Token | discussed |
Token ID | 6693 |
Feature activation | +1.04e-03 |
Pos logit contributions | |
aciously | +0.960 |
prevail | +0.939 |
elia | +0.883 |
Nadu | +0.865 |
itions | +0.852 |
Neg logit contributions | |
IDER | -0.999 |
Random | -0.925 |
rl | -0.867 |
ylum | -0.867 |
acco | -0.860 |
Token | � |
Token ID | 447 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
IDER | +1.070 |
Random | +0.993 |
rl | +0.933 |
Rough | +0.932 |
ylum | +0.923 |
Neg logit contributions | |
aciously | -1.033 |
prevail | -1.006 |
elia | -0.956 |
Nadu | -0.940 |
itions | -0.919 |
Token | � |
Token ID | 251 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
IDER | +0.066 |
Random | +0.060 |
rl | +0.056 |
Rough | +0.056 |
ylum | +0.056 |
Neg logit contributions | |
aciously | -0.079 |
prevail | -0.077 |
elia | -0.074 |
Nadu | -0.073 |
itions | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
aciously | +1.477 |
prevail | +1.446 |
elia | +1.377 |
Nadu | +1.357 |
itions | +1.328 |
Neg logit contributions | |
IDER | -1.583 |
Random | -1.460 |
rl | -1.362 |
Rough | -1.360 |
asions | -1.353 |
Token | � |
Token ID | 564 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
IDER | +0.519 |
Random | +0.484 |
rl | +0.456 |
Rough | +0.456 |
ylum | +0.451 |
Neg logit contributions | |
aciously | -0.432 |
prevail | -0.420 |
elia | -0.397 |
Nadu | -0.390 |
itions | -0.381 |
Token | � |
Token ID | 250 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
IDER | +0.749 |
Random | +0.691 |
Rough | +0.654 |
acco | +0.647 |
rl | +0.646 |
Neg logit contributions | |
aciously | -0.705 |
prevail | -0.687 |
elia | -0.659 |
Nadu | -0.641 |
itions | -0.631 |
Token | Sch |
Token ID | 14874 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
IDER | +1.176 |
Random | +1.076 |
rl | +0.994 |
Rough | +0.990 |
ylum | +0.979 |
Neg logit contributions | |
aciously | -1.585 |
prevail | -1.553 |
elia | -1.485 |
Nadu | -1.464 |
itions | -1.437 |
Token | ole |
Token ID | 2305 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
IDER | +9.473 |
rl | +8.874 |
Random | +8.839 |
ylum | +8.666 |
acco | +8.623 |
Neg logit contributions | |
prevail | -8.121 |
aciously | -7.712 |
Nadu | -7.291 |
elia | -7.011 |
itions | -6.787 |
Token | io |
Token ID | 952 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
IDER | +0.158 |
Random | +0.146 |
Rough | +0.137 |
rl | +0.136 |
acco | +0.135 |
Neg logit contributions | |
aciously | -0.155 |
prevail | -0.151 |
elia | -0.144 |
Nadu | -0.142 |
itions | -0.139 |
Token | � |
Token ID | 447 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
IDER | +0.562 |
Random | +0.519 |
rl | +0.486 |
Rough | +0.484 |
ylum | +0.481 |
Neg logit contributions | |
aciously | -0.606 |
prevail | -0.592 |
elia | -0.562 |
Nadu | -0.553 |
itions | -0.542 |
Token | � |
Token ID | 251 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
aciously | +0.612 |
prevail | +0.599 |
elia | +0.573 |
Nadu | +0.564 |
itions | +0.554 |
Neg logit contributions | |
IDER | -0.498 |
Random | -0.455 |
Rough | -0.421 |
rl | -0.420 |
acco | -0.417 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
aciously | +1.707 |
prevail | +1.669 |
elia | +1.594 |
Nadu | +1.572 |
itions | +1.533 |
Neg logit contributions | |
IDER | -1.820 |
Random | -1.676 |
Rough | -1.563 |
rl | -1.556 |
asions | -1.547 |
Token | Waves |
Token ID | 42733 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
IDER | +0.919 |
Random | +0.854 |
rl | +0.802 |
Rough | +0.799 |
ylum | +0.794 |
Neg logit contributions | |
aciously | -0.846 |
prevail | -0.825 |
elia | -0.783 |
Nadu | -0.770 |
itions | -0.754 |
Token |
|
Token ID | 198 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
IDER | +1.756 |
Random | +1.637 |
Rough | +1.547 |
rl | +1.541 |
ylum | +1.518 |
Neg logit contributions | |
aciously | -1.540 |
prevail | -1.494 |
elia | -1.419 |
Nadu | -1.398 |
itions | -1.357 |
Token |
|
Token ID | 198 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
aciously | +1.228 |
prevail | +1.162 |
elia | +1.148 |
ged | +1.130 |
ging | +1.096 |
Neg logit contributions | |
IDER | -2.074 |
Random | -1.913 |
acco | -1.883 |
ylum | -1.882 |
afort | -1.865 |
Token | The |
Token ID | 464 |
Feature activation | +5.91e-04 |
Pos logit contributions | |
aciously | +1.387 |
prevail | +1.332 |
elia | +1.311 |
ged | +1.287 |
Nadu | +1.283 |
Neg logit contributions | |
IDER | -1.100 |
Random | -0.962 |
acco | -0.952 |
ylum | -0.951 |
Rough | -0.945 |
Token | normal |
Token ID | 3487 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
aciously | +0.001 |
prevail | +0.001 |
elia | +0.001 |
Nadu | +0.001 |
itions | +0.001 |
Neg logit contributions | |
IDER | -0.001 |
Random | -0.001 |
rl | -0.001 |
acco | -0.001 |
ylum | -0.001 |
Token | extr |
Token ID | 22820 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
aciously | +0.163 |
prevail | +0.160 |
elia | +0.150 |
Nadu | +0.148 |
itions | +0.145 |
Neg logit contributions | |
IDER | -0.201 |
Random | -0.188 |
rl | -0.177 |
acco | -0.177 |
Rough | -0.176 |
Token | usion |
Token ID | 4241 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
IDER | +5.446 |
Random | +4.791 |
rl | +4.562 |
aders | +4.550 |
asions | +4.486 |
Neg logit contributions | |
prevail | -11.644 |
aciously | -11.629 |
Nadu | -11.114 |
elia | -11.055 |
eness | -10.509 |
Token | done |
Token ID | 1760 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
IDER | +0.039 |
Random | +0.037 |
rl | +0.035 |
acco | +0.034 |
ylum | +0.034 |
Neg logit contributions | |
aciously | -0.033 |
prevail | -0.032 |
elia | -0.030 |
Nadu | -0.030 |
ged | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
aciously | +2.507 |
prevail | +2.456 |
elia | +2.318 |
itions | +2.249 |
ged | +2.247 |
Neg logit contributions | |
IDER | -3.168 |
Random | -2.958 |
acco | -2.806 |
ylum | -2.781 |
asions | -2.772 |
Token | the |
Token ID | 262 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
aciously | +1.572 |
prevail | +1.544 |
elia | +1.454 |
Nadu | +1.431 |
itions | +1.405 |
Neg logit contributions | |
IDER | -1.831 |
Random | -1.706 |
ylum | -1.608 |
rl | -1.601 |
acco | -1.591 |
Token | previous |
Token ID | 2180 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
IDER | +0.236 |
Random | +0.221 |
rl | +0.208 |
ylum | +0.207 |
Rough | +0.207 |
Neg logit contributions | |
aciously | -0.179 |
prevail | -0.175 |
elia | -0.164 |
Nadu | -0.162 |
itions | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
IDER | +0.584 |
Random | +0.545 |
rl | +0.514 |
Rough | +0.513 |
ylum | +0.509 |
Neg logit contributions | |
aciously | -0.472 |
prevail | -0.460 |
elia | -0.434 |
Nadu | -0.426 |
itions | -0.417 |
Token |
|
Token ID | 198 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
aciously | +0.254 |
prevail | +0.247 |
elia | +0.235 |
Nadu | +0.231 |
itions | +0.225 |
Neg logit contributions | |
IDER | -0.303 |
Random | -0.282 |
rl | -0.266 |
ylum | -0.264 |
acco | -0.264 |
Token |
|
Token ID | 198 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
IDER | +1.209 |
Random | +1.123 |
acco | +1.072 |
ylum | +1.071 |
Rough | +1.063 |
Neg logit contributions | |
aciously | -0.874 |
prevail | -0.842 |
elia | -0.807 |
Nadu | -0.783 |
ged | -0.780 |
Token | La |
Token ID | 14772 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
IDER | +0.984 |
Random | +0.891 |
Rough | +0.830 |
rl | +0.826 |
ylum | +0.822 |
Neg logit contributions | |
aciously | -1.360 |
prevail | -1.326 |
elia | -1.277 |
Nadu | -1.258 |
ged | -1.239 |
Token | uren |
Token ID | 23532 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
aciously | +2.864 |
prevail | +2.755 |
elia | +2.665 |
Nadu | +2.589 |
itions | +2.558 |
Neg logit contributions | |
IDER | -3.319 |
Random | -3.035 |
ylum | -2.888 |
rl | -2.887 |
Rough | -2.865 |
Token | Carter |
Token ID | 10831 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
aciously | +3.211 |
prevail | +3.109 |
elia | +3.011 |
Nadu | +2.936 |
ged | +2.899 |
Neg logit contributions | |
IDER | -3.653 |
Random | -3.389 |
rl | -3.170 |
asions | -3.154 |
ylum | -3.147 |
Token | , |
Token ID | 11 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
IDER | +8.012 |
Random | +7.495 |
Rough | +7.146 |
rl | +6.998 |
Rap | +6.924 |
Neg logit contributions | |
aciously | -8.818 |
prevail | -8.593 |
Nadu | -8.067 |
elia | -8.066 |
eness | -7.878 |
Token | centre |
Token ID | 7372 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
IDER | +0.163 |
Random | +0.152 |
rl | +0.143 |
Rough | +0.142 |
ylum | +0.142 |
Neg logit contributions | |
aciously | -0.140 |
prevail | -0.137 |
elia | -0.129 |
Nadu | -0.127 |
itions | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
aciously | +2.192 |
prevail | +2.140 |
elia | +2.036 |
Nadu | +2.003 |
itions | +1.962 |
Neg logit contributions | |
IDER | -2.190 |
Random | -2.028 |
rl | -1.899 |
Rough | -1.893 |
ylum | -1.879 |
Token | helped |
Token ID | 4193 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
aciously | +0.077 |
prevail | +0.075 |
elia | +0.071 |
Nadu | +0.070 |
itions | +0.069 |
Neg logit contributions | |
IDER | -0.079 |
Random | -0.074 |
rl | -0.069 |
Rough | -0.068 |
ylum | -0.068 |
Token | begin |
Token ID | 2221 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
IDER | +0.148 |
Random | +0.139 |
rl | +0.131 |
ylum | +0.130 |
Rough | +0.130 |
Neg logit contributions | |
aciously | -0.106 |
prevail | -0.104 |
elia | -0.097 |
Nadu | -0.096 |
itions | -0.094 |
Token | ney |
Token ID | 1681 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
aciously | +2.699 |
prevail | +2.559 |
elia | +2.540 |
Nadu | +2.447 |
ged | +2.421 |
Neg logit contributions | |
IDER | -2.824 |
Random | -2.619 |
Rough | -2.470 |
rl | -2.439 |
ylum | -2.435 |
Token | made |
Token ID | 925 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
aciously | +0.943 |
prevail | +0.930 |
elia | +0.873 |
Nadu | +0.867 |
ged | +0.849 |
Neg logit contributions | |
IDER | -0.937 |
Random | -0.865 |
ylum | -0.806 |
rl | -0.805 |
Rough | -0.800 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
IDER | +1.005 |
Random | +0.933 |
rl | +0.876 |
Rough | +0.870 |
ylum | +0.865 |
Neg logit contributions | |
aciously | -0.926 |
prevail | -0.907 |
elia | -0.858 |
Nadu | -0.843 |
itions | -0.826 |
Token | Obama |
Token ID | 2486 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
IDER | +0.312 |
Random | +0.291 |
rl | +0.274 |
Rough | +0.272 |
ylum | +0.271 |
Neg logit contributions | |
aciously | -0.262 |
prevail | -0.257 |
elia | -0.241 |
Nadu | -0.238 |
ged | -0.232 |
Token | - |
Token ID | 12 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
IDER | +1.965 |
Random | +1.830 |
rl | +1.722 |
Rough | +1.720 |
ylum | +1.703 |
Neg logit contributions | |
aciously | -1.752 |
prevail | -1.706 |
elia | -1.620 |
Nadu | -1.589 |
itions | -1.556 |
Token | Carter |
Token ID | 49958 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
aciously | +0.288 |
prevail | +0.278 |
elia | +0.268 |
Nadu | +0.262 |
ged | +0.260 |
Neg logit contributions | |
IDER | -0.257 |
Random | -0.235 |
Rough | -0.221 |
rl | -0.218 |
ylum | -0.217 |
Token | ana |
Token ID | 44763 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
IDER | +8.480 |
Random | +7.924 |
Rough | +7.710 |
rl | +7.558 |
Rap | +7.503 |
Neg logit contributions | |
aciously | -8.102 |
prevail | -7.605 |
elia | -7.402 |
itions | -7.166 |
Nadu | -7.047 |
Token | |
Token ID | 3907 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
aciously | +2.357 |
prevail | +2.305 |
elia | +2.175 |
Nadu | +2.125 |
itions | +2.087 |
Neg logit contributions | |
IDER | -2.961 |
Random | -2.756 |
Rough | -2.599 |
rl | -2.594 |
ylum | -2.578 |
Token | log |
Token ID | 6404 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
aciously | +2.691 |
prevail | +2.567 |
elia | +2.501 |
ged | +2.423 |
itions | +2.411 |
Neg logit contributions | |
IDER | -2.611 |
Random | -2.423 |
Rough | -2.267 |
ylum | -2.235 |
acco | -2.232 |
Token | y |
Token ID | 88 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
aciously | +2.172 |
prevail | +2.112 |
elia | +2.004 |
Nadu | +1.955 |
ged | +1.932 |
Neg logit contributions | |
IDER | -2.550 |
Random | -2.360 |
Rough | -2.219 |
rl | -2.210 |
ylum | -2.194 |
Token | a |
Token ID | 257 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
aciously | +1.893 |
prevail | +1.881 |
elia | +1.743 |
Nadu | +1.718 |
ged | +1.683 |
Neg logit contributions | |
IDER | -2.246 |
Random | -2.098 |
Rough | -1.952 |
rl | -1.951 |
acco | -1.946 |
Token | ulation |
Token ID | 1741 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
IDER | +1.325 |
Random | +1.213 |
rl | +1.128 |
Rough | +1.127 |
acco | +1.124 |
Neg logit contributions | |
aciously | -1.676 |
prevail | -1.650 |
elia | -1.562 |
Nadu | -1.561 |
itions | -1.508 |
Token | and |
Token ID | 290 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
aciously | +0.916 |
prevail | +0.902 |
elia | +0.843 |
Nadu | +0.825 |
ged | +0.815 |
Neg logit contributions | |
IDER | -1.119 |
Random | -1.045 |
rl | -0.991 |
Rough | -0.977 |
ylum | -0.973 |
Token | lymph |
Token ID | 28837 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
aciously | +0.323 |
prevail | +0.319 |
elia | +0.299 |
Nadu | +0.293 |
ged | +0.288 |
Neg logit contributions | |
IDER | -0.369 |
Random | -0.343 |
rl | -0.325 |
Rough | -0.319 |
acco | -0.319 |
Token | nodes |
Token ID | 13760 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
aciously | +3.529 |
prevail | +3.408 |
elia | +3.252 |
Nadu | +3.149 |
ged | +3.073 |
Neg logit contributions | |
IDER | -5.659 |
Random | -5.283 |
rl | -5.016 |
Rough | -5.014 |
ylum | -4.995 |
Token | .[ |
Token ID | 3693 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
IDER | +0.728 |
Random | +0.676 |
rl | +0.634 |
Rough | +0.631 |
acco | +0.625 |
Neg logit contributions | |
aciously | -0.698 |
prevail | -0.686 |
elia | -0.649 |
Nadu | -0.634 |
ged | -0.624 |
Token | 118 |
Token ID | 16817 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
aciously | +2.196 |
prevail | +2.149 |
elia | +2.070 |
Nadu | +2.048 |
ged | +2.016 |
Neg logit contributions | |
IDER | -1.286 |
Random | -1.146 |
Rough | -1.046 |
ylum | -1.037 |
acco | -1.035 |
Token | ] |
Token ID | 60 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
IDER | +7.742 |
Random | +7.137 |
Rough | +6.908 |
rl | +6.832 |
Rap | +6.790 |
Neg logit contributions | |
aciously | -8.139 |
prevail | -8.043 |
elia | -7.673 |
Nadu | -7.577 |
itions | -7.487 |
Token |
|
Token ID | 198 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
aciously | +0.626 |
prevail | +0.617 |
elia | +0.589 |
Nadu | +0.581 |
ged | +0.563 |
Neg logit contributions | |
IDER | -0.760 |
Random | -0.705 |
rl | -0.670 |
acco | -0.667 |
arted | -0.660 |
Token |
|
Token ID | 198 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
aciously | +1.057 |
prevail | +1.004 |
elia | +0.987 |
ged | +0.974 |
Nadu | +0.946 |
Neg logit contributions | |
IDER | -1.776 |
Random | -1.632 |
acco | -1.608 |
ylum | -1.599 |
afort | -1.589 |
Token | See |
Token ID | 6214 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
aciously | +1.057 |
prevail | +1.025 |
elia | +1.005 |
Nadu | +0.986 |
ged | +0.978 |
Neg logit contributions | |
IDER | -0.813 |
Random | -0.716 |
Rough | -0.694 |
acco | -0.683 |
ylum | -0.681 |
Token | also |
Token ID | 635 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
aciously | +0.716 |
prevail | +0.702 |
elia | +0.666 |
Nadu | +0.655 |
itions | +0.642 |
Neg logit contributions | |
IDER | -0.823 |
Random | -0.765 |
rl | -0.720 |
Rough | -0.711 |
ylum | -0.710 |
Token | von |
Token ID | 18042 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
IDER | +2.500 |
Random | +2.328 |
Rough | +2.236 |
rl | +2.216 |
ylum | +2.207 |
Neg logit contributions | |
aciously | -1.830 |
prevail | -1.774 |
elia | -1.669 |
Nadu | -1.652 |
itions | -1.595 |
Token | Viet |
Token ID | 8730 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
IDER | +0.920 |
Random | +0.857 |
Rough | +0.808 |
rl | +0.807 |
ylum | +0.800 |
Neg logit contributions | |
aciously | -0.785 |
prevail | -0.766 |
elia | -0.722 |
Nadu | -0.712 |
itions | -0.694 |
Token | ing |
Token ID | 278 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
aciously | +4.206 |
prevail | +4.085 |
elia | +3.993 |
itions | +3.844 |
Nadu | +3.832 |
Neg logit contributions | |
IDER | -4.460 |
Random | -4.044 |
rl | -3.726 |
ylum | -3.717 |
Rough | -3.712 |
Token | hoff |
Token ID | 36092 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
IDER | +0.734 |
Random | +0.678 |
rl | +0.633 |
Rough | +0.630 |
ylum | +0.623 |
Neg logit contributions | |
aciously | -0.772 |
prevail | -0.756 |
elia | -0.720 |
Nadu | -0.706 |
itions | -0.695 |
Token | - |
Token ID | 12 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
IDER | +1.416 |
Random | +1.309 |
rl | +1.223 |
Rough | +1.220 |
ylum | +1.207 |
Neg logit contributions | |
aciously | -1.495 |
prevail | -1.461 |
elia | -1.391 |
Nadu | -1.367 |
itions | -1.342 |
Token | Sche |
Token ID | 27054 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
aciously | +0.828 |
prevail | +0.810 |
elia | +0.779 |
Nadu | +0.763 |
itions | +0.756 |
Neg logit contributions | |
IDER | -0.653 |
Random | -0.591 |
rl | -0.551 |
Rough | -0.549 |
ylum | -0.546 |
Token | el |
Token ID | 417 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
IDER | +8.754 |
rl | +8.045 |
Random | +7.913 |
aders | +7.764 |
ylum | +7.726 |
Neg logit contributions | |
prevail | -8.011 |
aciously | -7.609 |
Nadu | -7.433 |
elia | -6.886 |
itions | -6.520 |
Token | signed |
Token ID | 4488 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
aciously | +0.196 |
prevail | +0.192 |
elia | +0.182 |
Nadu | +0.179 |
itions | +0.177 |
Neg logit contributions | |
IDER | -0.193 |
Random | -0.178 |
rl | -0.166 |
Rough | -0.166 |
ylum | -0.164 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
IDER | +0.220 |
Random | +0.205 |
rl | +0.193 |
Rough | +0.192 |
acco | +0.190 |
Neg logit contributions | |
aciously | -0.198 |
prevail | -0.193 |
elia | -0.183 |
Nadu | -0.180 |
itions | -0.176 |
Token | unconditional |
Token ID | 42423 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
IDER | +0.550 |
Random | +0.515 |
rl | +0.488 |
acco | +0.483 |
Rough | +0.483 |
Neg logit contributions | |
aciously | -0.370 |
prevail | -0.360 |
elia | -0.336 |
Nadu | -0.330 |
itions | -0.322 |
Token | instrument |
Token ID | 8875 |
Feature activation | -9.70e-03 |
Pos logit contributions | |
aciously | +1.498 |
prevail | +1.469 |
ged | +1.288 |
elia | +1.245 |
Nadu | +1.229 |
Neg logit contributions | |
IDER | -4.540 |
Random | -4.270 |
rl | -4.095 |
acco | -4.092 |
afort | -4.060 |
Token | , |
Token ID | 11 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
aciously | +0.315 |
prevail | +0.307 |
elia | +0.292 |
Nadu | +0.289 |
itions | +0.281 |
Neg logit contributions | |
IDER | -0.293 |
Random | -0.271 |
Rough | -0.254 |
rl | -0.253 |
acco | -0.251 |
Token | said |
Token ID | 531 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
aciously | +0.105 |
prevail | +0.103 |
elia | +0.097 |
Nadu | +0.096 |
itions | +0.095 |
Neg logit contributions | |
IDER | -0.095 |
Random | -0.087 |
rl | -0.081 |
Rough | -0.080 |
asions | -0.080 |
Token | that |
Token ID | 326 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
IDER | +0.580 |
Random | +0.539 |
rl | +0.507 |
Rough | +0.505 |
ylum | +0.502 |
Neg logit contributions | |
aciously | -0.517 |
prevail | -0.505 |
elia | -0.478 |
Nadu | -0.470 |
itions | -0.460 |
Token | � |
Token ID | 564 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
IDER | +2.003 |
Random | +1.863 |
Rough | +1.752 |
rl | +1.751 |
ylum | +1.732 |
Neg logit contributions | |
aciously | -1.835 |
prevail | -1.786 |
elia | -1.695 |
Nadu | -1.667 |
itions | -1.628 |
Token | � |
Token ID | 250 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
IDER | +0.788 |
Random | +0.722 |
Rough | +0.677 |
rl | +0.675 |
ylum | +0.673 |
Neg logit contributions | |
aciously | -0.785 |
prevail | -0.767 |
elia | -0.730 |
Nadu | -0.713 |
itions | -0.704 |
Token | inqu |
Token ID | 18934 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
IDER | +2.137 |
Random | +1.959 |
rl | +1.822 |
Rough | +1.817 |
ylum | +1.800 |
Neg logit contributions | |
aciously | -2.589 |
prevail | -2.532 |
elia | -2.419 |
Nadu | -2.383 |
itions | -2.340 |
Token | iring |
Token ID | 3428 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
IDER | +6.572 |
Random | +5.894 |
arted | +5.840 |
rl | +5.645 |
aders | +5.600 |
Neg logit contributions | |
prevail | -10.029 |
aciously | -9.620 |
Nadu | -9.503 |
elia | -9.027 |
ged | -8.675 |
Token | whether |
Token ID | 1771 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
IDER | +4.041 |
Random | +3.773 |
Rough | +3.566 |
rl | +3.548 |
ylum | +3.500 |
Neg logit contributions | |
aciously | -3.543 |
prevail | -3.475 |
elia | -3.300 |
Nadu | -3.249 |
itions | -3.160 |
Token | underwear |
Token ID | 26170 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
IDER | +1.205 |
Random | +1.117 |
rl | +1.048 |
Rough | +1.042 |
ylum | +1.038 |
Neg logit contributions | |
aciously | -1.149 |
prevail | -1.122 |
elia | -1.065 |
Nadu | -1.047 |
itions | -1.027 |
Token | was |
Token ID | 373 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
aciously | +0.269 |
prevail | +0.265 |
elia | +0.250 |
Nadu | +0.246 |
ged | +0.244 |
Neg logit contributions | |
IDER | -0.264 |
Random | -0.243 |
Rough | -0.227 |
ylum | -0.227 |
rl | -0.227 |
Token | being |
Token ID | 852 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
IDER | +0.789 |
Random | +0.730 |
rl | +0.686 |
Rough | +0.682 |
ylum | +0.679 |
Neg logit contributions | |
aciously | -0.768 |
prevail | -0.753 |
elia | -0.712 |
Nadu | -0.702 |
ged | -0.686 |
Token | institution |
Token ID | 9901 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
IDER | +0.330 |
Random | +0.308 |
rl | +0.289 |
Rough | +0.286 |
acco | +0.285 |
Neg logit contributions | |
aciously | -0.291 |
prevail | -0.285 |
elia | -0.269 |
Nadu | -0.265 |
itions | -0.259 |
Token | this |
Token ID | 428 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
IDER | +2.602 |
Random | +2.415 |
rl | +2.274 |
Rough | +2.271 |
ylum | +2.247 |
Neg logit contributions | |
aciously | -2.411 |
prevail | -2.347 |
elia | -2.232 |
Nadu | -2.192 |
itions | -2.140 |
Token | year |
Token ID | 614 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
aciously | +0.152 |
prevail | +0.147 |
elia | +0.138 |
Nadu | +0.134 |
itions | +0.132 |
Neg logit contributions | |
IDER | -0.220 |
Random | -0.206 |
rl | -0.195 |
Rough | -0.195 |
acco | -0.194 |
Token | � |
Token ID | 564 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
IDER | +0.377 |
Random | +0.351 |
rl | +0.329 |
Rough | +0.328 |
ylum | +0.326 |
Neg logit contributions | |
aciously | -0.335 |
prevail | -0.327 |
elia | -0.309 |
Nadu | -0.304 |
itions | -0.297 |
Token | � |
Token ID | 250 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
IDER | +0.863 |
Random | +0.806 |
rl | +0.761 |
Rough | +0.760 |
ylum | +0.753 |
Neg logit contributions | |
aciously | -0.669 |
prevail | -0.650 |
elia | -0.614 |
Nadu | -0.602 |
itions | -0.587 |
Token | exc |
Token ID | 41194 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
IDER | +1.275 |
Random | +1.181 |
Rough | +1.104 |
rl | +1.100 |
acco | +1.093 |
Neg logit contributions | |
aciously | -1.228 |
prevail | -1.196 |
elia | -1.136 |
Nadu | -1.118 |
itions | -1.097 |
Token | ited |
Token ID | 863 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
IDER | +8.473 |
Random | +7.866 |
rl | +7.647 |
arted | +7.625 |
Rap | +7.614 |
Neg logit contributions | |
aciously | -7.793 |
prevail | -7.763 |
eness | -7.177 |
elia | -7.172 |
Nadu | -7.133 |
Token | � |
Token ID | 447 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
IDER | +0.607 |
Random | +0.565 |
rl | +0.530 |
Rough | +0.529 |
ylum | +0.525 |
Neg logit contributions | |
aciously | -0.552 |
prevail | -0.539 |
elia | -0.511 |
Nadu | -0.502 |
itions | -0.491 |
Token | � |
Token ID | 251 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
IDER | +0.218 |
Random | +0.202 |
rl | +0.189 |
Rough | +0.189 |
ylum | +0.187 |
Neg logit contributions | |
aciously | -0.225 |
prevail | -0.220 |
elia | -0.210 |
Nadu | -0.206 |
itions | -0.202 |
Token | about |
Token ID | 546 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
aciously | +1.196 |
prevail | +1.167 |
elia | +1.112 |
Nadu | +1.088 |
itions | +1.073 |
Neg logit contributions | |
IDER | -1.286 |
Random | -1.189 |
Rough | -1.109 |
acco | -1.107 |
rl | -1.107 |
Token | the |
Token ID | 262 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
IDER | +4.059 |
Random | +3.764 |
rl | +3.570 |
Rough | +3.547 |
ylum | +3.499 |
Neg logit contributions | |
aciously | -3.847 |
prevail | -3.722 |
elia | -3.524 |
Nadu | -3.509 |
itions | -3.413 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
IDER | +1.234 |
Random | +1.131 |
Rough | +1.073 |
rl | +1.065 |
ylum | +1.048 |
Neg logit contributions | |
aciously | -1.271 |
prevail | -1.230 |
elia | -1.173 |
Nadu | -1.154 |
ged | -1.129 |
Token | ( |
Token ID | 357 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
aciously | +0.603 |
prevail | +0.589 |
elia | +0.561 |
Nadu | +0.551 |
ged | +0.536 |
Neg logit contributions | |
IDER | -0.692 |
Random | -0.644 |
rl | -0.606 |
acco | -0.604 |
ylum | -0.602 |
Token | Photo |
Token ID | 6191 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
aciously | +0.430 |
prevail | +0.421 |
elia | +0.404 |
Nadu | +0.398 |
ged | +0.391 |
Neg logit contributions | |
IDER | -0.320 |
Random | -0.291 |
rl | -0.271 |
Rough | -0.270 |
ylum | -0.270 |
Token | : |
Token ID | 25 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
aciously | +2.059 |
prevail | +2.005 |
elia | +1.891 |
Nadu | +1.861 |
itions | +1.819 |
Neg logit contributions | |
IDER | -2.481 |
Random | -2.318 |
rl | -2.189 |
Rough | -2.182 |
ylum | -2.157 |
Token | Mary |
Token ID | 5335 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
IDER | +1.101 |
Random | +1.029 |
Rough | +0.971 |
rl | +0.970 |
ylum | +0.959 |
Neg logit contributions | |
aciously | -0.874 |
prevail | -0.850 |
elia | -0.801 |
Nadu | -0.786 |
itions | -0.768 |
Token | Sch |
Token ID | 3059 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
IDER | +2.145 |
Random | +1.978 |
rl | +1.845 |
Rough | +1.841 |
ylum | +1.821 |
Neg logit contributions | |
aciously | -2.402 |
prevail | -2.348 |
elia | -2.238 |
Nadu | -2.204 |
itions | -2.160 |
Token | wal |
Token ID | 16783 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
IDER | +8.379 |
Random | +7.743 |
rl | +7.718 |
arted | +7.422 |
ylum | +7.406 |
Neg logit contributions | |
prevail | -8.466 |
aciously | -7.843 |
Nadu | -7.536 |
elia | -7.358 |
itions | -7.213 |
Token | m |
Token ID | 76 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
IDER | +3.214 |
Random | +2.995 |
rl | +2.845 |
Rough | +2.815 |
ylum | +2.788 |
Neg logit contributions | |
aciously | -3.013 |
prevail | -2.962 |
elia | -2.766 |
Nadu | -2.744 |
itions | -2.663 |
Token | / |
Token ID | 14 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
IDER | +0.044 |
Random | +0.041 |
rl | +0.038 |
Rough | +0.038 |
ylum | +0.038 |
Neg logit contributions | |
aciously | -0.043 |
prevail | -0.042 |
elia | -0.040 |
Nadu | -0.040 |
itions | -0.039 |
Token | AP |
Token ID | 2969 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
IDER | +0.461 |
Random | +0.420 |
rl | +0.391 |
Rough | +0.390 |
ylum | +0.387 |
Neg logit contributions | |
aciously | -0.594 |
prevail | -0.582 |
elia | -0.558 |
Nadu | -0.548 |
itions | -0.539 |
Token | ) |
Token ID | 8 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
IDER | +2.632 |
Random | +2.365 |
Rough | +2.270 |
rl | +2.212 |
Rap | +2.188 |
Neg logit contributions | |
aciously | -3.517 |
prevail | -3.460 |
elia | -3.283 |
Nadu | -3.220 |
eness | -3.185 |
Token | , |
Token ID | 11 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
IDER | +2.007 |
Random | +1.862 |
rl | +1.752 |
Rough | +1.742 |
ylum | +1.731 |
Neg logit contributions | |
aciously | -1.875 |
prevail | -1.833 |
elia | -1.732 |
Nadu | -1.699 |
itions | -1.670 |
Token | he |
Token ID | 339 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
IDER | +1.035 |
Random | +0.960 |
rl | +0.905 |
Rough | +0.898 |
ylum | +0.894 |
Neg logit contributions | |
aciously | -0.948 |
prevail | -0.928 |
elia | -0.873 |
Nadu | -0.859 |
itions | -0.842 |
Token | planned |
Token ID | 6027 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
IDER | +1.084 |
Random | +0.994 |
rl | +0.932 |
Rough | +0.926 |
ylum | +0.924 |
Neg logit contributions | |
aciously | -1.159 |
prevail | -1.131 |
elia | -1.068 |
Nadu | -1.051 |
ged | -1.040 |
Token | a |
Token ID | 257 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
aciously | +1.970 |
prevail | +1.911 |
elia | +1.781 |
Nadu | +1.751 |
itions | +1.745 |
Neg logit contributions | |
IDER | -2.305 |
Random | -2.123 |
rl | -2.014 |
ylum | -1.994 |
Rough | -1.976 |
Token | " |
Token ID | 366 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
aciously | +0.105 |
prevail | +0.103 |
elia | +0.097 |
Nadu | +0.095 |
ged | +0.094 |
Neg logit contributions | |
IDER | -0.121 |
Random | -0.112 |
rl | -0.106 |
ylum | -0.105 |
acco | -0.104 |
Token | sur |
Token ID | 11793 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
IDER | +1.730 |
Random | +1.599 |
rl | +1.493 |
Rough | +1.490 |
ylum | +1.474 |
Neg logit contributions | |
aciously | -1.862 |
prevail | -1.820 |
elia | -1.733 |
Nadu | -1.706 |
itions | -1.671 |
Token | prise |
Token ID | 7919 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
IDER | +6.749 |
Random | +6.588 |
rl | +6.217 |
ylum | +6.090 |
Rap | +6.008 |
Neg logit contributions | |
prevail | -9.044 |
aciously | -8.997 |
Nadu | -8.703 |
elia | -8.373 |
eness | -8.105 |
Token | " |
Token ID | 1 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
IDER | +3.602 |
Random | +3.351 |
Rough | +3.141 |
rl | +3.131 |
ylum | +3.100 |
Neg logit contributions | |
aciously | -3.495 |
prevail | -3.396 |
elia | -3.250 |
Nadu | -3.183 |
itions | -3.115 |
Token | trip |
Token ID | 5296 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
IDER | +1.214 |
Random | +1.125 |
rl | +1.065 |
ylum | +1.051 |
acco | +1.048 |
Neg logit contributions | |
aciously | -1.040 |
prevail | -1.018 |
elia | -0.948 |
Nadu | -0.939 |
itions | -0.923 |
Token | to |
Token ID | 284 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
IDER | +2.694 |
Random | +2.506 |
rl | +2.356 |
Rough | +2.352 |
ylum | +2.330 |
Neg logit contributions | |
aciously | -2.411 |
prevail | -2.350 |
elia | -2.228 |
Nadu | -2.190 |
itions | -2.139 |
Token | Mexico |
Token ID | 5828 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
aciously | +0.235 |
prevail | +0.231 |
elia | +0.217 |
Nadu | +0.213 |
ged | +0.208 |
Neg logit contributions | |
IDER | -0.282 |
Random | -0.262 |
rl | -0.247 |
ylum | -0.245 |
Rough | -0.244 |
Token | everyone |
Token ID | 2506 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
IDER | +0.154 |
Random | +0.143 |
rl | +0.135 |
acco | +0.133 |
ylum | +0.132 |
Neg logit contributions | |
aciously | -0.152 |
prevail | -0.152 |
Nadu | -0.142 |
elia | -0.142 |
ged | -0.138 |
Token | was |
Token ID | 373 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
aciously | +2.061 |
prevail | +2.052 |
elia | +1.909 |
Nadu | +1.903 |
ged | +1.883 |
Neg logit contributions | |
IDER | -2.102 |
Random | -1.959 |
rl | -1.848 |
Rough | -1.824 |
acco | -1.794 |
Token | doing |
Token ID | 1804 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
IDER | +1.259 |
Random | +1.174 |
rl | +1.103 |
Rough | +1.095 |
ylum | +1.084 |
Neg logit contributions | |
aciously | -1.184 |
prevail | -1.156 |
elia | -1.095 |
Nadu | -1.078 |
ged | -1.055 |
Token | . |
Token ID | 13 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
aciously | +1.615 |
prevail | +1.599 |
elia | +1.484 |
Nadu | +1.479 |
ged | +1.455 |
Neg logit contributions | |
IDER | -1.976 |
Random | -1.840 |
rl | -1.735 |
acco | -1.724 |
Rough | -1.716 |
Token | Glenn |
Token ID | 17551 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
IDER | +1.045 |
Random | +0.969 |
acco | +0.917 |
rl | +0.917 |
ylum | +0.915 |
Neg logit contributions | |
aciously | -0.897 |
prevail | -0.881 |
Nadu | -0.837 |
elia | -0.834 |
ged | -0.811 |
Token | McGr |
Token ID | 41114 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
aciously | +1.240 |
prevail | +1.206 |
elia | +1.140 |
Nadu | +1.128 |
itions | +1.105 |
Neg logit contributions | |
IDER | -1.317 |
Random | -1.226 |
rl | -1.169 |
ylum | -1.148 |
Rough | -1.148 |
Token | ath |
Token ID | 776 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
IDER | +6.864 |
Random | +6.242 |
aders | +5.845 |
rl | +5.816 |
acco | +5.753 |
Neg logit contributions | |
prevail | -9.717 |
aciously | -9.609 |
Nadu | -9.204 |
elia | -9.136 |
ged | -9.055 |
Token | had |
Token ID | 550 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
IDER | +2.110 |
Random | +1.949 |
rl | +1.820 |
Rough | +1.811 |
ylum | +1.800 |
Neg logit contributions | |
aciously | -2.284 |
prevail | -2.236 |
elia | -2.123 |
Nadu | -2.096 |
ged | -2.052 |
Token | a |
Token ID | 257 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
IDER | +2.671 |
Random | +2.480 |
rl | +2.329 |
Rough | +2.323 |
ylum | +2.302 |
Neg logit contributions | |
aciously | -2.517 |
prevail | -2.456 |
elia | -2.330 |
Nadu | -2.292 |
itions | -2.241 |
Token | slight |
Token ID | 3731 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
IDER | +0.430 |
Random | +0.400 |
rl | +0.377 |
ylum | +0.374 |
acco | +0.372 |
Neg logit contributions | |
aciously | -0.392 |
prevail | -0.383 |
elia | -0.363 |
Nadu | -0.356 |
ged | -0.350 |
Token | bend |
Token ID | 19396 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
IDER | +1.584 |
Random | +1.463 |
rl | +1.366 |
Rough | +1.354 |
ylum | +1.352 |
Neg logit contributions | |
aciously | -1.730 |
prevail | -1.696 |
elia | -1.615 |
Nadu | -1.592 |
ged | -1.558 |
Token | on |
Token ID | 319 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
aciously | +1.071 |
prevail | +1.041 |
elia | +0.983 |
Nadu | +0.964 |
ged | +0.949 |
Neg logit contributions | |
IDER | -1.227 |
Random | -1.147 |
rl | -1.079 |
Rough | -1.070 |
asions | -1.068 |
Token | what |
Token ID | 644 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
aciously | +1.266 |
prevail | +1.230 |
elia | +1.170 |
Nadu | +1.133 |
ged | +1.130 |
Neg logit contributions | |
IDER | -1.428 |
Random | -1.330 |
rl | -1.258 |
ylum | -1.239 |
asions | -1.233 |
Token | he |
Token ID | 339 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
aciously | +0.325 |
prevail | +0.320 |
elia | +0.302 |
Nadu | +0.298 |
itions | +0.292 |
Neg logit contributions | |
IDER | -0.332 |
Random | -0.307 |
rl | -0.289 |
Rough | -0.285 |
acco | -0.284 |
Token | called |
Token ID | 1444 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
IDER | +0.382 |
Random | +0.353 |
Rough | +0.329 |
ylum | +0.325 |
rl | +0.324 |
Neg logit contributions | |
aciously | -0.425 |
prevail | -0.413 |
elia | -0.392 |
Nadu | -0.388 |
itions | -0.384 |
Token | " |
Token ID | 366 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
aciously | +2.534 |
prevail | +2.475 |
elia | +2.322 |
Nadu | +2.264 |
ged | +2.260 |
Neg logit contributions | |
IDER | -3.134 |
Random | -2.916 |
rl | -2.767 |
ylum | -2.714 |
acco | -2.699 |
Token | ex |
Token ID | 1069 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
aciously | +0.715 |
prevail | +0.689 |
elia | +0.666 |
Nadu | +0.647 |
ged | +0.645 |
Neg logit contributions | |
IDER | -0.686 |
Random | -0.625 |
Rough | -0.589 |
rl | -0.587 |
ylum | -0.583 |
Token | orbit |
Token ID | 42594 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
IDER | +8.503 |
Random | +7.870 |
ylum | +7.582 |
rl | +7.529 |
asive | +7.453 |
Neg logit contributions | |
prevail | -7.611 |
aciously | -7.459 |
Nadu | -7.155 |
elia | -6.858 |
ged | -6.689 |
Token | ant |
Token ID | 415 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
IDER | +2.204 |
Random | +2.036 |
rl | +1.901 |
Rough | +1.892 |
ylum | +1.881 |
Neg logit contributions | |
aciously | -2.441 |
prevail | -2.398 |
elia | -2.286 |
Nadu | -2.260 |
ged | -2.202 |
Token | " |
Token ID | 1 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
IDER | +0.893 |
Random | +0.826 |
rl | +0.773 |
Rough | +0.766 |
ylum | +0.762 |
Neg logit contributions | |
aciously | -0.937 |
prevail | -0.913 |
elia | -0.864 |
Nadu | -0.851 |
ged | -0.836 |
Token | pay |
Token ID | 1414 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
IDER | +0.541 |
Random | +0.503 |
rl | +0.474 |
ylum | +0.468 |
acco | +0.467 |
Neg logit contributions | |
aciously | -0.484 |
prevail | -0.472 |
elia | -0.445 |
Nadu | -0.437 |
itions | -0.430 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
IDER | +0.020 |
Random | +0.018 |
rl | +0.017 |
Rough | +0.017 |
ylum | +0.017 |
Neg logit contributions | |
aciously | -0.018 |
prevail | -0.017 |
elia | -0.016 |
Nadu | -0.016 |
itions | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
IDER | +0.789 |
Random | +0.731 |
acco | +0.702 |
ylum | +0.700 |
Rough | +0.694 |
Neg logit contributions | |
aciously | -0.551 |
prevail | -0.530 |
elia | -0.512 |
Nadu | -0.495 |
ged | -0.494 |
Token | Customer |
Token ID | 44939 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
IDER | +0.947 |
Random | +0.861 |
Rough | +0.803 |
rl | +0.800 |
ylum | +0.793 |
Neg logit contributions | |
aciously | -1.249 |
prevail | -1.219 |
elia | -1.171 |
Nadu | -1.153 |
ged | -1.133 |
Token | : |
Token ID | 25 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
IDER | +4.607 |
Random | +4.263 |
Rough | +4.028 |
rl | +3.990 |
Rap | +3.955 |
Neg logit contributions | |
aciously | -4.228 |
prevail | -4.108 |
elia | -3.849 |
Nadu | -3.802 |
itions | -3.718 |
Token | � |
Token ID | 564 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
IDER | +2.340 |
Random | +2.177 |
rl | +2.047 |
Rough | +2.044 |
ylum | +2.024 |
Neg logit contributions | |
aciously | -2.093 |
prevail | -2.040 |
elia | -1.934 |
Nadu | -1.900 |
itions | -1.858 |
Token | � |
Token ID | 250 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
IDER | +2.031 |
Random | +1.869 |
rl | +1.736 |
Rough | +1.731 |
ylum | +1.702 |
Neg logit contributions | |
aciously | -2.531 |
prevail | -2.478 |
elia | -2.367 |
Nadu | -2.343 |
itions | -2.294 |
Token | Exc |
Token ID | 40127 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
IDER | +1.764 |
Random | +1.599 |
rl | +1.484 |
Rough | +1.483 |
ylum | +1.470 |
Neg logit contributions | |
aciously | -2.386 |
prevail | -2.331 |
elia | -2.242 |
Nadu | -2.205 |
ged | -2.166 |
Token | use |
Token ID | 1904 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
IDER | +6.315 |
Random | +5.793 |
rl | +5.476 |
asions | +5.460 |
arted | +5.426 |
Neg logit contributions | |
aciously | -9.543 |
prevail | -9.430 |
Nadu | -9.143 |
elia | -8.922 |
eness | -8.885 |
Token | me |
Token ID | 502 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
IDER | +1.639 |
Random | +1.529 |
rl | +1.441 |
Rough | +1.439 |
ylum | +1.426 |
Neg logit contributions | |
aciously | -1.363 |
prevail | -1.327 |
elia | -1.255 |
Nadu | -1.234 |
itions | -1.204 |
Token | , |
Token ID | 11 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
aciously | +1.085 |
prevail | +1.057 |
elia | +1.003 |
Nadu | +0.986 |
ged | +0.961 |
Neg logit contributions | |
IDER | -1.243 |
Random | -1.155 |
acco | -1.085 |
rl | -1.081 |
ylum | -1.079 |
Token | but |
Token ID | 475 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
IDER | +1.460 |
Random | +1.351 |
rl | +1.265 |
acco | +1.252 |
ylum | +1.248 |
Neg logit contributions | |
aciously | -1.448 |
prevail | -1.423 |
elia | -1.345 |
Nadu | -1.326 |
itions | -1.293 |
Token | you |
Token ID | 345 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
IDER | +1.792 |
Random | +1.654 |
rl | +1.544 |
Rough | +1.531 |
acco | +1.527 |
Neg logit contributions | |
aciously | -1.834 |
prevail | -1.802 |
elia | -1.710 |
Nadu | -1.688 |
itions | -1.643 |
Token | groups |
Token ID | 2628 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
IDER | +3.488 |
Random | +3.246 |
Rough | +3.061 |
rl | +3.046 |
ylum | +3.022 |
Neg logit contributions | |
aciously | -3.136 |
prevail | -3.049 |
elia | -2.901 |
Nadu | -2.855 |
itions | -2.784 |
Token | of |
Token ID | 286 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
aciously | +0.128 |
prevail | +0.125 |
elia | +0.117 |
Nadu | +0.113 |
itions | +0.112 |
Neg logit contributions | |
IDER | -0.184 |
Random | -0.172 |
rl | -0.163 |
Rough | -0.162 |
ylum | -0.161 |
Token | people |
Token ID | 661 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
IDER | +0.030 |
Random | +0.028 |
rl | +0.027 |
acco | +0.026 |
ylum | +0.026 |
Neg logit contributions | |
aciously | -0.023 |
prevail | -0.022 |
elia | -0.021 |
Nadu | -0.021 |
ged | -0.020 |
Token | who |
Token ID | 508 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
IDER | +1.479 |
Random | +1.373 |
rl | +1.292 |
Rough | +1.283 |
acco | +1.274 |
Neg logit contributions | |
aciously | -1.319 |
prevail | -1.290 |
elia | -1.218 |
Nadu | -1.194 |
itions | -1.171 |
Token | " |
Token ID | 366 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
IDER | +0.571 |
Random | +0.531 |
rl | +0.501 |
Rough | +0.498 |
ylum | +0.493 |
Neg logit contributions | |
aciously | -0.471 |
prevail | -0.465 |
elia | -0.433 |
Nadu | -0.424 |
itions | -0.418 |
Token | inv |
Token ID | 16340 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
aciously | +0.452 |
prevail | +0.437 |
elia | +0.418 |
Nadu | +0.405 |
ged | +0.404 |
Neg logit contributions | |
IDER | -0.478 |
Random | -0.439 |
Rough | -0.415 |
rl | -0.410 |
ylum | -0.409 |
Token | ade |
Token ID | 671 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
IDER | +9.406 |
Random | +8.644 |
aders | +8.616 |
asions | +8.526 |
rl | +8.379 |
Neg logit contributions | |
prevail | -6.793 |
aciously | -6.474 |
Nadu | -6.304 |
elia | -6.046 |
ged | -5.882 |
Token | our |
Token ID | 674 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
IDER | +0.736 |
Random | +0.675 |
rl | +0.632 |
Rough | +0.629 |
acco | +0.624 |
Neg logit contributions | |
aciously | -0.754 |
prevail | -0.734 |
elia | -0.695 |
Nadu | -0.682 |
ged | -0.673 |
Token | communities |
Token ID | 5348 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
aciously | +2.675 |
prevail | +2.622 |
elia | +2.493 |
Nadu | +2.432 |
ged | +2.415 |
Neg logit contributions | |
IDER | -2.848 |
Random | -2.630 |
rl | -2.483 |
afort | -2.444 |
ylum | -2.442 |
Token | pre |
Token ID | 662 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
aciously | +0.939 |
prevail | +0.921 |
elia | +0.859 |
itions | +0.846 |
Nadu | +0.839 |
Neg logit contributions | |
IDER | -1.074 |
Random | -0.994 |
rl | -0.932 |
Rough | -0.926 |
acco | -0.924 |
Token | ying |
Token ID | 1112 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
IDER | +1.797 |
Random | +1.677 |
rl | +1.576 |
Rough | +1.572 |
ylum | +1.558 |
Neg logit contributions | |
aciously | -1.573 |
prevail | -1.537 |
elia | -1.452 |
Nadu | -1.430 |
itions | -1.389 |
Token | , |
Token ID | 11 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
IDER | +0.039 |
Random | +0.036 |
Rough | +0.034 |
rl | +0.034 |
ylum | +0.033 |
Neg logit contributions | |
aciously | -0.038 |
prevail | -0.037 |
elia | -0.036 |
Nadu | -0.035 |
itions | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
IDER | +1.255 |
Random | +1.169 |
rl | +1.101 |
Rough | +1.101 |
ylum | +1.089 |
Neg logit contributions | |
aciously | -1.060 |
prevail | -1.032 |
elia | -0.977 |
Nadu | -0.959 |
itions | -0.937 |
Token | author |
Token ID | 1772 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
IDER | +0.455 |
Random | +0.426 |
rl | +0.404 |
ylum | +0.402 |
acco | +0.399 |
Neg logit contributions | |
aciously | -0.338 |
prevail | -0.330 |
elia | -0.308 |
Nadu | -0.304 |
itions | -0.297 |
Token | , |
Token ID | 11 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
aciously | +2.275 |
prevail | +2.211 |
elia | +2.101 |
Nadu | +2.056 |
ged | +2.051 |
Neg logit contributions | |
IDER | -2.292 |
Random | -2.112 |
rl | -2.006 |
asions | -1.984 |
ylum | -1.983 |
Token | Michael |
Token ID | 3899 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
IDER | +0.191 |
Random | +0.178 |
rl | +0.169 |
Rough | +0.167 |
ylum | +0.167 |
Neg logit contributions | |
aciously | -0.145 |
prevail | -0.142 |
elia | -0.133 |
Nadu | -0.131 |
itions | -0.128 |
Token | Sche |
Token ID | 10011 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
IDER | +0.354 |
Random | +0.330 |
rl | +0.310 |
Rough | +0.308 |
ylum | +0.307 |
Neg logit contributions | |
aciously | -0.307 |
prevail | -0.299 |
elia | -0.284 |
Nadu | -0.279 |
itions | -0.272 |
Token | in |
Token ID | 259 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
IDER | +8.966 |
Random | +8.203 |
rl | +8.197 |
ylum | +7.981 |
aders | +7.948 |
Neg logit contributions | |
prevail | -7.236 |
aciously | -6.949 |
Nadu | -6.726 |
elia | -6.291 |
itions | -6.049 |
Token | , |
Token ID | 11 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
aciously | +0.510 |
prevail | +0.495 |
elia | +0.474 |
Nadu | +0.463 |
itions | +0.456 |
Neg logit contributions | |
IDER | -0.502 |
Random | -0.464 |
rl | -0.433 |
Rough | -0.433 |
ylum | -0.430 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
IDER | +0.155 |
Random | +0.143 |
rl | +0.135 |
ylum | +0.133 |
Rough | +0.133 |
Neg logit contributions | |
aciously | -0.164 |
prevail | -0.160 |
elia | -0.152 |
Nadu | -0.150 |
ged | -0.148 |
Token | the |
Token ID | 262 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
aciously | +0.298 |
prevail | +0.292 |
elia | +0.276 |
Nadu | +0.270 |
itions | +0.266 |
Neg logit contributions | |
IDER | -0.343 |
Random | -0.320 |
rl | -0.302 |
ylum | -0.297 |
Rough | -0.296 |
Token | argument |
Token ID | 4578 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
aciously | +0.578 |
prevail | +0.566 |
elia | +0.527 |
Nadu | +0.519 |
itions | +0.509 |
Neg logit contributions | |
IDER | -0.719 |
Random | -0.673 |
rl | -0.638 |
acco | -0.629 |
Rough | -0.628 |
Token | . |
Token ID | 13 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
IDER | +1.198 |
Random | +1.111 |
rl | +1.051 |
Rough | +1.045 |
ylum | +1.038 |
Neg logit contributions | |
aciously | -1.101 |
prevail | -1.068 |
elia | -1.017 |
Nadu | -1.001 |
itions | -0.977 |
Token | � |
Token ID | 447 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
IDER | +0.866 |
Random | +0.803 |
rl | +0.753 |
Rough | +0.749 |
acco | +0.747 |
Neg logit contributions | |
aciously | -0.827 |
prevail | -0.809 |
elia | -0.769 |
Nadu | -0.757 |
itions | -0.738 |
Token | � |
Token ID | 251 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
IDER | +0.870 |
Random | +0.798 |
rl | +0.740 |
Rough | +0.739 |
ylum | +0.730 |
Neg logit contributions | |
aciously | -1.108 |
prevail | -1.083 |
elia | -1.036 |
Nadu | -1.022 |
itions | -1.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
aciously | +0.647 |
prevail | +0.632 |
elia | +0.602 |
Nadu | +0.589 |
ged | +0.572 |
Neg logit contributions | |
IDER | -0.793 |
Random | -0.741 |
acco | -0.701 |
rl | -0.696 |
ylum | -0.692 |
Token |
|
Token ID | 198 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
IDER | +0.780 |
Random | +0.723 |
acco | +0.695 |
ylum | +0.693 |
Rough | +0.686 |
Neg logit contributions | |
aciously | -0.549 |
prevail | -0.529 |
elia | -0.509 |
Nadu | -0.493 |
ged | -0.492 |
Token | McC |
Token ID | 30464 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
IDER | +0.853 |
Random | +0.779 |
Rough | +0.727 |
rl | +0.724 |
acco | +0.720 |
Neg logit contributions | |
aciously | -1.075 |
prevail | -1.049 |
elia | -1.007 |
Nadu | -0.989 |
ged | -0.973 |
Token | ain |
Token ID | 391 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
IDER | +8.749 |
Random | +8.164 |
rl | +7.668 |
acco | +7.598 |
Rough | +7.581 |
Neg logit contributions | |
aciously | -7.719 |
prevail | -7.600 |
elia | -7.092 |
Nadu | -7.042 |
ged | -6.860 |
Token | continued |
Token ID | 3767 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
IDER | +3.569 |
Random | +3.306 |
rl | +3.113 |
Rough | +3.104 |
ylum | +3.061 |
Neg logit contributions | |
aciously | -3.493 |
prevail | -3.407 |
elia | -3.246 |
Nadu | -3.188 |
itions | -3.118 |
Token | to |
Token ID | 284 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
IDER | +1.146 |
Random | +1.065 |
rl | +1.004 |
Rough | +1.002 |
ylum | +0.991 |
Neg logit contributions | |
aciously | -1.036 |
prevail | -1.008 |
elia | -0.958 |
Nadu | -0.943 |
itions | -0.921 |
Token | defend |
Token ID | 4404 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
aciously | +0.319 |
prevail | +0.315 |
elia | +0.291 |
Nadu | +0.287 |
ged | +0.281 |
Neg logit contributions | |
IDER | -0.402 |
Random | -0.374 |
rl | -0.351 |
Rough | -0.350 |
acco | -0.349 |
Token | Obama |
Token ID | 2486 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
IDER | +1.242 |
Random | +1.155 |
Rough | +1.088 |
rl | +1.088 |
ylum | +1.076 |
Neg logit contributions | |
aciously | -1.101 |
prevail | -1.072 |
elia | -1.016 |
Nadu | -1.002 |
itions | -0.977 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
IDER | +0.125 |
Random | +0.117 |
rl | +0.111 |
ylum | +0.111 |
Rough | +0.110 |
Neg logit contributions | |
aciously | -0.083 |
prevail | -0.081 |
elia | -0.076 |
Nadu | -0.074 |
itions | -0.072 |
Token | ( |
Token ID | 357 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
aciously | +1.960 |
prevail | +1.921 |
elia | +1.794 |
Nadu | +1.768 |
itions | +1.723 |
Neg logit contributions | |
IDER | -2.602 |
Random | -2.438 |
ylum | -2.315 |
rl | -2.298 |
acco | -2.270 |
Token | Photo |
Token ID | 6191 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
aciously | +1.032 |
prevail | +1.006 |
elia | +0.972 |
Nadu | +0.959 |
ged | +0.943 |
Neg logit contributions | |
IDER | -0.690 |
Random | -0.619 |
ylum | -0.577 |
Rough | -0.574 |
rl | -0.572 |
Token | : |
Token ID | 25 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
aciously | +1.657 |
prevail | +1.597 |
elia | +1.519 |
ged | +1.466 |
Nadu | +1.457 |
Neg logit contributions | |
IDER | -2.799 |
Random | -2.607 |
acco | -2.528 |
ylum | -2.507 |
asive | -2.483 |
Token | Wayne |
Token ID | 13329 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
IDER | +1.291 |
Random | +1.204 |
Rough | +1.139 |
rl | +1.136 |
ylum | +1.119 |
Neg logit contributions | |
aciously | -1.044 |
prevail | -1.015 |
elia | -0.958 |
Nadu | -0.940 |
itions | -0.919 |
Token | McG |
Token ID | 11130 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
aciously | +1.421 |
prevail | +1.387 |
elia | +1.324 |
Nadu | +1.292 |
itions | +1.268 |
Neg logit contributions | |
IDER | -1.653 |
Random | -1.554 |
rl | -1.458 |
ylum | -1.450 |
Rough | -1.442 |
Token | a |
Token ID | 64 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
IDER | +7.350 |
Random | +6.810 |
rl | +6.611 |
ylum | +6.446 |
acco | +6.444 |
Neg logit contributions | |
prevail | -8.719 |
aciously | -8.471 |
Nadu | -8.144 |
elia | -7.761 |
ged | -7.563 |
Token | hee |
Token ID | 21067 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
IDER | +3.687 |
Random | +3.481 |
rl | +3.316 |
Rough | +3.306 |
ylum | +3.283 |
Neg logit contributions | |
aciously | -1.944 |
prevail | -1.886 |
elia | -1.739 |
Nadu | -1.710 |
itions | -1.643 |
Token | III |
Token ID | 6711 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
IDER | +3.027 |
Random | +2.779 |
Rough | +2.612 |
rl | +2.607 |
acco | +2.561 |
Neg logit contributions | |
aciously | -3.128 |
prevail | -3.050 |
elia | -2.920 |
Nadu | -2.873 |
itions | -2.796 |
Token | / |
Token ID | 14 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
IDER | +3.039 |
Random | +2.800 |
Rough | +2.623 |
rl | +2.618 |
acco | +2.574 |
Neg logit contributions | |
aciously | -3.125 |
prevail | -3.059 |
elia | -2.923 |
Nadu | -2.880 |
itions | -2.812 |
Token | Dem |
Token ID | 11522 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
IDER | +0.538 |
Random | +0.488 |
rl | +0.451 |
Rough | +0.450 |
ylum | +0.447 |
Neg logit contributions | |
aciously | -0.774 |
prevail | -0.759 |
elia | -0.727 |
Nadu | -0.717 |
ged | -0.705 |
Token | front |
Token ID | 2166 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
aciously | +0.327 |
prevail | +0.321 |
elia | +0.302 |
Nadu | +0.296 |
ged | +0.290 |
Neg logit contributions | |
IDER | -0.410 |
Random | -0.383 |
rl | -0.362 |
Rough | -0.359 |
ylum | -0.359 |
Token | group |
Token ID | 1448 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
aciously | +0.630 |
prevail | +0.619 |
elia | +0.577 |
Nadu | +0.567 |
ged | +0.557 |
Neg logit contributions | |
IDER | -0.843 |
Random | -0.791 |
rl | -0.745 |
Rough | -0.745 |
ylum | -0.739 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
aciously | +0.835 |
prevail | +0.814 |
elia | +0.766 |
Nadu | +0.756 |
ged | +0.743 |
Neg logit contributions | |
IDER | -0.999 |
Random | -0.936 |
rl | -0.878 |
Rough | -0.873 |
ylum | -0.870 |
Token |
|
Token ID | 198 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
IDER | +0.306 |
Random | +0.285 |
rl | +0.269 |
ylum | +0.267 |
acco | +0.267 |
Neg logit contributions | |
aciously | -0.264 |
prevail | -0.258 |
elia | -0.245 |
Nadu | -0.242 |
ged | -0.235 |
Token |
|
Token ID | 198 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
IDER | +1.617 |
Random | +1.503 |
acco | +1.430 |
ylum | +1.428 |
rl | +1.421 |
Neg logit contributions | |
aciously | -1.191 |
prevail | -1.149 |
elia | -1.098 |
Nadu | -1.071 |
ged | -1.060 |
Token | Sch |
Token ID | 14874 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
IDER | +1.243 |
Random | +1.121 |
Rough | +1.043 |
rl | +1.038 |
ylum | +1.035 |
Neg logit contributions | |
aciously | -1.845 |
prevail | -1.801 |
elia | -1.735 |
Nadu | -1.711 |
ged | -1.686 |
Token | w |
Token ID | 86 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
IDER | +8.328 |
Random | +7.966 |
rl | +7.574 |
arted | +7.467 |
acco | +7.408 |
Neg logit contributions | |
prevail | -7.649 |
aciously | -7.597 |
elia | -7.066 |
Nadu | -7.030 |
ged | -6.740 |
Token | artz |
Token ID | 13636 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
IDER | +0.579 |
Random | +0.500 |
Rough | +0.468 |
rl | +0.421 |
Rap | +0.407 |
Neg logit contributions | |
aciously | -1.675 |
prevail | -1.611 |
elia | -1.599 |
itions | -1.566 |
eness | -1.559 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
IDER | +2.647 |
Random | +2.435 |
rl | +2.281 |
Rough | +2.281 |
ylum | +2.256 |
Neg logit contributions | |
aciously | -2.930 |
prevail | -2.857 |
elia | -2.744 |
Nadu | -2.692 |
itions | -2.634 |
Token | a |
Token ID | 257 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
IDER | +0.244 |
Random | +0.228 |
rl | +0.214 |
Rough | +0.211 |
ylum | +0.211 |
Neg logit contributions | |
aciously | -0.230 |
prevail | -0.227 |
elia | -0.212 |
Nadu | -0.211 |
itions | -0.206 |
Token | former |
Token ID | 1966 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
aciously | +1.314 |
prevail | +1.286 |
elia | +1.196 |
Nadu | +1.169 |
ged | +1.163 |
Neg logit contributions | |
IDER | -1.923 |
Random | -1.799 |
rl | -1.706 |
ylum | -1.696 |
asions | -1.681 |
Token | But |
Token ID | 1537 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
IDER | +0.087 |
Random | +0.081 |
Rough | +0.077 |
rl | +0.077 |
acco | +0.076 |
Neg logit contributions | |
aciously | -0.070 |
prevail | -0.067 |
elia | -0.064 |
Nadu | -0.063 |
ged | -0.061 |
Token | DON |
Token ID | 23917 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
aciously | +0.032 |
prevail | +0.032 |
elia | +0.030 |
Nadu | +0.029 |
itions | +0.029 |
Neg logit contributions | |
IDER | -0.036 |
Random | -0.033 |
rl | -0.031 |
acco | -0.031 |
ylum | -0.031 |
Token | � |
Token ID | 447 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
aciously | +4.567 |
prevail | +4.562 |
elia | +4.234 |
eness | +4.190 |
Nadu | +4.169 |
Neg logit contributions | |
IDER | -5.400 |
Random | -5.146 |
ylum | -5.075 |
acco | -4.946 |
rl | -4.864 |
Token | � |
Token ID | 247 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
aciously | +0.569 |
prevail | +0.558 |
elia | +0.523 |
eness | +0.510 |
itions | +0.506 |
Neg logit contributions | |
IDER | -0.719 |
Random | -0.674 |
acco | -0.644 |
Rough | -0.634 |
asions | -0.628 |
Token | T |
Token ID | 51 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
aciously | +0.526 |
prevail | +0.512 |
elia | +0.486 |
Nadu | +0.477 |
itions | +0.469 |
Neg logit contributions | |
IDER | -0.572 |
Random | -0.532 |
Rough | -0.501 |
rl | -0.498 |
ylum | -0.497 |
Token | DO |
Token ID | 8410 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
prevail | +5.008 |
aciously | +4.913 |
Nadu | +4.547 |
elia | +4.381 |
ged | +4.335 |
Neg logit contributions | |
IDER | -5.736 |
Random | -5.353 |
ylum | -5.147 |
acco | -5.127 |
rl | -5.092 |
Token | IT |
Token ID | 7283 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
prevail | +4.287 |
aciously | +4.284 |
elia | +4.009 |
Nadu | +3.972 |
itions | +3.957 |
Neg logit contributions | |
IDER | -5.021 |
Random | -4.770 |
ylum | -4.685 |
acco | -4.605 |
arted | -4.556 |
Token | . |
Token ID | 13 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
aciously | +1.734 |
prevail | +1.710 |
elia | +1.599 |
Nadu | +1.583 |
itions | +1.538 |
Neg logit contributions | |
IDER | -2.238 |
Random | -2.107 |
ylum | -2.008 |
acco | -1.986 |
rl | -1.986 |
Token |
|
Token ID | 198 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
IDER | +0.223 |
Random | +0.207 |
acco | +0.197 |
rl | +0.196 |
ylum | +0.195 |
Neg logit contributions | |
aciously | -0.190 |
prevail | -0.186 |
elia | -0.175 |
Nadu | -0.174 |
ged | -0.169 |
Token |
|
Token ID | 198 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
IDER | +0.689 |
Random | +0.639 |
acco | +0.615 |
ylum | +0.614 |
Rough | +0.606 |
Neg logit contributions | |
aciously | -0.477 |
prevail | -0.458 |
elia | -0.442 |
Nadu | -0.428 |
ged | -0.427 |
Token | C |
Token ID | 34 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
IDER | +1.024 |
Random | +0.937 |
Rough | +0.885 |
rl | +0.880 |
acco | +0.877 |
Neg logit contributions | |
aciously | -1.114 |
prevail | -1.081 |
elia | -1.035 |
Nadu | -1.015 |
ged | -0.999 |
Token | continuous |
Token ID | 12948 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
IDER | +0.123 |
Random | +0.115 |
rl | +0.108 |
Rough | +0.108 |
acco | +0.107 |
Neg logit contributions | |
aciously | -0.105 |
prevail | -0.103 |
elia | -0.097 |
Nadu | -0.096 |
itions | -0.093 |
Token | cooperation |
Token ID | 11113 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
IDER | +0.212 |
Random | +0.198 |
rl | +0.187 |
Rough | +0.185 |
acco | +0.185 |
Neg logit contributions | |
aciously | -0.166 |
prevail | -0.162 |
elia | -0.152 |
Nadu | -0.150 |
ged | -0.146 |
Token | to |
Token ID | 284 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
prevail | +4.143 |
aciously | +4.096 |
itions | +3.723 |
elia | +3.712 |
Nadu | +3.674 |
Neg logit contributions | |
IDER | -5.674 |
Random | -5.482 |
rl | -5.081 |
Rough | -5.022 |
acco | -5.022 |
Token | maintain |
Token ID | 5529 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
aciously | +0.773 |
prevail | +0.762 |
elia | +0.698 |
Nadu | +0.686 |
itions | +0.672 |
Neg logit contributions | |
IDER | -1.203 |
Random | -1.130 |
rl | -1.068 |
Rough | -1.063 |
ylum | -1.060 |
Token | regional |
Token ID | 7915 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
aciously | +0.161 |
prevail | +0.157 |
elia | +0.148 |
Nadu | +0.146 |
itions | +0.142 |
Neg logit contributions | |
IDER | -0.205 |
Random | -0.192 |
rl | -0.181 |
Rough | -0.180 |
acco | -0.179 |
Token | peace |
Token ID | 4167 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
aciously | +1.005 |
prevail | +0.987 |
Nadu | +0.919 |
elia | +0.917 |
itions | +0.897 |
Neg logit contributions | |
IDER | -1.216 |
Random | -1.132 |
rl | -1.066 |
acco | -1.058 |
Rough | -1.056 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
prevail | +4.413 |
aciously | +4.365 |
itions | +4.000 |
elia | +3.965 |
Nadu | +3.957 |
Neg logit contributions | |
IDER | -5.300 |
Random | -5.044 |
Rough | -4.720 |
acco | -4.611 |
rl | -4.601 |
Token | stability |
Token ID | 10159 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
IDER | +0.037 |
Random | +0.035 |
rl | +0.033 |
Rough | +0.033 |
acco | +0.032 |
Neg logit contributions | |
aciously | -0.030 |
prevail | -0.030 |
elia | -0.027 |
Nadu | -0.027 |
itions | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
aciously | +2.010 |
prevail | +1.950 |
elia | +1.876 |
Nadu | +1.841 |
ged | +1.798 |
Neg logit contributions | |
IDER | -1.840 |
Random | -1.688 |
rl | -1.584 |
Rough | -1.573 |
ylum | -1.571 |
Token | prosperity |
Token ID | 19519 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
aciously | +0.397 |
prevail | +0.390 |
elia | +0.367 |
Nadu | +0.363 |
itions | +0.356 |
Neg logit contributions | |
IDER | -0.407 |
Random | -0.378 |
rl | -0.354 |
Rough | -0.353 |
acco | -0.350 |
Token | in |
Token ID | 287 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
prevail | +2.815 |
aciously | +2.801 |
elia | +2.583 |
Nadu | +2.558 |
itions | +2.513 |
Neg logit contributions | |
IDER | -3.652 |
Random | -3.450 |
rl | -3.226 |
Rough | -3.225 |
acco | -3.195 |
Token |
|
Token ID | 198 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
aciously | +0.457 |
prevail | +0.446 |
elia | +0.422 |
Nadu | +0.416 |
ged | +0.404 |
Neg logit contributions | |
IDER | -0.570 |
Random | -0.533 |
rl | -0.502 |
Rough | -0.498 |
ylum | -0.497 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
aciously | +0.467 |
prevail | +0.446 |
elia | +0.432 |
ged | +0.421 |
Nadu | +0.417 |
Neg logit contributions | |
IDER | -0.719 |
Random | -0.666 |
acco | -0.648 |
ylum | -0.645 |
afort | -0.636 |
Token | Today |
Token ID | 8888 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
aciously | +0.356 |
prevail | +0.346 |
elia | +0.335 |
Nadu | +0.330 |
ged | +0.328 |
Neg logit contributions | |
IDER | -0.265 |
Random | -0.239 |
Rough | -0.226 |
acco | -0.222 |
ylum | -0.222 |
Token | , |
Token ID | 11 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
aciously | +2.471 |
prevail | +2.449 |
elia | +2.297 |
Nadu | +2.289 |
ged | +2.233 |
Neg logit contributions | |
IDER | -2.754 |
Random | -2.568 |
rl | -2.391 |
ylum | -2.360 |
Rough | -2.355 |
Token | local |
Token ID | 1957 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
aciously | +0.765 |
prevail | +0.761 |
Nadu | +0.708 |
elia | +0.707 |
ged | +0.688 |
Neg logit contributions | |
IDER | -0.942 |
Random | -0.884 |
rl | -0.831 |
arted | -0.818 |
asions | -0.814 |
Token | news |
Token ID | 1705 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
aciously | +2.877 |
prevail | +2.856 |
Nadu | +2.682 |
elia | +2.653 |
itions | +2.603 |
Neg logit contributions | |
IDER | -3.860 |
Random | -3.622 |
rl | -3.406 |
ylum | -3.387 |
afort | -3.374 |
Token | media |
Token ID | 2056 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
prevail | +4.188 |
aciously | +4.167 |
elia | +3.789 |
itions | +3.721 |
Nadu | +3.693 |
Neg logit contributions | |
IDER | -5.442 |
Random | -5.122 |
ylum | -4.830 |
rl | -4.816 |
Rough | -4.804 |
Token | report |
Token ID | 989 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
IDER | +0.854 |
Random | +0.795 |
rl | +0.751 |
Rough | +0.748 |
ylum | +0.744 |
Neg logit contributions | |
aciously | -0.691 |
prevail | -0.679 |
elia | -0.632 |
Nadu | -0.625 |
itions | -0.610 |
Token | that |
Token ID | 326 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
IDER | +1.082 |
Random | +1.001 |
rl | +0.939 |
Rough | +0.938 |
ylum | +0.928 |
Neg logit contributions | |
aciously | -1.082 |
prevail | -1.054 |
elia | -1.003 |
Nadu | -0.988 |
itions | -0.966 |
Token | y |
Token ID | 331 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
IDER | +1.383 |
Random | +1.289 |
rl | +1.214 |
Rough | +1.211 |
ylum | +1.201 |
Neg logit contributions | |
aciously | -1.173 |
prevail | -1.144 |
elia | -1.082 |
Nadu | -1.063 |
itions | -1.038 |
Token | aku |
Token ID | 8719 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
aciously | +4.569 |
elia | +4.233 |
prevail | +4.145 |
itions | +4.137 |
ged | +4.045 |
Neg logit contributions | |
IDER | -4.828 |
Random | -4.541 |
Rough | -4.285 |
Rap | -4.169 |
rl | -4.103 |
Token | workers |
Token ID | 3259 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
aciously | +1.136 |
prevail | +1.110 |
elia | +1.040 |
Nadu | +1.027 |
itions | +1.007 |
Neg logit contributions | |
IDER | -1.477 |
Random | -1.379 |
rl | -1.300 |
acco | -1.292 |
asions | -1.283 |
Token | at |
Token ID | 379 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
aciously | +1.754 |
prevail | +1.736 |
elia | +1.628 |
Nadu | +1.606 |
ged | +1.577 |
Neg logit contributions | |
IDER | -2.237 |
Random | -2.101 |
acco | -1.970 |
rl | -1.961 |
arted | -1.956 |
Token | Manitoba |
Token ID | 28293 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
aciously | +0.951 |
prevail | +0.925 |
elia | +0.872 |
Nadu | +0.857 |
ged | +0.837 |
Neg logit contributions | |
IDER | -1.318 |
Random | -1.233 |
rl | -1.162 |
acco | -1.154 |
ylum | -1.152 |
Token | Hydro |
Token ID | 32116 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
aciously | +1.125 |
prevail | +1.093 |
elia | +1.027 |
Nadu | +1.006 |
itions | +0.981 |
Neg logit contributions | |
IDER | -1.553 |
Random | -1.456 |
Rough | -1.383 |
rl | -1.379 |
ylum | -1.365 |
Token | . |
Token ID | 13 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
IDER | +0.195 |
Random | +0.181 |
rl | +0.171 |
Rough | +0.170 |
ylum | +0.169 |
Neg logit contributions | |
aciously | -0.170 |
prevail | -0.166 |
elia | -0.157 |
Nadu | -0.154 |
itions | -0.151 |
Token | Union |
Token ID | 4479 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
aciously | +0.803 |
prevail | +0.784 |
elia | +0.745 |
Nadu | +0.736 |
ged | +0.717 |
Neg logit contributions | |
IDER | -0.960 |
Random | -0.895 |
rl | -0.841 |
acco | -0.839 |
ylum | -0.834 |
Token | spokesperson |
Token ID | 11821 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
aciously | +4.700 |
prevail | +4.619 |
ged | +4.423 |
Nadu | +4.387 |
elia | +4.314 |
Neg logit contributions | |
IDER | -6.041 |
Random | -5.712 |
asions | -5.330 |
ylum | -5.329 |
rl | -5.308 |
Token | and |
Token ID | 290 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
aciously | +3.494 |
prevail | +3.353 |
elia | +3.236 |
Nadu | +3.155 |
ged | +3.106 |
Neg logit contributions | |
IDER | -4.816 |
Random | -4.550 |
rl | -4.227 |
asions | -4.211 |
acco | -4.211 |
Token | business |
Token ID | 1597 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aciously | +1.285 |
prevail | +1.259 |
elia | +1.181 |
Nadu | +1.173 |
ged | +1.147 |
Neg logit contributions | |
IDER | -1.705 |
Random | -1.605 |
rl | -1.506 |
acco | -1.496 |
asions | -1.491 |
Token | manager |
Token ID | 4706 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
aciously | +0.638 |
prevail | +0.625 |
elia | +0.583 |
Nadu | +0.576 |
itions | +0.567 |
Neg logit contributions | |
IDER | -0.839 |
Random | -0.792 |
rl | -0.743 |
Rough | -0.740 |
ylum | -0.740 |
Token | Mike |
Token ID | 4995 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
aciously | +2.417 |
prevail | +2.336 |
elia | +2.236 |
Nadu | +2.177 |
ged | +2.126 |
Neg logit contributions | |
IDER | -3.261 |
Random | -3.076 |
rl | -2.879 |
acco | -2.850 |
asions | -2.840 |
Token | ipp |
Token ID | 3974 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
IDER | +0.651 |
Random | +0.590 |
Rough | +0.551 |
rl | +0.543 |
ylum | +0.538 |
Neg logit contributions | |
aciously | -0.791 |
prevail | -0.754 |
elia | -0.746 |
itions | -0.723 |
eness | -0.718 |
Token | in |
Token ID | 259 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
IDER | +2.800 |
Random | +2.532 |
Rough | +2.321 |
rl | +2.318 |
ylum | +2.288 |
Neg logit contributions | |
aciously | -4.326 |
prevail | -4.236 |
elia | -4.074 |
Nadu | -4.014 |
itions | -3.950 |
Token | are |
Token ID | 389 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
IDER | +0.121 |
Random | +0.112 |
rl | +0.105 |
Rough | +0.104 |
ylum | +0.103 |
Neg logit contributions | |
aciously | -0.118 |
prevail | -0.117 |
elia | -0.109 |
Nadu | -0.107 |
ged | -0.105 |
Token | safe |
Token ID | 3338 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
aciously | +0.464 |
prevail | +0.457 |
elia | +0.429 |
Nadu | +0.413 |
ged | +0.408 |
Neg logit contributions | |
IDER | -0.608 |
Random | -0.572 |
rl | -0.541 |
acco | -0.533 |
ylum | -0.529 |
Token | . |
Token ID | 13 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
IDER | +1.141 |
Random | +1.061 |
rl | +0.996 |
Rough | +0.994 |
ylum | +0.984 |
Neg logit contributions | |
aciously | -1.049 |
prevail | -1.025 |
elia | -0.970 |
Nadu | -0.954 |
itions | -0.933 |
Token | Together |
Token ID | 17083 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
aciously | +0.180 |
prevail | +0.178 |
elia | +0.170 |
Nadu | +0.165 |
ged | +0.163 |
Neg logit contributions | |
IDER | -0.225 |
Random | -0.210 |
acco | -0.201 |
rl | -0.200 |
ylum | -0.198 |
Token | they |
Token ID | 484 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
prevail | +5.412 |
aciously | +5.329 |
elia | +5.035 |
ged | +4.858 |
itions | +4.858 |
Neg logit contributions | |
IDER | -5.997 |
Random | -5.677 |
rl | -5.360 |
ylum | -5.260 |
acco | -5.243 |
Token | ride |
Token ID | 6594 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
prevail | +0.895 |
aciously | +0.880 |
elia | +0.803 |
Nadu | +0.785 |
itions | +0.777 |
Neg logit contributions | |
IDER | -1.231 |
Random | -1.165 |
rl | -1.099 |
Rough | -1.087 |
ylum | -1.078 |
Token | to |
Token ID | 284 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
aciously | +0.644 |
prevail | +0.632 |
elia | +0.589 |
Nadu | +0.578 |
ged | +0.572 |
Neg logit contributions | |
IDER | -0.722 |
Random | -0.675 |
rl | -0.635 |
ylum | -0.627 |
acco | -0.626 |
Token | Ed |
Token ID | 1717 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
aciously | +0.766 |
prevail | +0.756 |
elia | +0.713 |
Nadu | +0.694 |
ged | +0.684 |
Neg logit contributions | |
IDER | -0.884 |
Random | -0.825 |
rl | -0.775 |
ylum | -0.766 |
acco | -0.763 |
Token | oras |
Token ID | 41043 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
aciously | +4.880 |
prevail | +4.731 |
ged | +4.629 |
elia | +4.590 |
ging | +4.549 |
Neg logit contributions | |
IDER | -4.909 |
Random | -4.358 |
acco | -4.074 |
asions | -4.072 |
asive | -4.055 |
Token | would |
Token ID | 561 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
IDER | +1.704 |
Random | +1.566 |
rl | +1.462 |
Rough | +1.449 |
ylum | +1.440 |
Neg logit contributions | |
aciously | -1.967 |
prevail | -1.930 |
elia | -1.828 |
Nadu | -1.807 |
ged | -1.771 |
Token | only |
Token ID | 691 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
prevail | +0.869 |
aciously | +0.867 |
elia | +0.773 |
Nadu | +0.770 |
ged | +0.756 |
Neg logit contributions | |
IDER | -1.219 |
Random | -1.145 |
rl | -1.074 |
Rap | -1.066 |
ylum | -1.063 |
Token | be |
Token ID | 307 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
aciously | +0.367 |
prevail | +0.364 |
elia | +0.330 |
Nadu | +0.327 |
ged | +0.319 |
Neg logit contributions | |
IDER | -0.525 |
Random | -0.495 |
rl | -0.465 |
ylum | -0.462 |
Rough | -0.461 |
Token | able |
Token ID | 1498 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
aciously | +1.770 |
prevail | +1.745 |
elia | +1.605 |
Nadu | +1.594 |
ged | +1.561 |
Neg logit contributions | |
IDER | -2.496 |
Random | -2.360 |
rl | -2.232 |
asions | -2.219 |
acco | -2.196 |
Token | to |
Token ID | 284 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
prevail | +2.136 |
aciously | +2.127 |
ged | +1.877 |
elia | +1.876 |
itions | +1.848 |
Neg logit contributions | |
IDER | -3.267 |
Random | -3.050 |
Rough | -2.861 |
Rap | -2.851 |
asions | -2.834 |
Token | pay |
Token ID | 1414 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
aciously | +1.512 |
prevail | +1.505 |
elia | +1.386 |
Nadu | +1.368 |
ged | +1.356 |
Neg logit contributions | |
IDER | -1.425 |
Random | -1.319 |
rl | -1.225 |
ylum | -1.220 |
Rap | -1.207 |
Token | as |
Token ID | 355 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
aciously | +2.118 |
prevail | +2.074 |
elia | +1.950 |
ged | +1.916 |
Nadu | +1.912 |
Neg logit contributions | |
IDER | -2.438 |
Random | -2.266 |
rl | -2.150 |
Rap | -2.096 |
acco | -2.092 |
Token | many |
Token ID | 867 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
IDER | +0.442 |
Random | +0.413 |
rl | +0.392 |
Rough | +0.389 |
acco | +0.386 |
Neg logit contributions | |
aciously | -0.323 |
prevail | -0.315 |
elia | -0.296 |
Nadu | -0.289 |
ged | -0.283 |
Token | bills |
Token ID | 9024 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
aciously | +2.439 |
prevail | +2.370 |
elia | +2.241 |
Nadu | +2.188 |
ged | +2.178 |
Neg logit contributions | |
IDER | -2.447 |
Random | -2.267 |
rl | -2.163 |
acco | -2.107 |
Rap | -2.096 |
Token | as |
Token ID | 355 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
IDER | +0.720 |
Random | +0.670 |
rl | +0.628 |
Rough | +0.623 |
acco | +0.616 |
Neg logit contributions | |
aciously | -0.715 |
prevail | -0.700 |
elia | -0.664 |
Nadu | -0.652 |
ged | -0.640 |
Token | it |
Token ID | 340 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
IDER | +1.626 |
Random | +1.495 |
rl | +1.391 |
Rough | +1.391 |
ylum | +1.375 |
Neg logit contributions | |
aciously | -1.921 |
prevail | -1.877 |
elia | -1.793 |
Nadu | -1.767 |
itions | -1.732 |
Token | really |
Token ID | 1107 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
IDER | +1.520 |
Random | +1.397 |
rl | +1.299 |
Rough | +1.295 |
ylum | +1.282 |
Neg logit contributions | |
aciously | -1.816 |
prevail | -1.779 |
elia | -1.695 |
Nadu | -1.672 |
itions | -1.639 |
Token | became |
Token ID | 2627 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
IDER | +3.850 |
Random | +3.454 |
Rough | +3.231 |
rl | +3.216 |
ylum | +3.187 |
Neg logit contributions | |
aciously | -5.702 |
prevail | -5.473 |
elia | -5.359 |
Nadu | -5.249 |
itions | -5.151 |
Token | a |
Token ID | 257 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
IDER | +2.557 |
Random | +2.375 |
rl | +2.233 |
Rough | +2.224 |
ylum | +2.204 |
Neg logit contributions | |
aciously | -2.354 |
prevail | -2.306 |
elia | -2.177 |
Nadu | -2.145 |
itions | -2.094 |
Token | nationwide |
Token ID | 13673 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
aciously | +0.500 |
prevail | +0.499 |
elia | +0.466 |
Nadu | +0.457 |
ged | +0.456 |
Neg logit contributions | |
IDER | -0.562 |
Random | -0.526 |
rl | -0.492 |
ylum | -0.490 |
Rough | -0.489 |
Token | man |
Token ID | 582 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
IDER | +1.731 |
Random | +1.603 |
rl | +1.495 |
Rough | +1.487 |
ylum | +1.477 |
Neg logit contributions | |
aciously | -1.783 |
prevail | -1.763 |
elia | -1.660 |
Nadu | -1.641 |
ged | -1.612 |
Token | ia |
Token ID | 544 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
aciously | +0.206 |
prevail | +0.201 |
elia | +0.191 |
Nadu | +0.190 |
itions | +0.185 |
Neg logit contributions | |
IDER | -0.194 |
Random | -0.179 |
rl | -0.169 |
ylum | -0.167 |
Rough | -0.167 |
Token | and |
Token ID | 290 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
prevail | +2.058 |
aciously | +2.038 |
elia | +1.868 |
Nadu | +1.862 |
ged | +1.824 |
Neg logit contributions | |
IDER | -2.708 |
Random | -2.536 |
Rough | -2.378 |
rl | -2.370 |
ylum | -2.359 |
Token | sentencing |
Token ID | 20565 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
IDER | +0.236 |
Random | +0.220 |
rl | +0.206 |
acco | +0.203 |
Rough | +0.203 |
Neg logit contributions | |
aciously | -0.207 |
prevail | -0.206 |
Nadu | -0.191 |
elia | -0.190 |
ged | -0.186 |
Token | became |
Token ID | 2627 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
IDER | +0.611 |
Random | +0.566 |
rl | +0.534 |
Rough | +0.527 |
ylum | +0.526 |
Neg logit contributions | |
aciously | -0.578 |
prevail | -0.568 |
elia | -0.533 |
Nadu | -0.526 |
itions | -0.516 |
Token | long |
Token ID | 890 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
IDER | +2.147 |
Random | +2.005 |
rl | +1.891 |
Rough | +1.888 |
ylum | +1.871 |
Neg logit contributions | |
aciously | -1.730 |
prevail | -1.683 |
elia | -1.591 |
Nadu | -1.561 |
itions | -1.524 |
Token | and |
Token ID | 290 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
IDER | +0.757 |
Random | +0.704 |
rl | +0.660 |
Rough | +0.658 |
ylum | +0.652 |
Neg logit contributions | |
aciously | -0.708 |
prevail | -0.691 |
elia | -0.654 |
Nadu | -0.645 |
itions | -0.630 |
Token | in |
Token ID | 287 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
IDER | +0.387 |
Random | +0.361 |
rl | +0.340 |
Rough | +0.339 |
ylum | +0.336 |
Neg logit contributions | |
aciously | -0.325 |
prevail | -0.317 |
elia | -0.299 |
Nadu | -0.294 |
itions | -0.287 |
Token | July |
Token ID | 2901 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
aciously | +0.222 |
prevail | +0.215 |
elia | +0.197 |
Nadu | +0.192 |
itions | +0.184 |
Neg logit contributions | |
IDER | -0.525 |
Random | -0.496 |
rl | -0.476 |
acco | -0.471 |
Rough | -0.471 |
Token | , |
Token ID | 11 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
aciously | +2.234 |
prevail | +2.189 |
Nadu | +2.019 |
elia | +2.000 |
itions | +1.951 |
Neg logit contributions | |
IDER | -3.208 |
Random | -3.007 |
rl | -2.862 |
ylum | -2.821 |
acco | -2.810 |
Token | seeking |
Token ID | 6095 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
aciously | +0.012 |
prevail | +0.011 |
elia | +0.011 |
Nadu | +0.010 |
itions | +0.010 |
Neg logit contributions | |
IDER | -0.015 |
Random | -0.014 |
rl | -0.013 |
Rough | -0.013 |
acco | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
IDER | +2.052 |
Random | +1.915 |
rl | +1.803 |
Rough | +1.802 |
ylum | +1.787 |
Neg logit contributions | |
aciously | -1.791 |
prevail | -1.741 |
elia | -1.654 |
Nadu | -1.621 |
itions | -1.583 |
Token | force |
Token ID | 2700 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
prevail | +1.349 |
aciously | +1.330 |
Nadu | +1.198 |
elia | +1.186 |
ged | +1.162 |
Neg logit contributions | |
IDER | -1.910 |
Random | -1.774 |
rl | -1.675 |
acco | -1.665 |
Rough | -1.663 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
aciously | +0.404 |
prevail | +0.394 |
elia | +0.374 |
Nadu | +0.368 |
itions | +0.360 |
Neg logit contributions | |
IDER | -0.417 |
Random | -0.387 |
rl | -0.363 |
Rough | -0.363 |
ylum | -0.359 |
Token | agency |
Token ID | 4086 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
aciously | +0.353 |
prevail | +0.346 |
elia | +0.329 |
Nadu | +0.324 |
itions | +0.317 |
Neg logit contributions | |
IDER | -0.321 |
Random | -0.296 |
rl | -0.277 |
Rough | -0.275 |
ylum | -0.273 |
Token | to |
Token ID | 284 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
IDER | +2.508 |
Random | +2.336 |
rl | +2.221 |
acco | +2.184 |
Rough | +2.180 |
Neg logit contributions | |
aciously | -2.619 |
prevail | -2.515 |
elia | -2.473 |
Nadu | -2.406 |
itions | -2.359 |
Token | finish |
Token ID | 5461 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
aciously | +0.586 |
prevail | +0.584 |
elia | +0.531 |
Nadu | +0.523 |
itions | +0.517 |
Neg logit contributions | |
IDER | -0.804 |
Random | -0.755 |
rl | -0.710 |
Rough | -0.705 |
ylum | -0.704 |
Token | investigating |
Token ID | 10240 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
aciously | +1.340 |
prevail | +1.311 |
elia | +1.226 |
Nadu | +1.214 |
itions | +1.190 |
Neg logit contributions | |
IDER | -1.605 |
Random | -1.491 |
rl | -1.406 |
acco | -1.394 |
afort | -1.386 |
Token | and |
Token ID | 290 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
aciously | +0.837 |
prevail | +0.816 |
elia | +0.769 |
Nadu | +0.756 |
ged | +0.750 |
Neg logit contributions | |
IDER | -0.922 |
Random | -0.852 |
Rough | -0.800 |
ylum | -0.800 |
rl | -0.799 |
Token | reboot |
Token ID | 20149 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
IDER | +0.107 |
Random | +0.099 |
rl | +0.094 |
ylum | +0.094 |
Rough | +0.093 |
Neg logit contributions | |
aciously | -0.093 |
prevail | -0.092 |
elia | -0.085 |
Nadu | -0.084 |
ged | -0.083 |
Token | all |
Token ID | 477 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
aciously | +0.446 |
prevail | +0.433 |
elia | +0.409 |
Nadu | +0.398 |
ged | +0.395 |
Neg logit contributions | |
IDER | -0.528 |
Random | -0.490 |
Rough | -0.462 |
rl | -0.461 |
ylum | -0.460 |
Token | the |
Token ID | 262 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
aciously | +1.674 |
prevail | +1.632 |
elia | +1.521 |
Nadu | +1.480 |
ged | +1.479 |
Neg logit contributions | |
IDER | -2.190 |
Random | -2.032 |
rl | -1.929 |
ylum | -1.920 |
acco | -1.912 |
Token | time |
Token ID | 640 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
IDER | +0.767 |
Random | +0.710 |
rl | +0.668 |
Rough | +0.665 |
ylum | +0.662 |
Neg logit contributions | |
aciously | -0.719 |
prevail | -0.701 |
elia | -0.664 |
Nadu | -0.653 |
itions | -0.641 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
aciously | +0.888 |
prevail | +0.871 |
elia | +0.817 |
Nadu | +0.801 |
ged | +0.792 |
Neg logit contributions | |
IDER | -1.101 |
Random | -1.025 |
ylum | -0.969 |
rl | -0.964 |
acco | -0.964 |
Token | Since |
Token ID | 4619 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
aciously | +0.328 |
prevail | +0.323 |
elia | +0.306 |
Nadu | +0.304 |
ged | +0.297 |
Neg logit contributions | |
IDER | -0.392 |
Random | -0.363 |
ylum | -0.348 |
acco | -0.346 |
rl | -0.345 |
Token | the |
Token ID | 262 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
aciously | +1.034 |
prevail | +1.022 |
elia | +0.960 |
Nadu | +0.955 |
ged | +0.937 |
Neg logit contributions | |
IDER | -1.211 |
Random | -1.121 |
ylum | -1.059 |
rl | -1.057 |
Rough | -1.045 |
Token | kernel |
Token ID | 9720 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
aciously | +1.021 |
prevail | +1.008 |
elia | +0.950 |
Nadu | +0.946 |
itions | +0.931 |
Neg logit contributions | |
IDER | -0.989 |
Random | -0.902 |
ylum | -0.850 |
rl | -0.846 |
acco | -0.835 |
Token | needs |
Token ID | 2476 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
aciously | +2.162 |
prevail | +2.122 |
elia | +1.985 |
Nadu | +1.979 |
ged | +1.966 |
Neg logit contributions | |
IDER | -2.122 |
Random | -1.902 |
ylum | -1.820 |
asions | -1.798 |
rl | -1.790 |
Token | about |
Token ID | 546 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
IDER | +0.638 |
Random | +0.594 |
rl | +0.559 |
Rough | +0.558 |
ylum | +0.552 |
Neg logit contributions | |
aciously | -0.578 |
prevail | -0.564 |
elia | -0.534 |
Nadu | -0.525 |
itions | -0.513 |
Token | work |
Token ID | 670 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
IDER | +0.125 |
Random | +0.118 |
Rough | +0.111 |
rl | +0.111 |
ylum | +0.110 |
Neg logit contributions | |
aciously | -0.085 |
prevail | -0.084 |
elia | -0.076 |
Nadu | -0.075 |
itions | -0.074 |
Token | in |
Token ID | 287 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
aciously | +0.837 |
prevail | +0.818 |
elia | +0.765 |
Nadu | +0.754 |
itions | +0.742 |
Neg logit contributions | |
IDER | -1.008 |
Random | -0.942 |
rl | -0.887 |
ylum | -0.886 |
Rough | -0.882 |
Token | a |
Token ID | 257 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
aciously | +0.449 |
prevail | +0.439 |
elia | +0.412 |
Nadu | +0.403 |
itions | +0.397 |
Neg logit contributions | |
IDER | -0.575 |
Random | -0.535 |
ylum | -0.506 |
rl | -0.505 |
Rough | -0.501 |
Token | viable |
Token ID | 13971 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
aciously | +0.425 |
prevail | +0.419 |
elia | +0.391 |
Nadu | +0.380 |
ged | +0.377 |
Neg logit contributions | |
IDER | -0.550 |
Random | -0.515 |
rl | -0.487 |
ylum | -0.485 |
asions | -0.482 |
Token | , |
Token ID | 11 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
IDER | +3.388 |
Random | +3.156 |
rl | +2.983 |
Rough | +2.979 |
acco | +2.945 |
Neg logit contributions | |
aciously | -2.792 |
prevail | -2.710 |
elia | -2.570 |
Nadu | -2.523 |
itions | -2.458 |
Token | downtown |
Token ID | 9436 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
IDER | +2.247 |
Random | +2.097 |
rl | +1.979 |
Rough | +1.974 |
ylum | +1.959 |
Neg logit contributions | |
aciously | -1.805 |
prevail | -1.762 |
elia | -1.658 |
Nadu | -1.629 |
itions | -1.590 |
Token | business |
Token ID | 1597 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
aciously | +0.255 |
prevail | +0.252 |
elia | +0.235 |
Nadu | +0.230 |
ged | +0.227 |
Neg logit contributions | |
IDER | -0.314 |
Random | -0.295 |
rl | -0.277 |
asions | -0.276 |
ylum | -0.276 |
Token | that |
Token ID | 326 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
IDER | +1.783 |
Random | +1.663 |
rl | +1.567 |
Rough | +1.564 |
ylum | +1.550 |
Neg logit contributions | |
aciously | -1.493 |
prevail | -1.455 |
elia | -1.376 |
Nadu | -1.351 |
itions | -1.320 |
Token | contributes |
Token ID | 22625 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
IDER | +0.962 |
Random | +0.889 |
rl | +0.832 |
Rough | +0.829 |
ylum | +0.822 |
Neg logit contributions | |
aciously | -0.968 |
prevail | -0.959 |
elia | -0.897 |
Nadu | -0.887 |
itions | -0.868 |
Token | to |
Token ID | 284 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
aciously | +0.437 |
prevail | +0.426 |
elia | +0.401 |
Nadu | +0.395 |
itions | +0.388 |
Neg logit contributions | |
IDER | -0.505 |
Random | -0.469 |
rl | -0.443 |
ylum | -0.440 |
Rough | -0.440 |
Token | our |
Token ID | 674 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
aciously | +1.228 |
prevail | +1.207 |
elia | +1.130 |
Nadu | +1.107 |
ged | +1.086 |
Neg logit contributions | |
IDER | -1.558 |
Random | -1.450 |
rl | -1.371 |
ylum | -1.369 |
Rough | -1.354 |
Token | at |
Token ID | 379 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
IDER | +4.796 |
Random | +4.454 |
Rough | +4.202 |
rl | +4.181 |
ylum | +4.138 |
Neg logit contributions | |
aciously | -4.820 |
prevail | -4.680 |
elia | -4.483 |
Nadu | -4.415 |
itions | -4.283 |
Token | the |
Token ID | 262 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
aciously | +0.155 |
prevail | +0.152 |
elia | +0.145 |
Nadu | +0.142 |
itions | +0.139 |
Neg logit contributions | |
IDER | -0.195 |
Random | -0.179 |
rl | -0.170 |
ylum | -0.169 |
Rough | -0.169 |
Token | bottom |
Token ID | 4220 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
IDER | +0.152 |
Random | +0.141 |
rl | +0.133 |
Rough | +0.132 |
ylum | +0.132 |
Neg logit contributions | |
aciously | -0.128 |
prevail | -0.126 |
elia | -0.119 |
Nadu | -0.117 |
itions | -0.114 |
Token | in |
Token ID | 287 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
aciously | +1.277 |
prevail | +1.238 |
elia | +1.152 |
Nadu | +1.123 |
itions | +1.106 |
Neg logit contributions | |
IDER | -1.993 |
Random | -1.872 |
rl | -1.781 |
Rough | -1.774 |
ylum | -1.763 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
IDER | +0.858 |
Random | +0.799 |
rl | +0.753 |
Rough | +0.751 |
ylum | +0.746 |
Neg logit contributions | |
aciously | -0.719 |
prevail | -0.701 |
elia | -0.663 |
Nadu | -0.651 |
itions | -0.636 |
Token | similar |
Token ID | 2092 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
aciously | +0.235 |
prevail | +0.230 |
elia | +0.216 |
Nadu | +0.212 |
ged | +0.208 |
Neg logit contributions | |
IDER | -0.298 |
Random | -0.276 |
rl | -0.262 |
ylum | -0.261 |
Rough | -0.259 |
Token | fashion |
Token ID | 6977 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
IDER | +2.916 |
Random | +2.753 |
Rough | +2.618 |
rl | +2.616 |
ylum | +2.592 |
Neg logit contributions | |
aciously | -1.633 |
prevail | -1.576 |
elia | -1.469 |
Nadu | -1.433 |
itions | -1.388 |
Token | as |
Token ID | 355 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
aciously | +1.284 |
prevail | +1.261 |
elia | +1.186 |
Nadu | +1.163 |
ged | +1.147 |
Neg logit contributions | |
IDER | -1.458 |
Random | -1.351 |
rl | -1.274 |
ylum | -1.266 |
Rough | -1.265 |
Token | had |
Token ID | 550 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
IDER | +2.166 |
Random | +2.015 |
rl | +1.894 |
Rough | +1.892 |
ylum | +1.873 |
Neg logit contributions | |
aciously | -1.953 |
prevail | -1.903 |
elia | -1.805 |
Nadu | -1.773 |
itions | -1.734 |
Token | been |
Token ID | 587 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
IDER | +0.418 |
Random | +0.389 |
rl | +0.365 |
Rough | +0.364 |
ylum | +0.361 |
Neg logit contributions | |
aciously | -0.383 |
prevail | -0.374 |
elia | -0.354 |
Nadu | -0.349 |
itions | -0.341 |
Token | used |
Token ID | 973 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
aciously | +2.057 |
prevail | +2.034 |
elia | +1.911 |
Nadu | +1.876 |
ged | +1.854 |
Neg logit contributions | |
IDER | -2.155 |
Random | -1.990 |
rl | -1.895 |
Rough | -1.865 |
asions | -1.853 |
Token | amid |
Token ID | 10371 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
IDER | +3.560 |
Random | +3.311 |
Rough | +3.108 |
rl | +3.107 |
ylum | +3.086 |
Neg logit contributions | |
aciously | -3.283 |
prevail | -3.186 |
elia | -3.044 |
Nadu | -3.004 |
itions | -2.909 |
Token | the |
Token ID | 262 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
aciously | +0.998 |
prevail | +0.973 |
elia | +0.920 |
Nadu | +0.899 |
ged | +0.889 |
Neg logit contributions | |
IDER | -1.118 |
Random | -1.030 |
rl | -0.980 |
Rough | -0.970 |
acco | -0.967 |
Token | j |
Token ID | 474 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
IDER | +0.457 |
Random | +0.422 |
rl | +0.398 |
Rough | +0.395 |
acco | +0.392 |
Neg logit contributions | |
aciously | -0.441 |
prevail | -0.431 |
elia | -0.409 |
Nadu | -0.401 |
ged | -0.394 |
Token | umble |
Token ID | 10344 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
aciously | +1.552 |
prevail | +1.456 |
elia | +1.419 |
itions | +1.392 |
eness | +1.367 |
Neg logit contributions | |
IDER | -1.780 |
Random | -1.667 |
Rough | -1.565 |
rl | -1.533 |
ylum | -1.528 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
aciously | +2.147 |
prevail | +2.077 |
elia | +1.934 |
Nadu | +1.888 |
itions | +1.834 |
Neg logit contributions | |
IDER | -3.746 |
Random | -3.526 |
rl | -3.355 |
Rough | -3.350 |
ylum | -3.323 |
Token | images |
Token ID | 4263 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
IDER | +0.392 |
Random | +0.361 |
rl | +0.342 |
Rough | +0.338 |
ylum | +0.337 |
Neg logit contributions | |
aciously | -0.372 |
prevail | -0.364 |
elia | -0.343 |
Nadu | -0.337 |
ged | -0.332 |
Token | appearing |
Token ID | 12655 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
IDER | +0.116 |
Random | +0.108 |
rl | +0.101 |
Rough | +0.101 |
acco | +0.100 |
Neg logit contributions | |
aciously | -0.106 |
prevail | -0.103 |
elia | -0.098 |
Nadu | -0.096 |
ged | -0.094 |
Token | on |
Token ID | 319 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
IDER | +1.563 |
Random | +1.454 |
rl | +1.362 |
Rough | +1.355 |
ylum | +1.346 |
Neg logit contributions | |
aciously | -1.539 |
prevail | -1.497 |
elia | -1.431 |
Nadu | -1.409 |
itions | -1.377 |
Token | their |
Token ID | 511 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
aciously | +0.200 |
prevail | +0.196 |
elia | +0.185 |
Nadu | +0.182 |
itions | +0.179 |
Neg logit contributions | |
IDER | -0.218 |
Random | -0.202 |
rl | -0.190 |
Rough | -0.189 |
ylum | -0.188 |
Token | screens |
Token ID | 8947 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
aciously | +0.033 |
prevail | +0.032 |
elia | +0.031 |
Nadu | +0.030 |
itions | +0.030 |
Neg logit contributions | |
IDER | -0.037 |
Random | -0.034 |
rl | -0.032 |
ylum | -0.032 |
Rough | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
IDER | +3.192 |
Random | +2.960 |
rl | +2.799 |
Rough | +2.772 |
ylum | +2.761 |
Neg logit contributions | |
aciously | -2.905 |
prevail | -2.824 |
elia | -2.672 |
Nadu | -2.656 |
itions | -2.560 |
Token | - |
Token ID | 12 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
IDER | +5.305 |
Random | +4.923 |
rl | +4.654 |
Rough | +4.633 |
Rap | +4.565 |
Neg logit contributions | |
aciously | -5.736 |
prevail | -5.547 |
Nadu | -5.295 |
elia | -5.241 |
itions | -5.119 |
Token | confidence |
Token ID | 39745 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
IDER | +0.854 |
Random | +0.782 |
Rough | +0.733 |
rl | +0.731 |
ylum | +0.729 |
Neg logit contributions | |
aciously | -0.804 |
prevail | -0.782 |
elia | -0.754 |
ged | -0.725 |
Nadu | -0.724 |
Token | , |
Token ID | 11 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
IDER | +0.687 |
Random | +0.639 |
rl | +0.602 |
Rough | +0.599 |
acco | +0.596 |
Neg logit contributions | |
aciously | -0.604 |
prevail | -0.595 |
elia | -0.557 |
Nadu | -0.547 |
ged | -0.538 |
Token | that |
Token ID | 326 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
IDER | +1.626 |
Random | +1.510 |
rl | +1.419 |
Rough | +1.410 |
acco | +1.405 |
Neg logit contributions | |
aciously | -1.522 |
prevail | -1.497 |
elia | -1.405 |
Nadu | -1.383 |
itions | -1.356 |
Token | he |
Token ID | 339 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
IDER | +2.230 |
Random | +2.058 |
rl | +1.921 |
Rough | +1.917 |
ylum | +1.897 |
Neg logit contributions | |
aciously | -2.453 |
prevail | -2.397 |
elia | -2.285 |
Nadu | -2.249 |
itions | -2.204 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
IDER | +1.263 |
Random | +1.165 |
rl | +1.078 |
Rough | +1.077 |
acco | +1.061 |
Neg logit contributions | |
aciously | -1.489 |
prevail | -1.466 |
elia | -1.387 |
Nadu | -1.364 |
itions | -1.350 |
Token | to |
Token ID | 284 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
IDER | +0.409 |
Random | +0.380 |
Rough | +0.358 |
rl | +0.357 |
ylum | +0.354 |
Neg logit contributions | |
aciously | -0.371 |
prevail | -0.360 |
elia | -0.343 |
Nadu | -0.338 |
itions | -0.328 |
Token | address |
Token ID | 2209 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
prevail | +0.855 |
aciously | +0.847 |
elia | +0.761 |
ged | +0.747 |
Nadu | +0.742 |
Neg logit contributions | |
IDER | -1.262 |
Random | -1.182 |
rl | -1.113 |
ylum | -1.108 |
Rough | -1.107 |
Token | . |
Token ID | 13 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
IDER | +1.152 |
Random | +1.073 |
rl | +1.010 |
Rough | +1.008 |
ylum | +0.999 |
Neg logit contributions | |
aciously | -0.998 |
prevail | -0.973 |
elia | -0.921 |
Nadu | -0.906 |
itions | -0.884 |
Token | And |
Token ID | 843 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
IDER | +1.033 |
Random | +0.962 |
acco | +0.912 |
rl | +0.909 |
ylum | +0.905 |
Neg logit contributions | |
aciously | -0.877 |
prevail | -0.855 |
elia | -0.815 |
Nadu | -0.801 |
ged | -0.788 |
Token | he |
Token ID | 339 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
aciously | +0.834 |
prevail | +0.820 |
elia | +0.771 |
ged | +0.745 |
Nadu | +0.743 |
Neg logit contributions | |
IDER | -0.990 |
Random | -0.924 |
rl | -0.868 |
acco | -0.868 |
ylum | -0.865 |
Token | the |
Token ID | 262 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
IDER | +0.747 |
Random | +0.691 |
rl | +0.647 |
Rough | +0.644 |
ylum | +0.640 |
Neg logit contributions | |
aciously | -0.720 |
prevail | -0.708 |
elia | -0.667 |
Nadu | -0.659 |
ged | -0.646 |
Token | other |
Token ID | 584 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
IDER | +1.042 |
Random | +0.974 |
rl | +0.921 |
Rough | +0.917 |
ylum | +0.914 |
Neg logit contributions | |
aciously | -0.774 |
prevail | -0.754 |
elia | -0.708 |
Nadu | -0.696 |
itions | -0.679 |
Token | , |
Token ID | 11 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
IDER | +2.828 |
Random | +2.636 |
Rough | +2.485 |
rl | +2.480 |
ylum | +2.459 |
Neg logit contributions | |
aciously | -2.368 |
prevail | -2.292 |
elia | -2.188 |
Nadu | -2.141 |
itions | -2.091 |
Token | better |
Token ID | 1365 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
IDER | +1.552 |
Random | +1.437 |
rl | +1.345 |
Rough | +1.340 |
ylum | +1.329 |
Neg logit contributions | |
aciously | -1.574 |
prevail | -1.540 |
elia | -1.460 |
Nadu | -1.440 |
itions | -1.409 |
Token | way |
Token ID | 835 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
IDER | +3.871 |
Random | +3.591 |
rl | +3.405 |
Rough | +3.396 |
acco | +3.359 |
Neg logit contributions | |
aciously | -3.056 |
prevail | -2.942 |
elia | -2.833 |
Nadu | -2.759 |
itions | -2.681 |
Token | is |
Token ID | 318 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
IDER | +1.626 |
Random | +1.513 |
Rough | +1.424 |
rl | +1.424 |
ylum | +1.407 |
Neg logit contributions | |
aciously | -1.489 |
prevail | -1.434 |
elia | -1.374 |
Nadu | -1.357 |
itions | -1.314 |
Token | to |
Token ID | 284 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
IDER | +1.318 |
Random | +1.226 |
rl | +1.153 |
Rough | +1.150 |
ylum | +1.140 |
Neg logit contributions | |
aciously | -1.172 |
prevail | -1.143 |
elia | -1.083 |
Nadu | -1.064 |
itions | -1.040 |
Token | try |
Token ID | 1949 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
aciously | +0.320 |
prevail | +0.317 |
elia | +0.290 |
Nadu | +0.288 |
ged | +0.282 |
Neg logit contributions | |
IDER | -0.423 |
Random | -0.395 |
rl | -0.373 |
ylum | -0.370 |
Rough | -0.370 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
IDER | +0.543 |
Random | +0.504 |
rl | +0.474 |
Rough | +0.473 |
ylum | +0.469 |
Neg logit contributions | |
aciously | -0.503 |
prevail | -0.491 |
elia | -0.465 |
Nadu | -0.458 |
itions | -0.448 |
Token | understand |
Token ID | 1833 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
aciously | +0.239 |
prevail | +0.237 |
elia | +0.216 |
Nadu | +0.213 |
itions | +0.209 |
Neg logit contributions | |
IDER | -0.344 |
Random | -0.322 |
rl | -0.304 |
ylum | -0.303 |
Rough | -0.302 |
Token | both |
Token ID | 1111 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
IDER | +1.818 |
Random | +1.685 |
rl | +1.579 |
Rough | +1.575 |
ylum | +1.562 |
Neg logit contributions | |
aciously | -1.782 |
prevail | -1.741 |
elia | -1.652 |
Nadu | -1.626 |
itions | -1.591 |
Token | 'm |
Token ID | 1101 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
prevail | +0.344 |
aciously | +0.344 |
elia | +0.315 |
Nadu | +0.312 |
ged | +0.311 |
Neg logit contributions | |
IDER | -0.404 |
Random | -0.375 |
ylum | -0.355 |
rl | -0.351 |
Rough | -0.350 |
Token | just |
Token ID | 655 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
aciously | +1.319 |
prevail | +1.305 |
elia | +1.219 |
Nadu | +1.187 |
ged | +1.166 |
Neg logit contributions | |
IDER | -1.751 |
Random | -1.626 |
rl | -1.557 |
asions | -1.535 |
ylum | -1.523 |
Token | not |
Token ID | 407 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
IDER | +1.722 |
Random | +1.598 |
rl | +1.511 |
Rough | +1.501 |
ylum | +1.492 |
Neg logit contributions | |
aciously | -1.501 |
prevail | -1.466 |
elia | -1.385 |
Nadu | -1.363 |
itions | -1.331 |
Token | optimistic |
Token ID | 16915 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
IDER | +0.870 |
Random | +0.812 |
rl | +0.771 |
Rough | +0.762 |
ylum | +0.761 |
Neg logit contributions | |
aciously | -0.659 |
prevail | -0.646 |
elia | -0.605 |
Nadu | -0.594 |
ged | -0.581 |
Token | given |
Token ID | 1813 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
aciously | +1.660 |
prevail | +1.635 |
elia | +1.527 |
Nadu | +1.508 |
ged | +1.487 |
Neg logit contributions | |
IDER | -1.976 |
Random | -1.842 |
rl | -1.745 |
ylum | -1.738 |
asions | -1.707 |
Token | his |
Token ID | 465 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
IDER | +0.711 |
Random | +0.658 |
rl | +0.619 |
ylum | +0.614 |
Rough | +0.612 |
Neg logit contributions | |
aciously | -0.664 |
prevail | -0.649 |
elia | -0.616 |
Nadu | -0.603 |
itions | -0.592 |
Token | track |
Token ID | 2610 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
IDER | +0.331 |
Random | +0.309 |
rl | +0.292 |
ylum | +0.290 |
Rough | +0.287 |
Neg logit contributions | |
aciously | -0.274 |
prevail | -0.268 |
elia | -0.251 |
Nadu | -0.247 |
ged | -0.242 |
Token | record |
Token ID | 1700 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
IDER | +0.098 |
Random | +0.090 |
rl | +0.085 |
Rough | +0.084 |
ylum | +0.084 |
Neg logit contributions | |
aciously | -0.103 |
prevail | -0.101 |
elia | -0.096 |
Nadu | -0.095 |
itions | -0.093 |
Token | of |
Token ID | 286 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
IDER | +0.378 |
Random | +0.353 |
rl | +0.333 |
Rough | +0.332 |
ylum | +0.330 |
Neg logit contributions | |
aciously | -0.297 |
prevail | -0.289 |
elia | -0.273 |
Nadu | -0.267 |
itions | -0.262 |
Token | late |
Token ID | 2739 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
IDER | +1.050 |
Random | +0.975 |
rl | +0.919 |
ylum | +0.912 |
acco | +0.904 |
Neg logit contributions | |
aciously | -0.964 |
prevail | -0.947 |
elia | -0.888 |
Nadu | -0.871 |
ged | -0.857 |
Token | . |
Token ID | 13 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
aciously | +1.344 |
prevail | +1.320 |
elia | +1.233 |
Nadu | +1.211 |
ged | +1.199 |
Neg logit contributions | |
IDER | -1.609 |
Random | -1.494 |
rl | -1.413 |
ylum | -1.410 |
Rough | -1.400 |
Token | ES |
Token ID | 1546 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
prevail | +5.366 |
aciously | +5.298 |
elia | +5.044 |
Nadu | +5.026 |
eness | +5.018 |
Neg logit contributions | |
IDER | -4.002 |
Random | -3.823 |
ylum | -3.602 |
rl | -3.567 |
acco | -3.523 |
Token | LO |
Token ID | 17579 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
prevail | +1.528 |
aciously | +1.521 |
elia | +1.412 |
Nadu | +1.403 |
ged | +1.365 |
Neg logit contributions | |
IDER | -1.847 |
Random | -1.760 |
acco | -1.653 |
rl | -1.650 |
ylum | -1.643 |
Token | OM |
Token ID | 2662 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
prevail | +4.632 |
aciously | +4.603 |
elia | +4.356 |
Nadu | +4.310 |
ged | +4.281 |
Neg logit contributions | |
IDER | -3.438 |
Random | -3.314 |
rl | -3.179 |
acco | -3.158 |
ylum | -3.135 |
Token |
|
Token ID | 198 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
aciously | +2.974 |
prevail | +2.962 |
Nadu | +2.782 |
ged | +2.737 |
elia | +2.718 |
Neg logit contributions | |
IDER | -3.521 |
Random | -3.384 |
ylum | -3.255 |
acco | -3.233 |
rl | -3.210 |
Token |
|
Token ID | 198 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
aciously | +1.360 |
prevail | +1.316 |
elia | +1.278 |
ged | +1.258 |
Nadu | +1.230 |
Neg logit contributions | |
IDER | -2.331 |
Random | -2.155 |
acco | -2.118 |
ylum | -2.101 |
afort | -2.091 |
Token | Ra |
Token ID | 21762 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
aciously | +1.334 |
prevail | +1.297 |
elia | +1.265 |
ged | +1.243 |
Nadu | +1.240 |
Neg logit contributions | |
IDER | -0.996 |
Random | -0.885 |
ylum | -0.852 |
Rough | -0.848 |
acco | -0.846 |
Token | ising |
Token ID | 1710 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
IDER | +5.172 |
Random | +4.606 |
acco | +4.376 |
ylum | +4.358 |
aders | +4.334 |
Neg logit contributions | |
aciously | -6.203 |
prevail | -6.184 |
Nadu | -5.765 |
elia | -5.749 |
ged | -5.597 |
Token | the |
Token ID | 262 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
IDER | +4.372 |
Random | +3.995 |
Rough | +3.780 |
ylum | +3.761 |
acco | +3.700 |
Neg logit contributions | |
aciously | -4.837 |
prevail | -4.679 |
elia | -4.480 |
Nadu | -4.441 |
itions | -4.302 |
Token | debt |
Token ID | 5057 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
IDER | +0.942 |
Random | +0.857 |
Rough | +0.790 |
rl | +0.789 |
ylum | +0.780 |
Neg logit contributions | |
aciously | -1.354 |
prevail | -1.326 |
elia | -1.271 |
Nadu | -1.253 |
itions | -1.232 |
Token | ceiling |
Token ID | 13387 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
aciously | +0.405 |
prevail | +0.395 |
elia | +0.371 |
Nadu | +0.366 |
ged | +0.356 |
Neg logit contributions | |
IDER | -0.487 |
Random | -0.454 |
rl | -0.429 |
Rough | -0.427 |
ylum | -0.422 |
Token | is |
Token ID | 318 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
aciously | +1.710 |
prevail | +1.706 |
Nadu | +1.578 |
elia | +1.570 |
ged | +1.557 |
Neg logit contributions | |
IDER | -1.754 |
Random | -1.628 |
rl | -1.516 |
asions | -1.499 |
acco | -1.498 |
Token | that |
Token ID | 326 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
aciously | +1.698 |
prevail | +1.672 |
elia | +1.567 |
Nadu | +1.537 |
itions | +1.515 |
Neg logit contributions | |
IDER | -1.828 |
Random | -1.708 |
rl | -1.603 |
Rough | -1.589 |
acco | -1.580 |
Token | its |
Token ID | 663 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
IDER | +1.074 |
Random | +1.001 |
rl | +0.942 |
Rough | +0.935 |
acco | +0.928 |
Neg logit contributions | |
aciously | -0.954 |
prevail | -0.938 |
elia | -0.883 |
Nadu | -0.868 |
itions | -0.850 |
Token | success |
Token ID | 1943 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
prevail | +2.115 |
aciously | +2.111 |
elia | +1.929 |
Nadu | +1.922 |
eness | +1.885 |
Neg logit contributions | |
IDER | -2.640 |
Random | -2.468 |
rl | -2.339 |
acco | -2.309 |
afort | -2.301 |
Token | � |
Token ID | 564 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
prevail | +3.778 |
aciously | +3.769 |
elia | +3.519 |
Nadu | +3.455 |
itions | +3.451 |
Neg logit contributions | |
IDER | -3.688 |
Random | -3.470 |
Rough | -3.214 |
acco | -3.193 |
rl | -3.189 |
Token | � |
Token ID | 250 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
IDER | +0.671 |
Random | +0.621 |
rl | +0.583 |
Rough | +0.578 |
ylum | +0.573 |
Neg logit contributions | |
aciously | -0.725 |
prevail | -0.706 |
elia | -0.674 |
Nadu | -0.665 |
itions | -0.649 |
Token | dep |
Token ID | 10378 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
IDER | +1.408 |
Random | +1.300 |
Rough | +1.214 |
rl | +1.213 |
ylum | +1.197 |
Neg logit contributions | |
aciously | -1.493 |
prevail | -1.457 |
elia | -1.390 |
Nadu | -1.366 |
itions | -1.341 |
Token | ends |
Token ID | 2412 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
IDER | +4.105 |
Random | +3.733 |
arted | +3.686 |
rl | +3.500 |
Rap | +3.439 |
Neg logit contributions | |
aciously | -7.317 |
prevail | -7.247 |
Nadu | -6.961 |
elia | -6.852 |
eness | -6.665 |
Token | on |
Token ID | 319 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
IDER | +1.130 |
Random | +1.048 |
rl | +0.986 |
Rough | +0.985 |
ylum | +0.972 |
Neg logit contributions | |
aciously | -1.092 |
prevail | -1.066 |
elia | -1.017 |
Nadu | -0.995 |
itions | -0.974 |
Token | us |
Token ID | 514 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
aciously | +0.539 |
prevail | +0.538 |
elia | +0.501 |
Nadu | +0.489 |
ged | +0.482 |
Neg logit contributions | |
IDER | -0.603 |
Random | -0.564 |
rl | -0.528 |
acco | -0.523 |
Rough | -0.523 |
Token | all |
Token ID | 477 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
aciously | +3.276 |
prevail | +3.275 |
elia | +3.026 |
Nadu | +2.964 |
eness | +2.922 |
Neg logit contributions | |
IDER | -3.709 |
Random | -3.451 |
Rough | -3.252 |
acco | -3.227 |
arted | -3.180 |
Token | � |
Token ID | 447 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
aciously | +2.135 |
prevail | +2.111 |
elia | +1.951 |
Nadu | +1.933 |
itions | +1.884 |
Neg logit contributions | |
IDER | -2.533 |
Random | -2.365 |
Rough | -2.213 |
acco | -2.209 |
rl | -2.203 |
Token | local |
Token ID | 1957 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
aciously | +1.006 |
prevail | +0.990 |
elia | +0.925 |
Nadu | +0.915 |
ged | +0.898 |
Neg logit contributions | |
IDER | -1.285 |
Random | -1.199 |
rl | -1.132 |
acco | -1.119 |
asions | -1.119 |
Token | ordinance |
Token ID | 19784 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
aciously | +1.250 |
prevail | +1.244 |
Nadu | +1.154 |
elia | +1.149 |
itions | +1.119 |
Neg logit contributions | |
IDER | -1.663 |
Random | -1.550 |
rl | -1.464 |
asions | -1.462 |
afort | -1.460 |
Token | barring |
Token ID | 34928 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
prevail | +2.465 |
aciously | +2.429 |
ged | +2.208 |
Nadu | +2.200 |
elia | +2.198 |
Neg logit contributions | |
IDER | -3.076 |
Random | -2.868 |
rl | -2.698 |
asions | -2.694 |
acco | -2.685 |
Token | men |
Token ID | 1450 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
prevail | +1.417 |
aciously | +1.415 |
elia | +1.310 |
Nadu | +1.299 |
ged | +1.287 |
Neg logit contributions | |
IDER | -1.699 |
Random | -1.561 |
rl | -1.475 |
afort | -1.467 |
acco | -1.463 |
Token | from |
Token ID | 422 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
aciously | +0.868 |
prevail | +0.847 |
elia | +0.799 |
Nadu | +0.789 |
ged | +0.780 |
Neg logit contributions | |
IDER | -0.935 |
Random | -0.867 |
Rough | -0.810 |
rl | -0.810 |
ylum | -0.804 |
Token | entering |
Token ID | 8218 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
aciously | +0.265 |
prevail | +0.261 |
elia | +0.244 |
Nadu | +0.240 |
ged | +0.237 |
Neg logit contributions | |
IDER | -0.289 |
Random | -0.267 |
rl | -0.251 |
Rough | -0.249 |
ylum | -0.249 |
Token | women |
Token ID | 1466 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
IDER | +5.598 |
Random | +5.296 |
rl | +4.972 |
Rough | +4.968 |
ylum | +4.860 |
Neg logit contributions | |
aciously | -5.758 |
prevail | -5.581 |
elia | -5.492 |
Nadu | -5.297 |
itions | -5.179 |
Token | 's |
Token ID | 338 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
aciously | +0.928 |
prevail | +0.907 |
elia | +0.862 |
Nadu | +0.845 |
itions | +0.828 |
Neg logit contributions | |
IDER | -0.979 |
Random | -0.911 |
rl | -0.857 |
Rough | -0.854 |
ylum | -0.844 |
Token | restrooms |
Token ID | 48537 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
aciously | +0.153 |
prevail | +0.151 |
elia | +0.144 |
Nadu | +0.143 |
itions | +0.141 |
Neg logit contributions | |
IDER | -0.082 |
Random | -0.072 |
Rough | -0.065 |
ylum | -0.065 |
rl | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
IDER | +0.600 |
Random | +0.557 |
Rough | +0.522 |
rl | +0.522 |
ylum | +0.516 |
Neg logit contributions | |
aciously | -0.520 |
prevail | -0.511 |
elia | -0.476 |
Nadu | -0.472 |
ged | -0.465 |
Token | vice |
Token ID | 7927 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
aciously | +0.144 |
prevail | +0.144 |
elia | +0.134 |
Nadu | +0.133 |
ged | +0.131 |
Neg logit contributions | |
IDER | -0.144 |
Random | -0.132 |
acco | -0.124 |
Rough | -0.124 |
rl | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
aciously | +0.315 |
prevail | +0.307 |
elia | +0.292 |
Nadu | +0.289 |
itions | +0.281 |
Neg logit contributions | |
IDER | -0.293 |
Random | -0.271 |
Rough | -0.254 |
rl | -0.253 |
acco | -0.251 |
Token | said |
Token ID | 531 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
aciously | +0.105 |
prevail | +0.103 |
elia | +0.097 |
Nadu | +0.096 |
itions | +0.095 |
Neg logit contributions | |
IDER | -0.095 |
Random | -0.087 |
rl | -0.081 |
Rough | -0.080 |
asions | -0.080 |
Token | that |
Token ID | 326 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
IDER | +0.580 |
Random | +0.539 |
rl | +0.507 |
Rough | +0.505 |
ylum | +0.502 |
Neg logit contributions | |
aciously | -0.517 |
prevail | -0.505 |
elia | -0.478 |
Nadu | -0.470 |
itions | -0.460 |
Token | � |
Token ID | 564 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
IDER | +2.003 |
Random | +1.863 |
Rough | +1.752 |
rl | +1.751 |
ylum | +1.732 |
Neg logit contributions | |
aciously | -1.835 |
prevail | -1.786 |
elia | -1.695 |
Nadu | -1.667 |
itions | -1.628 |
Token | � |
Token ID | 250 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
IDER | +0.788 |
Random | +0.722 |
Rough | +0.677 |
rl | +0.675 |
ylum | +0.673 |
Neg logit contributions | |
aciously | -0.785 |
prevail | -0.767 |
elia | -0.730 |
Nadu | -0.713 |
itions | -0.704 |
Token | inqu |
Token ID | 18934 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
IDER | +2.137 |
Random | +1.959 |
rl | +1.822 |
Rough | +1.817 |
ylum | +1.800 |
Neg logit contributions | |
aciously | -2.589 |
prevail | -2.532 |
elia | -2.419 |
Nadu | -2.383 |
itions | -2.340 |
Token | iring |
Token ID | 3428 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
IDER | +6.572 |
Random | +5.894 |
arted | +5.840 |
rl | +5.645 |
aders | +5.600 |
Neg logit contributions | |
prevail | -10.029 |
aciously | -9.620 |
Nadu | -9.503 |
elia | -9.027 |
ged | -8.675 |
Token | whether |
Token ID | 1771 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
IDER | +4.041 |
Random | +3.773 |
Rough | +3.566 |
rl | +3.548 |
ylum | +3.500 |
Neg logit contributions | |
aciously | -3.543 |
prevail | -3.475 |
elia | -3.300 |
Nadu | -3.249 |
itions | -3.160 |
Token | underwear |
Token ID | 26170 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
IDER | +1.205 |
Random | +1.117 |
rl | +1.048 |
Rough | +1.042 |
ylum | +1.038 |
Neg logit contributions | |
aciously | -1.149 |
prevail | -1.122 |
elia | -1.065 |
Nadu | -1.047 |
itions | -1.027 |
Token | was |
Token ID | 373 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
aciously | +0.269 |
prevail | +0.265 |
elia | +0.250 |
Nadu | +0.246 |
ged | +0.244 |
Neg logit contributions | |
IDER | -0.264 |
Random | -0.243 |
Rough | -0.227 |
ylum | -0.227 |
rl | -0.227 |
Token | being |
Token ID | 852 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
IDER | +0.789 |
Random | +0.730 |
rl | +0.686 |
Rough | +0.682 |
ylum | +0.679 |
Neg logit contributions | |
aciously | -0.768 |
prevail | -0.753 |
elia | -0.712 |
Nadu | -0.702 |
ged | -0.686 |
Token | our |
Token ID | 674 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
IDER | +1.589 |
Random | +1.472 |
rl | +1.378 |
Rough | +1.375 |
ylum | +1.361 |
Neg logit contributions | |
aciously | -1.603 |
prevail | -1.566 |
elia | -1.489 |
Nadu | -1.465 |
itions | -1.434 |
Token | heads |
Token ID | 6665 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
aciously | +2.088 |
prevail | +2.042 |
elia | +1.949 |
eness | +1.891 |
ged | +1.889 |
Neg logit contributions | |
IDER | -1.820 |
Random | -1.675 |
rl | -1.573 |
ylum | -1.563 |
Rough | -1.548 |
Token | at |
Token ID | 379 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
aciously | +2.265 |
prevail | +2.233 |
elia | +2.076 |
eness | +2.016 |
itions | +2.012 |
Neg logit contributions | |
IDER | -2.686 |
Random | -2.483 |
acco | -2.359 |
Rough | -2.354 |
rl | -2.343 |
Token | the |
Token ID | 262 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
IDER | +0.133 |
Random | +0.123 |
rl | +0.116 |
ylum | +0.115 |
Rough | +0.115 |
Neg logit contributions | |
aciously | -0.125 |
prevail | -0.122 |
elia | -0.116 |
Nadu | -0.113 |
ged | -0.111 |
Token | irrational |
Token ID | 25086 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
IDER | +0.742 |
Random | +0.691 |
rl | +0.652 |
ylum | +0.647 |
Rough | +0.646 |
Neg logit contributions | |
aciously | -0.652 |
prevail | -0.636 |
elia | -0.603 |
Nadu | -0.589 |
ged | -0.578 |
Token | ex |
Token ID | 409 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
IDER | +0.646 |
Random | +0.600 |
rl | +0.564 |
Rough | +0.562 |
ylum | +0.559 |
Neg logit contributions | |
aciously | -0.603 |
prevail | -0.589 |
elia | -0.558 |
Nadu | -0.549 |
ged | -0.538 |
Token | uber |
Token ID | 18478 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
IDER | +4.342 |
Random | +3.944 |
rl | +3.684 |
aders | +3.678 |
acco | +3.663 |
Neg logit contributions | |
aciously | -6.539 |
prevail | -6.463 |
Nadu | -6.215 |
elia | -6.091 |
ged | -5.918 |
Token | ance |
Token ID | 590 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
IDER | +0.626 |
Random | +0.574 |
rl | +0.533 |
Rough | +0.532 |
ylum | +0.526 |
Neg logit contributions | |
aciously | -0.781 |
prevail | -0.764 |
elia | -0.729 |
Nadu | -0.718 |
itions | -0.706 |
Token | that |
Token ID | 326 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
aciously | +1.747 |
prevail | +1.733 |
elia | +1.594 |
Nadu | +1.552 |
eness | +1.529 |
Neg logit contributions | |
IDER | -2.488 |
Random | -2.334 |
rl | -2.210 |
Rough | -2.197 |
asions | -2.186 |
Token | once |
Token ID | 1752 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
IDER | +0.749 |
Random | +0.691 |
rl | +0.648 |
Rough | +0.643 |
ylum | +0.640 |
Neg logit contributions | |
aciously | -0.757 |
prevail | -0.749 |
elia | -0.702 |
Nadu | -0.691 |
ged | -0.681 |
Token | valued |
Token ID | 17560 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
aciously | +0.396 |
prevail | +0.391 |
elia | +0.366 |
Nadu | +0.362 |
ged | +0.356 |
Neg logit contributions | |
IDER | -0.359 |
Random | -0.332 |
rl | -0.309 |
Rough | -0.308 |
asions | -0.304 |