Token | It |
Token ID | 632 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
ples | +5.604 |
ptions | +5.319 |
ount | +5.246 |
ydia | +5.001 |
blo | +4.996 |
Neg logit contributions | |
tum | -3.948 |
His | -3.253 |
night | -3.167 |
lung | -3.106 |
steak | -3.063 |
Token | is |
Token ID | 318 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ples | +7.680 |
ount | +7.105 |
ptions | +7.055 |
ydia | +6.946 |
Jem | +6.874 |
Neg logit contributions | |
tum | -5.330 |
night | -4.695 |
lung | -4.353 |
leg | -4.248 |
steak | -4.182 |
Token | their |
Token ID | 511 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ples | +4.027 |
ount | +3.716 |
paints | +3.656 |
angles | +3.511 |
violet | +3.510 |
Neg logit contributions | |
tum | -2.376 |
thirst | -1.979 |
night | -1.893 |
steak | -1.866 |
lung | -1.817 |
Token | teacher |
Token ID | 4701 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ples | +0.895 |
ount | +0.839 |
Jas | +0.833 |
yl | +0.812 |
paints | +0.809 |
Neg logit contributions | |
tum | -0.462 |
thirst | -0.371 |
night | -0.367 |
steak | -0.335 |
lung | -0.321 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
ples | +4.775 |
ount | +4.590 |
ydia | +4.555 |
Jas | +4.457 |
violet | +4.423 |
Neg logit contributions | |
tum | -3.610 |
night | -2.924 |
steak | -2.880 |
lung | -2.828 |
thirst | -2.823 |
Token | She |
Token ID | 1375 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
ples | +6.735 |
ptions | +6.362 |
ount | +6.168 |
blo | +6.032 |
paints | +5.998 |
Neg logit contributions | |
tum | -3.406 |
His | -2.845 |
night | -2.527 |
His | -2.426 |
steak | -2.393 |
Token | comes |
Token ID | 2058 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
ples | +9.258 |
ount | +8.839 |
ydia | +8.678 |
ptions | +8.619 |
Jem | +8.361 |
Neg logit contributions | |
tum | -6.816 |
night | -5.839 |
lung | -5.822 |
sled | -5.579 |
drowned | -5.522 |
Token | to |
Token ID | 284 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ples | +0.866 |
ount | +0.804 |
Jas | +0.796 |
paints | +0.776 |
yl | +0.774 |
Neg logit contributions | |
tum | -0.682 |
night | -0.582 |
thirst | -0.582 |
steak | -0.541 |
lung | -0.525 |
Token | see |
Token ID | 766 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ples | +1.907 |
ount | +1.763 |
Jas | +1.688 |
blo | +1.662 |
paints | +1.656 |
Neg logit contributions | |
tum | -1.617 |
night | -1.399 |
thirst | -1.390 |
steak | -1.321 |
dinner | -1.268 |
Token | what |
Token ID | 644 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ples | +3.560 |
ount | +3.158 |
ydia | +3.098 |
Jas | +3.045 |
iddling | +3.019 |
Neg logit contributions | |
tum | -4.015 |
steak | -3.539 |
night | -3.415 |
dinner | -3.385 |
thirst | -3.383 |
Token | is |
Token ID | 318 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
ples | +2.639 |
ount | +2.367 |
Jas | +2.219 |
ydia | +2.196 |
violet | +2.171 |
Neg logit contributions | |
tum | -3.082 |
night | -2.665 |
steak | -2.625 |
thirst | -2.497 |
lung | -2.476 |
Token | comes |
Token ID | 2058 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
ples | +7.302 |
ount | +6.696 |
ydia | +6.428 |
umes | +6.303 |
od | +6.299 |
Neg logit contributions | |
tum | -7.806 |
night | -6.741 |
sled | -6.696 |
leg | -6.671 |
muscle | -6.614 |
Token | to |
Token ID | 284 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ples | +1.720 |
ount | +1.613 |
Jas | +1.574 |
yl | +1.548 |
paints | +1.547 |
Neg logit contributions | |
tum | -1.074 |
night | -0.890 |
thirst | -0.884 |
steak | -0.819 |
lung | -0.787 |
Token | their |
Token ID | 511 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ples | +2.234 |
ount | +2.061 |
Jas | +1.937 |
blo | +1.934 |
paints | +1.922 |
Neg logit contributions | |
tum | -2.148 |
thirst | -1.858 |
night | -1.836 |
steak | -1.761 |
dinner | -1.728 |
Token | room |
Token ID | 2119 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
ples | +1.044 |
ount | +0.952 |
Jas | +0.929 |
yl | +0.902 |
ydia | +0.887 |
Neg logit contributions | |
tum | -1.324 |
thirst | -1.158 |
night | -1.144 |
steak | -1.101 |
lung | -1.076 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
ples | +1.345 |
ount | +1.239 |
Jas | +1.225 |
yl | +1.188 |
ydia | +1.185 |
Neg logit contributions | |
tum | -1.316 |
night | -1.121 |
thirst | -1.119 |
steak | -1.067 |
lung | -1.029 |
Token | She |
Token ID | 1375 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
ples | +3.960 |
ount | +3.513 |
ptions | +3.417 |
angles | +3.274 |
blo | +3.251 |
Neg logit contributions | |
tum | -4.841 |
night | -3.896 |
steak | -3.733 |
leg | -3.731 |
time | -3.718 |
Token | is |
Token ID | 318 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
ples | +7.925 |
ount | +7.540 |
od | +7.468 |
written | +6.977 |
ydia | +6.970 |
Neg logit contributions | |
tum | -7.932 |
leg | -6.617 |
sled | -6.436 |
night | -6.223 |
muscle | -6.206 |
Token | not |
Token ID | 407 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ples | +6.112 |
ount | +5.561 |
od | +5.336 |
Kay | +5.330 |
violet | +5.330 |
Neg logit contributions | |
tum | -2.570 |
thirst | -1.935 |
leg | -1.911 |
steak | -1.756 |
dinner | -1.740 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ples | +3.666 |
ount | +3.354 |
violet | +3.252 |
paints | +3.220 |
Jas | +3.213 |
Neg logit contributions | |
tum | -2.541 |
thirst | -2.135 |
steak | -2.023 |
night | -2.006 |
dinner | -1.973 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ples | +2.130 |
ount | +1.944 |
Jas | +1.922 |
yl | +1.897 |
ydia | +1.895 |
Neg logit contributions | |
tum | -1.985 |
night | -1.691 |
thirst | -1.658 |
steak | -1.610 |
dinner | -1.540 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ples | +4.273 |
ount | +3.788 |
ptions | +3.745 |
blo | +3.653 |
Jas | +3.619 |
Neg logit contributions | |
tum | -3.761 |
night | -2.918 |
steak | -2.778 |
time | -2.772 |
leg | -2.757 |
Token | . |
Token ID | 13 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
ples | +0.860 |
ount | +0.793 |
Jas | +0.787 |
yl | +0.764 |
paints | +0.760 |
Neg logit contributions | |
tum | -0.880 |
night | -0.768 |
thirst | -0.767 |
steak | -0.725 |
lung | -0.702 |
Token | Sammy |
Token ID | 44067 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
tum | +0.090 |
night | +0.078 |
thirst | +0.078 |
steak | +0.074 |
lung | +0.071 |
Neg logit contributions | |
ples | -0.103 |
Jas | -0.096 |
ount | -0.095 |
paints | -0.092 |
yl | -0.091 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ples | +0.286 |
Jas | +0.262 |
ount | +0.262 |
yl | +0.253 |
paints | +0.253 |
Neg logit contributions | |
tum | -0.302 |
thirst | -0.265 |
night | -0.263 |
steak | -0.248 |
lung | -0.241 |
Token | to |
Token ID | 284 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
ples | +0.024 |
Jas | +0.022 |
ount | +0.022 |
paints | +0.021 |
yl | +0.021 |
Neg logit contributions | |
tum | -0.018 |
thirst | -0.015 |
night | -0.015 |
steak | -0.014 |
lung | -0.014 |
Token | touch |
Token ID | 3638 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
tum | +0.066 |
thirst | +0.058 |
night | +0.058 |
steak | +0.054 |
lung | +0.053 |
Neg logit contributions | |
ples | -0.064 |
Jas | -0.059 |
ount | -0.059 |
paints | -0.057 |
yl | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
ples | +1.044 |
ount | +0.966 |
Jas | +0.955 |
yl | +0.926 |
paints | +0.917 |
Neg logit contributions | |
tum | -1.026 |
thirst | -0.894 |
night | -0.879 |
steak | -0.846 |
lung | -0.818 |
Token | staff |
Token ID | 3085 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
ples | +8.074 |
Jas | +7.222 |
ount | +7.133 |
iddling | +6.999 |
bugs | +6.820 |
Neg logit contributions | |
tum | -8.344 |
job | -7.028 |
dinner | -6.898 |
thirst | -6.782 |
leg | -6.671 |
Token | , |
Token ID | 11 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
tum | +0.966 |
thirst | +0.850 |
night | +0.848 |
steak | +0.773 |
lung | +0.754 |
Neg logit contributions | |
ples | -1.003 |
Jas | -0.922 |
ount | -0.920 |
paints | -0.903 |
blo | -0.896 |
Token | but |
Token ID | 475 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
tum | +0.635 |
night | +0.570 |
thirst | +0.560 |
steak | +0.518 |
lung | +0.506 |
Neg logit contributions | |
ples | -0.660 |
Jas | -0.617 |
ount | -0.606 |
paints | -0.598 |
Kay | -0.585 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
tum | +0.624 |
night | +0.539 |
thirst | +0.526 |
steak | +0.488 |
lung | +0.470 |
Neg logit contributions | |
ples | -0.857 |
Jas | -0.821 |
ount | -0.795 |
yl | -0.788 |
Kay | -0.784 |
Token | didn |
Token ID | 1422 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
ples | +0.035 |
Jas | +0.032 |
ount | +0.032 |
yl | +0.031 |
paints | +0.031 |
Neg logit contributions | |
tum | -0.038 |
thirst | -0.033 |
night | -0.033 |
steak | -0.031 |
lung | -0.030 |
Token | comes |
Token ID | 2058 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ples | +7.586 |
ount | +6.983 |
od | +6.673 |
ydia | +6.615 |
umes | +6.540 |
Neg logit contributions | |
tum | -7.691 |
night | -6.411 |
leg | -6.398 |
drowned | -6.287 |
sled | -6.279 |
Token | to |
Token ID | 284 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ples | +1.603 |
ount | +1.504 |
Jas | +1.472 |
yl | +1.444 |
paints | +1.443 |
Neg logit contributions | |
tum | -0.996 |
night | -0.825 |
thirst | -0.823 |
steak | -0.760 |
lung | -0.727 |
Token | their |
Token ID | 511 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ples | +1.710 |
ount | +1.582 |
Jas | +1.518 |
yl | +1.487 |
blo | +1.482 |
Neg logit contributions | |
tum | -1.684 |
thirst | -1.464 |
night | -1.454 |
steak | -1.397 |
dinner | -1.344 |
Token | room |
Token ID | 2119 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
ples | +1.083 |
ount | +0.992 |
Jas | +0.969 |
yl | +0.937 |
ydia | +0.921 |
Neg logit contributions | |
tum | -1.389 |
thirst | -1.215 |
night | -1.199 |
steak | -1.158 |
lung | -1.129 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ples | +1.469 |
ount | +1.354 |
Jas | +1.339 |
yl | +1.299 |
ydia | +1.297 |
Neg logit contributions | |
tum | -1.451 |
thirst | -1.236 |
night | -1.231 |
steak | -1.172 |
lung | -1.130 |
Token | She |
Token ID | 1375 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
ples | +2.402 |
ount | +2.115 |
yl | +1.998 |
ptions | +1.988 |
Jas | +1.976 |
Neg logit contributions | |
tum | -4.054 |
night | -3.454 |
thirst | -3.365 |
steak | -3.321 |
lung | -3.243 |
Token | sees |
Token ID | 7224 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ples | +7.725 |
ount | +7.381 |
od | +7.217 |
ydia | +6.708 |
written | +6.697 |
Neg logit contributions | |
tum | -8.214 |
leg | -6.743 |
drowned | -6.401 |
steak | -6.390 |
sled | -6.352 |
Token | them |
Token ID | 606 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
ples | +3.680 |
ount | +3.369 |
Jas | +3.281 |
yl | +3.273 |
ydia | +3.194 |
Neg logit contributions | |
tum | -3.112 |
steak | -2.709 |
thirst | -2.579 |
night | -2.522 |
dinner | -2.505 |
Token | fighting |
Token ID | 4330 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
ples | +1.493 |
Jas | +1.363 |
ount | +1.349 |
yl | +1.320 |
ydia | +1.319 |
Neg logit contributions | |
tum | -1.809 |
thirst | -1.593 |
night | -1.562 |
steak | -1.519 |
lung | -1.483 |
Token | over |
Token ID | 625 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
ples | +1.028 |
ount | +0.944 |
Jas | +0.939 |
yl | +0.914 |
paints | +0.897 |
Neg logit contributions | |
tum | -1.135 |
night | -0.997 |
thirst | -0.986 |
steak | -0.947 |
lung | -0.914 |
Token | the |
Token ID | 262 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
ples | +1.143 |
ount | +1.066 |
Jas | +1.046 |
yl | +1.016 |
ydia | +1.008 |
Neg logit contributions | |
tum | -1.076 |
thirst | -0.934 |
night | -0.915 |
steak | -0.887 |
lung | -0.850 |
Token | what |
Token ID | 644 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ples | +2.939 |
ydia | +2.593 |
Jas | +2.524 |
yl | +2.512 |
ount | +2.493 |
Neg logit contributions | |
tum | -4.191 |
thirst | -3.601 |
steak | -3.553 |
night | -3.495 |
dinner | -3.435 |
Token | they |
Token ID | 484 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
ples | +2.646 |
ount | +2.432 |
Jas | +2.309 |
ydia | +2.308 |
ptions | +2.270 |
Neg logit contributions | |
tum | -2.328 |
night | -1.914 |
steak | -1.884 |
thirst | -1.858 |
lung | -1.775 |
Token | are |
Token ID | 389 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ples | +5.196 |
Jas | +5.103 |
ount | +4.896 |
yl | +4.797 |
ydia | +4.775 |
Neg logit contributions | |
tum | -4.494 |
night | -3.918 |
thirst | -3.829 |
drowned | -3.637 |
uch | -3.602 |
Token | doing |
Token ID | 1804 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
ples | +3.493 |
Jas | +3.141 |
ydia | +3.108 |
ount | +3.100 |
Kay | +3.021 |
Neg logit contributions | |
tum | -4.590 |
thirst | -4.050 |
dinner | -3.999 |
night | -3.914 |
steak | -3.878 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ples | +1.327 |
ount | +1.220 |
Jas | +1.208 |
yl | +1.175 |
paints | +1.168 |
Neg logit contributions | |
tum | -1.320 |
night | -1.162 |
thirst | -1.145 |
steak | -1.088 |
lung | -1.051 |
Token | She |
Token ID | 1375 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
ples | +2.557 |
ptions | +2.127 |
ount | +2.117 |
yl | +2.102 |
Jas | +2.020 |
Neg logit contributions | |
tum | -4.529 |
thirst | -3.764 |
night | -3.743 |
steak | -3.622 |
stomach | -3.519 |
Token | sees |
Token ID | 7224 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ples | +7.403 |
ount | +7.312 |
od | +6.645 |
Jem | +6.483 |
ydia | +6.403 |
Neg logit contributions | |
tum | -7.816 |
night | -6.332 |
leg | -6.307 |
steak | -6.276 |
sled | -6.194 |
Token | them |
Token ID | 606 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ples | +3.578 |
ydia | +3.116 |
ount | +3.109 |
Jas | +3.105 |
yl | +3.041 |
Neg logit contributions | |
tum | -3.437 |
steak | -2.927 |
thirst | -2.878 |
night | -2.746 |
dinner | -2.694 |
Token | in |
Token ID | 287 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ples | +1.940 |
ount | +1.791 |
Jas | +1.788 |
ydia | +1.740 |
yl | +1.727 |
Neg logit contributions | |
tum | -2.207 |
thirst | -1.938 |
night | -1.905 |
steak | -1.843 |
lung | -1.819 |
Token | the |
Token ID | 262 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ples | +3.159 |
ount | +3.095 |
Jas | +2.800 |
paints | +2.788 |
yl | +2.772 |
Neg logit contributions | |
tum | -2.543 |
steak | -2.125 |
thirst | -2.124 |
night | -2.035 |
lung | -2.031 |
Token | hat |
Token ID | 6877 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ples | +2.746 |
ount | +2.555 |
Jas | +2.444 |
yl | +2.344 |
Kay | +2.314 |
Neg logit contributions | |
tum | -3.328 |
night | -2.838 |
thirst | -2.801 |
lung | -2.681 |
steak | -2.679 |
Token | comes |
Token ID | 2058 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
ples | +7.906 |
ount | +7.163 |
umes | +6.957 |
ydia | +6.931 |
od | +6.893 |
Neg logit contributions | |
tum | -7.740 |
night | -6.513 |
leg | -6.312 |
drowned | -6.238 |
sled | -6.103 |
Token | to |
Token ID | 284 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ples | +1.391 |
ount | +1.304 |
Jas | +1.281 |
yl | +1.257 |
paints | +1.254 |
Neg logit contributions | |
tum | -0.887 |
night | -0.736 |
thirst | -0.735 |
steak | -0.677 |
lung | -0.651 |
Token | the |
Token ID | 262 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
ples | +1.729 |
ount | +1.585 |
Jas | +1.517 |
paints | +1.493 |
blo | +1.490 |
Neg logit contributions | |
tum | -1.733 |
thirst | -1.507 |
night | -1.491 |
steak | -1.434 |
dinner | -1.381 |
Token | box |
Token ID | 3091 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ples | +1.467 |
ount | +1.340 |
Jas | +1.326 |
yl | +1.271 |
Kay | +1.234 |
Neg logit contributions | |
tum | -1.924 |
thirst | -1.689 |
night | -1.659 |
steak | -1.643 |
lung | -1.604 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ples | +1.926 |
ount | +1.785 |
Jas | +1.756 |
ydia | +1.695 |
yl | +1.693 |
Neg logit contributions | |
tum | -1.757 |
night | -1.497 |
thirst | -1.485 |
steak | -1.433 |
lung | -1.375 |
Token | She |
Token ID | 1375 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
ples | +3.328 |
ount | +2.917 |
ptions | +2.859 |
yl | +2.706 |
blo | +2.642 |
Neg logit contributions | |
tum | -5.258 |
night | -4.355 |
thirst | -4.190 |
steak | -4.157 |
leg | -4.114 |
Token | says |
Token ID | 1139 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ples | +7.762 |
ount | +7.257 |
od | +7.118 |
ydia | +6.709 |
Jas | +6.532 |
Neg logit contributions | |
tum | -8.104 |
leg | -6.541 |
sled | -6.434 |
steak | -6.403 |
night | -6.225 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ples | +2.673 |
ount | +2.464 |
Jas | +2.406 |
ydia | +2.387 |
ptions | +2.352 |
Neg logit contributions | |
tum | -1.651 |
night | -1.275 |
thirst | -1.262 |
steak | -1.231 |
lung | -1.133 |
Token | " |
Token ID | 366 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ples | +3.025 |
ount | +2.792 |
Jas | +2.707 |
ydia | +2.703 |
ptions | +2.654 |
Neg logit contributions | |
tum | -3.187 |
thirst | -2.555 |
steak | -2.510 |
night | -2.499 |
lung | -2.433 |
Token | Stop |
Token ID | 19485 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ples | +2.498 |
ount | +2.221 |
Jas | +2.158 |
paints | +2.110 |
blo | +2.066 |
Neg logit contributions | |
tum | -3.306 |
night | -2.953 |
steak | -2.946 |
thirst | -2.927 |
lung | -2.809 |
Token | , |
Token ID | 11 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
ples | +3.063 |
ount | +2.940 |
ydia | +2.823 |
Jas | +2.789 |
paints | +2.733 |
Neg logit contributions | |
tum | -2.548 |
thirst | -2.133 |
night | -2.117 |
steak | -2.075 |
lung | -1.998 |
Token | is |
Token ID | 318 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ples | +7.641 |
ptions | +7.183 |
ount | +7.145 |
ydia | +6.980 |
Jem | +6.932 |
Neg logit contributions | |
tum | -5.370 |
night | -4.670 |
lung | -4.334 |
leg | -4.165 |
steak | -4.132 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ples | +4.329 |
ount | +4.013 |
paints | +3.929 |
ptions | +3.817 |
angles | +3.796 |
Neg logit contributions | |
tum | -2.427 |
thirst | -2.009 |
night | -1.895 |
steak | -1.885 |
dinner | -1.821 |
Token | 's |
Token ID | 338 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
ples | +2.909 |
ount | +2.795 |
Jas | +2.776 |
ydia | +2.680 |
paints | +2.648 |
Neg logit contributions | |
tum | -1.652 |
night | -1.312 |
thirst | -1.302 |
lung | -1.228 |
steak | -1.203 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ples | +1.763 |
ount | +1.655 |
Jas | +1.616 |
yl | +1.545 |
ptions | +1.543 |
Neg logit contributions | |
tum | -1.492 |
thirst | -1.252 |
night | -1.226 |
steak | -1.167 |
lung | -1.144 |
Token | . |
Token ID | 13 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ydia | +6.700 |
ples | +6.601 |
Jas | +6.521 |
ount | +6.520 |
ey | +6.266 |
Neg logit contributions | |
tum | -4.102 |
lung | -3.187 |
night | -3.149 |
steak | -3.088 |
thirst | -3.077 |
Token | She |
Token ID | 1375 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
ples | +7.048 |
ptions | +6.683 |
angles | +6.320 |
ount | +6.304 |
els | +6.228 |
Neg logit contributions | |
tum | -4.237 |
His | -3.206 |
night | -2.975 |
thirst | -2.743 |
leg | -2.666 |
Token | has |
Token ID | 468 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ples | +8.062 |
ount | +7.853 |
ptions | +7.730 |
ydia | +7.668 |
Jem | +7.445 |
Neg logit contributions | |
tum | -7.158 |
night | -6.246 |
lung | -5.992 |
steak | -5.704 |
thirst | -5.539 |
Token | come |
Token ID | 1282 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
ples | +2.814 |
ount | +2.663 |
Jas | +2.513 |
yl | +2.459 |
ydia | +2.438 |
Neg logit contributions | |
tum | -2.145 |
thirst | -1.733 |
steak | -1.688 |
night | -1.687 |
lung | -1.604 |
Token | to |
Token ID | 284 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
ples | +1.789 |
ount | +1.674 |
Jas | +1.654 |
paints | +1.616 |
yl | +1.610 |
Neg logit contributions | |
tum | -1.103 |
night | -0.928 |
thirst | -0.905 |
steak | -0.832 |
lung | -0.812 |
Token | pick |
Token ID | 2298 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ples | +0.994 |
ount | +0.914 |
Jas | +0.900 |
yl | +0.875 |
paints | +0.871 |
Neg logit contributions | |
tum | -0.976 |
thirst | -0.849 |
night | -0.840 |
steak | -0.794 |
lung | -0.768 |
Token | them |
Token ID | 606 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ples | +2.733 |
ount | +2.495 |
Jas | +2.491 |
ptions | +2.380 |
yl | +2.368 |
Neg logit contributions | |
tum | -2.494 |
night | -2.192 |
thirst | -2.133 |
steak | -2.106 |
dinner | -1.994 |
Token |
|
Token ID | 198 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
tum | +0.208 |
thirst | +0.182 |
night | +0.181 |
steak | +0.167 |
lung | +0.162 |
Neg logit contributions | |
ples | -0.236 |
Jas | -0.221 |
ount | -0.220 |
yl | -0.213 |
paints | -0.213 |
Token | Mom |
Token ID | 29252 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
tum | +0.719 |
night | +0.618 |
thirst | +0.610 |
steak | +0.555 |
lung | +0.543 |
Neg logit contributions | |
ples | -0.888 |
Jas | -0.832 |
ount | -0.827 |
yl | -0.812 |
paints | -0.806 |
Token | hears |
Token ID | 23180 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
ples | +4.192 |
Kay | +4.001 |
ount | +3.980 |
ydia | +3.889 |
yl | +3.831 |
Neg logit contributions | |
tum | -5.354 |
night | -4.642 |
steak | -4.567 |
dinner | -4.312 |
drowned | -4.280 |
Token | them |
Token ID | 606 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
ples | +1.390 |
ount | +1.258 |
Jas | +1.198 |
paints | +1.190 |
blo | +1.183 |
Neg logit contributions | |
tum | -1.974 |
thirst | -1.740 |
night | -1.739 |
steak | -1.694 |
dinner | -1.623 |
Token | . |
Token ID | 13 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ples | +1.050 |
Jas | +0.962 |
ount | +0.959 |
yl | +0.937 |
paints | +0.927 |
Neg logit contributions | |
tum | -1.033 |
night | -0.893 |
thirst | -0.892 |
steak | -0.842 |
lung | -0.818 |
Token | She |
Token ID | 1375 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
ples | +3.366 |
ount | +2.967 |
ptions | +2.967 |
yl | +2.785 |
angles | +2.750 |
Neg logit contributions | |
tum | -5.466 |
night | -4.566 |
thirst | -4.395 |
leg | -4.323 |
steak | -4.316 |
Token | comes |
Token ID | 2058 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
ples | +7.906 |
ount | +7.163 |
umes | +6.957 |
ydia | +6.931 |
od | +6.893 |
Neg logit contributions | |
tum | -7.740 |
night | -6.513 |
leg | -6.312 |
drowned | -6.238 |
sled | -6.103 |
Token | to |
Token ID | 284 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ples | +1.391 |
ount | +1.304 |
Jas | +1.281 |
yl | +1.257 |
paints | +1.254 |
Neg logit contributions | |
tum | -0.887 |
night | -0.736 |
thirst | -0.735 |
steak | -0.677 |
lung | -0.651 |
Token | the |
Token ID | 262 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
ples | +1.729 |
ount | +1.585 |
Jas | +1.517 |
paints | +1.493 |
blo | +1.490 |
Neg logit contributions | |
tum | -1.733 |
thirst | -1.507 |
night | -1.491 |
steak | -1.434 |
dinner | -1.381 |
Token | box |
Token ID | 3091 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ples | +1.467 |
ount | +1.340 |
Jas | +1.326 |
yl | +1.271 |
Kay | +1.234 |
Neg logit contributions | |
tum | -1.924 |
thirst | -1.689 |
night | -1.659 |
steak | -1.643 |
lung | -1.604 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ples | +1.926 |
ount | +1.785 |
Jas | +1.756 |
ydia | +1.695 |
yl | +1.693 |
Neg logit contributions | |
tum | -1.757 |
night | -1.497 |
thirst | -1.485 |
steak | -1.433 |
lung | -1.375 |
Token | comes |
Token ID | 2058 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
ples | +7.240 |
ount | +6.792 |
Jem | +6.344 |
ydia | +6.330 |
od | +6.275 |
Neg logit contributions | |
tum | -6.892 |
night | -5.952 |
muscle | -5.836 |
leg | -5.802 |
sled | -5.734 |
Token | to |
Token ID | 284 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ples | +1.405 |
ount | +1.315 |
Jas | +1.287 |
yl | +1.262 |
paints | +1.262 |
Neg logit contributions | |
tum | -0.979 |
night | -0.822 |
thirst | -0.821 |
steak | -0.762 |
lung | -0.734 |
Token | their |
Token ID | 511 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
ples | +2.669 |
ount | +2.470 |
blo | +2.332 |
paints | +2.293 |
Jas | +2.292 |
Neg logit contributions | |
tum | -2.298 |
thirst | -1.987 |
night | -1.942 |
steak | -1.855 |
dinner | -1.849 |
Token | room |
Token ID | 2119 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
ples | +0.902 |
ount | +0.823 |
Jas | +0.808 |
yl | +0.780 |
ydia | +0.763 |
Neg logit contributions | |
tum | -1.180 |
thirst | -1.037 |
night | -1.027 |
steak | -0.988 |
lung | -0.963 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ples | +1.282 |
ount | +1.186 |
Jas | +1.174 |
yl | +1.138 |
paints | +1.133 |
Neg logit contributions | |
tum | -1.168 |
thirst | -0.993 |
night | -0.992 |
steak | -0.939 |
lung | -0.905 |
Token | She |
Token ID | 1375 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ples | +3.724 |
ount | +3.362 |
ptions | +3.195 |
blo | +3.097 |
yl | +3.097 |
Neg logit contributions | |
tum | -4.061 |
night | -3.288 |
thirst | -3.186 |
time | -3.124 |
leg | -3.121 |
Token | is |
Token ID | 318 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ples | +7.818 |
ount | +7.449 |
od | +7.224 |
written | +6.815 |
ydia | +6.748 |
Neg logit contributions | |
tum | -7.688 |
leg | -6.396 |
sled | -6.161 |
muscle | -6.070 |
drowned | -6.065 |
Token | not |
Token ID | 407 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ples | +6.537 |
ount | +6.001 |
od | +5.741 |
violet | +5.733 |
Kay | +5.731 |
Neg logit contributions | |
tum | -2.352 |
thirst | -1.748 |
leg | -1.693 |
steak | -1.560 |
dinner | -1.519 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ples | +3.977 |
ount | +3.650 |
violet | +3.527 |
paints | +3.515 |
Jas | +3.488 |
Neg logit contributions | |
tum | -2.607 |
thirst | -2.208 |
steak | -2.106 |
night | -2.062 |
dinner | -2.042 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
ples | +2.613 |
ount | +2.389 |
Jas | +2.349 |
yl | +2.326 |
violet | +2.323 |
Neg logit contributions | |
tum | -2.312 |
night | -1.947 |
thirst | -1.906 |
steak | -1.866 |
dinner | -1.796 |
Token |
|
Token ID | 198 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ples | +4.177 |
ount | +3.730 |
ptions | +3.644 |
blo | +3.575 |
Jas | +3.534 |
Neg logit contributions | |
tum | -3.469 |
night | -2.704 |
thirst | -2.605 |
time | -2.576 |
steak | -2.549 |
Token |
|
Token ID | 198 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
tum | +0.541 |
thirst | +0.478 |
night | +0.477 |
steak | +0.440 |
lung | +0.426 |
Neg logit contributions | |
ples | -0.585 |
Jas | -0.550 |
ount | -0.544 |
yl | -0.529 |
paints | -0.529 |
Token | Mom |
Token ID | 29252 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
tum | +0.653 |
thirst | +0.568 |
night | +0.566 |
steak | +0.519 |
lung | +0.507 |
Neg logit contributions | |
ples | -0.709 |
Jas | -0.658 |
ount | -0.651 |
yl | -0.643 |
paints | -0.637 |
Token | hears |
Token ID | 23180 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ples | +4.426 |
ount | +4.199 |
Kay | +4.168 |
ydia | +4.026 |
Jas | +4.006 |
Neg logit contributions | |
tum | -5.029 |
night | -4.326 |
steak | -4.277 |
leg | -4.053 |
dinner | -4.049 |
Token | them |
Token ID | 606 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
ples | +1.739 |
ount | +1.590 |
Jas | +1.504 |
blo | +1.499 |
yl | +1.493 |
Neg logit contributions | |
tum | -2.306 |
night | -2.034 |
thirst | -2.017 |
steak | -1.996 |
dinner | -1.907 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ples | +0.980 |
Jas | +0.897 |
ount | +0.894 |
yl | +0.872 |
paints | +0.866 |
Neg logit contributions | |
tum | -0.969 |
night | -0.837 |
thirst | -0.837 |
steak | -0.789 |
lung | -0.768 |
Token | She |
Token ID | 1375 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
ples | +3.494 |
ount | +3.092 |
ptions | +3.006 |
yl | +2.846 |
angles | +2.839 |
Neg logit contributions | |
tum | -5.300 |
night | -4.431 |
time | -4.249 |
leg | -4.247 |
steak | -4.236 |
Token | comes |
Token ID | 2058 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
ples | +7.813 |
ount | +7.109 |
od | +6.803 |
Jem | +6.687 |
umes | +6.684 |
Neg logit contributions | |
tum | -7.625 |
night | -6.550 |
leg | -6.434 |
drowned | -6.321 |
muscle | -6.316 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ples | +1.798 |
ount | +1.688 |
Jas | +1.647 |
paints | +1.618 |
yl | +1.618 |
Neg logit contributions | |
tum | -1.094 |
night | -0.903 |
thirst | -0.898 |
steak | -0.829 |
lung | -0.797 |
Token | see |
Token ID | 766 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
ples | +2.047 |
ount | +1.889 |
Jas | +1.786 |
blo | +1.773 |
paints | +1.764 |
Neg logit contributions | |
tum | -2.007 |
thirst | -1.741 |
night | -1.731 |
steak | -1.658 |
dinner | -1.610 |
Token | what |
Token ID | 644 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ples | +3.346 |
ount | +2.918 |
ydia | +2.886 |
yl | +2.873 |
Jas | +2.867 |
Neg logit contributions | |
tum | -4.631 |
steak | -4.095 |
dinner | -3.927 |
night | -3.913 |
thirst | -3.899 |
Token | is |
Token ID | 318 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ples | +2.952 |
ount | +2.676 |
Jas | +2.470 |
ydia | +2.459 |
violet | +2.457 |
Neg logit contributions | |
tum | -3.312 |
night | -2.813 |
steak | -2.787 |
time | -2.647 |
dinner | -2.646 |
Token | comes |
Token ID | 2058 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
ples | +7.262 |
ount | +6.653 |
ydia | +6.480 |
ptions | +6.229 |
od | +6.212 |
Neg logit contributions | |
tum | -7.545 |
night | -6.401 |
sled | -6.263 |
leg | -6.186 |
drowned | -6.133 |
Token | to |
Token ID | 284 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
ples | +1.933 |
ount | +1.817 |
Jas | +1.761 |
paints | +1.735 |
yl | +1.732 |
Neg logit contributions | |
tum | -1.200 |
night | -0.992 |
thirst | -0.986 |
steak | -0.911 |
lung | -0.878 |
Token | the |
Token ID | 262 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ples | +1.584 |
ount | +1.454 |
Jas | +1.397 |
paints | +1.362 |
blo | +1.361 |
Neg logit contributions | |
tum | -1.703 |
thirst | -1.488 |
night | -1.484 |
steak | -1.422 |
lung | -1.370 |
Token | yard |
Token ID | 12699 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ples | +2.808 |
ount | +2.584 |
Jas | +2.514 |
yl | +2.419 |
Kay | +2.384 |
Neg logit contributions | |
tum | -3.226 |
steak | -2.719 |
thirst | -2.688 |
dinner | -2.626 |
lung | -2.624 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ples | +2.554 |
ount | +2.375 |
Jas | +2.342 |
ydia | +2.317 |
yl | +2.286 |
Neg logit contributions | |
tum | -2.221 |
thirst | -1.851 |
night | -1.842 |
steak | -1.771 |
leg | -1.730 |
Token | She |
Token ID | 1375 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
ples | +2.143 |
ount | +1.888 |
ptions | +1.768 |
yl | +1.746 |
Jas | +1.717 |
Neg logit contributions | |
tum | -4.065 |
night | -3.505 |
thirst | -3.381 |
steak | -3.356 |
lung | -3.286 |
Token | sees |
Token ID | 7224 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ples | +7.542 |
ount | +7.122 |
od | +6.991 |
ydia | +6.686 |
written | +6.600 |
Neg logit contributions | |
tum | -7.989 |
sled | -6.639 |
leg | -6.563 |
drowned | -6.345 |
steak | -6.298 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ples | +2.892 |
ount | +2.653 |
Jas | +2.619 |
yl | +2.569 |
ydia | +2.562 |
Neg logit contributions | |
tum | -2.552 |
steak | -2.222 |
thirst | -2.126 |
night | -2.122 |
dinner | -2.025 |
Token | box |
Token ID | 3091 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ples | +3.735 |
ount | +3.474 |
Jas | +3.352 |
ain | +3.248 |
ydia | +3.203 |
Neg logit contributions | |
tum | -3.522 |
steak | -2.938 |
thirst | -2.880 |
lung | -2.807 |
dinner | -2.761 |
Token | and |
Token ID | 290 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
ples | +4.382 |
ount | +4.131 |
ydia | +4.128 |
Jas | +4.050 |
ptions | +3.970 |
Neg logit contributions | |
tum | -3.107 |
leg | -2.462 |
thirst | -2.439 |
night | -2.413 |
steak | -2.382 |
Token | the |
Token ID | 262 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ples | +8.173 |
ount | +7.822 |
yl | +7.309 |
ydia | +7.256 |
od | +7.209 |
Neg logit contributions | |
tum | -3.939 |
steak | -2.972 |
leg | -2.852 |
sled | -2.793 |
dinner | -2.777 |
Token | Sara |
Token ID | 24799 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ples | +1.398 |
ount | +1.237 |
Jas | +1.209 |
paints | +1.192 |
yl | +1.174 |
Neg logit contributions | |
tum | -2.076 |
thirst | -1.835 |
night | -1.820 |
steak | -1.779 |
lung | -1.701 |
Token | and |
Token ID | 290 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ples | +0.361 |
ount | +0.334 |
Jas | +0.334 |
yl | +0.323 |
paints | +0.323 |
Neg logit contributions | |
tum | -0.321 |
thirst | -0.278 |
night | -0.276 |
steak | -0.259 |
lung | -0.251 |
Token | Ben |
Token ID | 3932 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
ples | +2.810 |
ount | +2.543 |
yl | +2.517 |
Jas | +2.461 |
ydia | +2.441 |
Neg logit contributions | |
tum | -3.086 |
night | -2.662 |
thirst | -2.644 |
steak | -2.507 |
lung | -2.437 |
Token | fighting |
Token ID | 4330 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
ples | +1.009 |
Jas | +0.922 |
ount | +0.919 |
yl | +0.895 |
paints | +0.882 |
Neg logit contributions | |
tum | -1.123 |
thirst | -0.981 |
night | -0.976 |
steak | -0.923 |
lung | -0.903 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ples | +1.248 |
ount | +1.140 |
Jas | +1.132 |
yl | +1.106 |
paints | +1.084 |
Neg logit contributions | |
tum | -1.377 |
night | -1.219 |
thirst | -1.197 |
steak | -1.146 |
lung | -1.105 |
Token | She |
Token ID | 1375 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
ples | +2.048 |
ount | +1.729 |
ptions | +1.683 |
yl | +1.653 |
Jas | +1.631 |
Neg logit contributions | |
tum | -3.808 |
thirst | -3.248 |
night | -3.227 |
steak | -3.136 |
lung | -3.064 |
Token | comes |
Token ID | 2058 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
ples | +8.389 |
ount | +7.646 |
Jem | +7.481 |
illian | +7.434 |
Jas | +7.389 |
Neg logit contributions | |
tum | -6.776 |
night | -5.670 |
leg | -5.627 |
muscle | -5.619 |
drowned | -5.477 |
Token | to |
Token ID | 284 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
ples | +1.454 |
ount | +1.363 |
Jas | +1.339 |
yl | +1.310 |
paints | +1.308 |
Neg logit contributions | |
tum | -0.955 |
night | -0.798 |
thirst | -0.797 |
steak | -0.731 |
lung | -0.707 |
Token | see |
Token ID | 766 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ples | +1.478 |
ount | +1.344 |
Jas | +1.302 |
paints | +1.277 |
yl | +1.271 |
Neg logit contributions | |
tum | -1.535 |
thirst | -1.341 |
night | -1.323 |
steak | -1.261 |
lung | -1.217 |
Token | what |
Token ID | 644 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ples | +3.026 |
Jas | +2.587 |
ydia | +2.558 |
ptions | +2.534 |
yl | +2.529 |
Neg logit contributions | |
tum | -4.045 |
thirst | -3.469 |
steak | -3.438 |
night | -3.329 |
lung | -3.269 |
Token | is |
Token ID | 318 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ples | +2.262 |
ount | +2.026 |
Jas | +1.953 |
ydia | +1.910 |
ptions | +1.903 |
Neg logit contributions | |
tum | -2.346 |
night | -1.973 |
steak | -1.941 |
thirst | -1.916 |
lung | -1.833 |
Token | and |
Token ID | 290 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
ples | +1.028 |
Jas | +0.946 |
ount | +0.943 |
yl | +0.920 |
paints | +0.912 |
Neg logit contributions | |
tum | -0.921 |
night | -0.790 |
thirst | -0.789 |
steak | -0.742 |
lung | -0.719 |
Token | comes |
Token ID | 2058 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ples | +4.928 |
ount | +4.439 |
ydia | +4.297 |
written | +4.041 |
blo | +4.034 |
Neg logit contributions | |
tum | -6.999 |
night | -6.228 |
leg | -5.778 |
sled | -5.768 |
muscle | -5.738 |
Token | to |
Token ID | 284 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ples | +2.925 |
ount | +2.764 |
violet | +2.660 |
Jas | +2.657 |
ydia | +2.648 |
Neg logit contributions | |
tum | -1.535 |
night | -1.236 |
thirst | -1.216 |
steak | -1.110 |
leg | -1.088 |
Token | see |
Token ID | 766 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ples | +2.001 |
ount | +1.848 |
Jas | +1.736 |
blo | +1.730 |
paints | +1.729 |
Neg logit contributions | |
tum | -2.004 |
thirst | -1.745 |
night | -1.738 |
steak | -1.658 |
dinner | -1.623 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ples | +3.739 |
ount | +3.336 |
violet | +3.257 |
yl | +3.248 |
ydia | +3.228 |
Neg logit contributions | |
tum | -5.086 |
steak | -4.385 |
dinner | -4.332 |
thirst | -4.254 |
night | -4.247 |
Token | She |
Token ID | 1375 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
ples | +2.343 |
ount | +2.040 |
ptions | +1.877 |
yl | +1.873 |
blo | +1.861 |
Neg logit contributions | |
tum | -4.358 |
night | -3.727 |
thirst | -3.609 |
steak | -3.556 |
leg | -3.514 |
Token | is |
Token ID | 318 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
ples | +8.180 |
ount | +7.573 |
od | +7.383 |
ydia | +7.044 |
written | +6.936 |
Neg logit contributions | |
tum | -7.388 |
leg | -5.931 |
night | -5.733 |
drowned | -5.697 |
sled | -5.637 |
Token | not |
Token ID | 407 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ples | +5.903 |
ount | +5.403 |
violet | +5.182 |
Jas | +5.179 |
od | +5.159 |
Neg logit contributions | |
tum | -2.209 |
thirst | -1.685 |
leg | -1.652 |
steak | -1.512 |
dinner | -1.464 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ples | +4.016 |
ount | +3.675 |
violet | +3.548 |
paints | +3.545 |
Jas | +3.523 |
Neg logit contributions | |
tum | -2.607 |
thirst | -2.194 |
steak | -2.114 |
night | -2.048 |
dinner | -2.040 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ples | +2.772 |
ount | +2.539 |
Jas | +2.490 |
violet | +2.475 |
ydia | +2.462 |
Neg logit contributions | |
tum | -2.403 |
night | -2.023 |
thirst | -1.963 |
steak | -1.938 |
dinner | -1.864 |
Token | She |
Token ID | 1375 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
ples | +2.640 |
ount | +2.253 |
ptions | +2.132 |
blo | +2.114 |
yl | +2.083 |
Neg logit contributions | |
tum | -4.664 |
night | -3.925 |
thirst | -3.794 |
leg | -3.736 |
steak | -3.724 |
Token |
|
Token ID | 198 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
tum | +0.817 |
night | +0.729 |
thirst | +0.727 |
steak | +0.670 |
lung | +0.650 |
Neg logit contributions | |
ples | -0.833 |
Jas | -0.794 |
ount | -0.780 |
yl | -0.761 |
paints | -0.754 |
Token | Mom |
Token ID | 29252 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
tum | +0.654 |
night | +0.565 |
thirst | +0.560 |
steak | +0.518 |
lung | +0.503 |
Neg logit contributions | |
ples | -0.765 |
Jas | -0.717 |
ount | -0.708 |
yl | -0.698 |
paints | -0.687 |
Token | hears |
Token ID | 23180 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ples | +3.968 |
ount | +3.824 |
Kay | +3.781 |
ydia | +3.658 |
Kay | +3.609 |
Neg logit contributions | |
tum | -5.238 |
night | -4.544 |
steak | -4.482 |
sled | -4.269 |
dinner | -4.239 |
Token | them |
Token ID | 606 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
ples | +2.252 |
ount | +2.057 |
blo | +1.967 |
paints | +1.939 |
yl | +1.927 |
Neg logit contributions | |
tum | -2.621 |
night | -2.277 |
thirst | -2.266 |
steak | -2.238 |
dinner | -2.173 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ples | +0.947 |
Jas | +0.869 |
ount | +0.868 |
yl | +0.844 |
paints | +0.839 |
Neg logit contributions | |
tum | -0.878 |
thirst | -0.756 |
night | -0.756 |
steak | -0.713 |
lung | -0.693 |
Token | She |
Token ID | 1375 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
ples | +3.904 |
ount | +3.481 |
ptions | +3.408 |
angles | +3.276 |
yl | +3.154 |
Neg logit contributions | |
tum | -5.500 |
night | -4.523 |
leg | -4.393 |
time | -4.363 |
thirst | -4.310 |
Token | comes |
Token ID | 2058 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
ples | +7.302 |
ount | +6.696 |
ydia | +6.428 |
umes | +6.303 |
od | +6.299 |
Neg logit contributions | |
tum | -7.806 |
night | -6.741 |
sled | -6.696 |
leg | -6.671 |
muscle | -6.614 |
Token | to |
Token ID | 284 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ples | +1.720 |
ount | +1.613 |
Jas | +1.574 |
yl | +1.548 |
paints | +1.547 |
Neg logit contributions | |
tum | -1.074 |
night | -0.890 |
thirst | -0.884 |
steak | -0.819 |
lung | -0.787 |
Token | their |
Token ID | 511 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ples | +2.234 |
ount | +2.061 |
Jas | +1.937 |
blo | +1.934 |
paints | +1.922 |
Neg logit contributions | |
tum | -2.148 |
thirst | -1.858 |
night | -1.836 |
steak | -1.761 |
dinner | -1.728 |
Token | room |
Token ID | 2119 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
ples | +1.044 |
ount | +0.952 |
Jas | +0.929 |
yl | +0.902 |
ydia | +0.887 |
Neg logit contributions | |
tum | -1.324 |
thirst | -1.158 |
night | -1.144 |
steak | -1.101 |
lung | -1.076 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
ples | +1.345 |
ount | +1.239 |
Jas | +1.225 |
yl | +1.188 |
ydia | +1.185 |
Neg logit contributions | |
tum | -1.316 |
night | -1.121 |
thirst | -1.119 |
steak | -1.067 |
lung | -1.029 |
Token |
|
Token ID | 198 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
tum | +0.687 |
thirst | +0.612 |
night | +0.611 |
steak | +0.561 |
lung | +0.546 |
Neg logit contributions | |
ples | -0.724 |
Jas | -0.684 |
ount | -0.676 |
paints | -0.656 |
yl | -0.656 |
Token | Mom |
Token ID | 29252 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
tum | +1.466 |
night | +1.293 |
thirst | +1.275 |
steak | +1.164 |
lung | +1.146 |
Neg logit contributions | |
ples | -1.422 |
Jas | -1.302 |
ount | -1.291 |
paints | -1.278 |
yl | -1.275 |
Token | hears |
Token ID | 23180 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
ples | +4.149 |
ount | +3.991 |
Kay | +3.971 |
ydia | +3.817 |
Jas | +3.809 |
Neg logit contributions | |
tum | -5.103 |
night | -4.388 |
steak | -4.386 |
dinner | -4.142 |
leg | -4.096 |
Token | them |
Token ID | 606 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
ples | +0.993 |
ount | +0.903 |
Jas | +0.877 |
yl | +0.854 |
paints | +0.848 |
Neg logit contributions | |
tum | -1.472 |
thirst | -1.308 |
night | -1.308 |
steak | -1.266 |
lung | -1.217 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ples | +1.031 |
Jas | +0.945 |
ount | +0.942 |
yl | +0.918 |
paints | +0.910 |
Neg logit contributions | |
tum | -1.010 |
thirst | -0.873 |
night | -0.872 |
steak | -0.824 |
lung | -0.800 |
Token | She |
Token ID | 1375 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
ples | +2.518 |
ount | +2.205 |
ptions | +2.118 |
yl | +2.084 |
Jas | +2.030 |
Neg logit contributions | |
tum | -4.518 |
night | -3.858 |
thirst | -3.757 |
steak | -3.715 |
leg | -3.633 |
Token | comes |
Token ID | 2058 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ples | +7.586 |
ount | +6.983 |
od | +6.673 |
ydia | +6.615 |
umes | +6.540 |
Neg logit contributions | |
tum | -7.691 |
night | -6.411 |
leg | -6.398 |
drowned | -6.287 |
sled | -6.279 |
Token | to |
Token ID | 284 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ples | +1.603 |
ount | +1.504 |
Jas | +1.472 |
yl | +1.444 |
paints | +1.443 |
Neg logit contributions | |
tum | -0.996 |
night | -0.825 |
thirst | -0.823 |
steak | -0.760 |
lung | -0.727 |
Token | their |
Token ID | 511 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ples | +1.710 |
ount | +1.582 |
Jas | +1.518 |
yl | +1.487 |
blo | +1.482 |
Neg logit contributions | |
tum | -1.684 |
thirst | -1.464 |
night | -1.454 |
steak | -1.397 |
dinner | -1.344 |
Token | room |
Token ID | 2119 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
ples | +1.083 |
ount | +0.992 |
Jas | +0.969 |
yl | +0.937 |
ydia | +0.921 |
Neg logit contributions | |
tum | -1.389 |
thirst | -1.215 |
night | -1.199 |
steak | -1.158 |
lung | -1.129 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ples | +1.469 |
ount | +1.354 |
Jas | +1.339 |
yl | +1.299 |
ydia | +1.297 |
Neg logit contributions | |
tum | -1.451 |
thirst | -1.236 |
night | -1.231 |
steak | -1.172 |
lung | -1.130 |
Token | comes |
Token ID | 2058 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
ples | +7.147 |
ount | +6.561 |
ydia | +6.400 |
written | +6.228 |
od | +6.194 |
Neg logit contributions | |
tum | -7.572 |
sled | -6.379 |
leg | -6.349 |
night | -6.334 |
muscle | -6.170 |
Token | to |
Token ID | 284 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ples | +1.378 |
ount | +1.292 |
Jas | +1.265 |
paints | +1.242 |
yl | +1.240 |
Neg logit contributions | |
tum | -0.921 |
night | -0.773 |
thirst | -0.771 |
steak | -0.711 |
lung | -0.684 |
Token | the |
Token ID | 262 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
ples | +1.650 |
ount | +1.498 |
Jas | +1.446 |
paints | +1.419 |
ydia | +1.412 |
Neg logit contributions | |
tum | -1.748 |
thirst | -1.532 |
night | -1.529 |
steak | -1.459 |
dinner | -1.409 |
Token | room |
Token ID | 2119 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ples | +1.341 |
ount | +1.217 |
Jas | +1.210 |
yl | +1.168 |
Kay | +1.129 |
Neg logit contributions | |
tum | -1.797 |
thirst | -1.567 |
night | -1.539 |
steak | -1.519 |
lung | -1.483 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ples | +2.592 |
ount | +2.405 |
Jas | +2.346 |
ydia | +2.324 |
yl | +2.299 |
Neg logit contributions | |
tum | -2.271 |
night | -1.894 |
thirst | -1.878 |
steak | -1.793 |
leg | -1.745 |
Token | She |
Token ID | 1375 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ples | +2.631 |
ount | +2.276 |
ptions | +2.188 |
ydia | +2.186 |
Jas | +2.157 |
Neg logit contributions | |
tum | -3.999 |
night | -3.397 |
thirst | -3.311 |
steak | -3.243 |
lung | -3.232 |
Token | sees |
Token ID | 7224 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ples | +7.436 |
ount | +7.051 |
od | +6.971 |
ydia | +6.525 |
written | +6.445 |
Neg logit contributions | |
tum | -8.097 |
leg | -6.635 |
sled | -6.451 |
night | -6.262 |
steak | -6.230 |
Token | Anna |
Token ID | 11735 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ples | +3.577 |
ount | +3.207 |
ydia | +3.146 |
Jas | +3.141 |
yl | +3.087 |
Neg logit contributions | |
tum | -3.019 |
steak | -2.611 |
thirst | -2.499 |
night | -2.457 |
dinner | -2.425 |
Token | and |
Token ID | 290 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ples | +2.413 |
Jas | +2.296 |
ount | +2.278 |
Kay | +2.210 |
ydia | +2.204 |
Neg logit contributions | |
tum | -1.723 |
thirst | -1.435 |
night | -1.415 |
steak | -1.373 |
lung | -1.356 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ples | +3.468 |
ount | +3.257 |
yl | +3.149 |
ydia | +3.068 |
Jas | +3.058 |
Neg logit contributions | |
tum | -2.538 |
night | -2.071 |
thirst | -2.064 |
steak | -2.043 |
lung | -1.925 |
Token | struggle |
Token ID | 6531 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
ples | +1.827 |
Jas | +1.698 |
ount | +1.677 |
yl | +1.640 |
ydia | +1.625 |
Neg logit contributions | |
tum | -1.969 |
thirst | -1.715 |
night | -1.672 |
steak | -1.620 |
lung | -1.600 |
Token | It |
Token ID | 632 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
ples | +4.121 |
ptions | +3.841 |
ount | +3.823 |
Jas | +3.682 |
ydia | +3.670 |
Neg logit contributions | |
tum | -3.366 |
night | -2.838 |
lung | -2.740 |
steak | -2.703 |
His | -2.658 |
Token | is |
Token ID | 318 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ples | +7.288 |
ount | +6.803 |
ptions | +6.759 |
ydia | +6.713 |
Jem | +6.603 |
Neg logit contributions | |
tum | -5.278 |
night | -4.595 |
lung | -4.351 |
leg | -4.202 |
steak | -4.162 |
Token | their |
Token ID | 511 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
ples | +4.213 |
ount | +3.908 |
paints | +3.834 |
ptions | +3.685 |
iddling | +3.677 |
Neg logit contributions | |
tum | -2.572 |
thirst | -2.151 |
steak | -2.069 |
night | -2.060 |
lung | -2.018 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
ples | +2.260 |
ount | +2.124 |
Jas | +2.069 |
ptions | +2.020 |
ydia | +2.007 |
Neg logit contributions | |
tum | -0.892 |
thirst | -0.641 |
night | -0.641 |
steak | -0.597 |
lung | -0.571 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ydia | +5.848 |
ples | +5.847 |
ount | +5.692 |
Jas | +5.659 |
paints | +5.568 |
Neg logit contributions | |
tum | -3.876 |
lung | -3.093 |
steak | -3.060 |
night | -3.037 |
thirst | -2.995 |
Token | She |
Token ID | 1375 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ples | +5.020 |
ptions | +4.723 |
ount | +4.562 |
paints | +4.367 |
ydia | +4.336 |
Neg logit contributions | |
tum | -4.453 |
night | -3.579 |
His | -3.508 |
lung | -3.407 |
steak | -3.356 |
Token | is |
Token ID | 318 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ples | +7.905 |
ount | +7.628 |
ptions | +7.534 |
ydia | +7.462 |
Jem | +7.217 |
Neg logit contributions | |
tum | -6.974 |
lung | -6.063 |
night | -5.974 |
sled | -5.773 |
steak | -5.725 |
Token | holding |
Token ID | 4769 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
ples | +6.397 |
ount | +5.696 |
pill | +5.508 |
paints | +5.482 |
angles | +5.386 |
Neg logit contributions | |
tum | -4.098 |
thirst | -3.404 |
leg | -3.372 |
steak | -3.318 |
dinner | -3.286 |
Token | a |
Token ID | 257 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ples | +1.383 |
ount | +1.294 |
Jas | +1.265 |
yl | +1.233 |
paints | +1.224 |
Neg logit contributions | |
tum | -1.236 |
thirst | -1.079 |
night | -1.063 |
steak | -1.020 |
lung | -0.980 |
Token | shiny |
Token ID | 22441 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ples | +2.244 |
ount | +2.119 |
Jas | +2.054 |
ydia | +1.924 |
ain | +1.895 |
Neg logit contributions | |
tum | -2.233 |
steak | -1.865 |
thirst | -1.855 |
night | -1.822 |
lung | -1.793 |
Token | key |
Token ID | 1994 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ples | +1.812 |
ount | +1.711 |
Jas | +1.679 |
ydia | +1.571 |
Kay | +1.548 |
Neg logit contributions | |
tum | -1.887 |
night | -1.621 |
thirst | -1.616 |
steak | -1.586 |
lung | -1.533 |
Token | decided |
Token ID | 3066 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
tum | +0.125 |
thirst | +0.110 |
night | +0.110 |
steak | +0.104 |
lung | +0.101 |
Neg logit contributions | |
ples | -0.108 |
Jas | -0.099 |
ount | -0.098 |
yl | -0.096 |
paints | -0.095 |
Token | to |
Token ID | 284 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ples | +0.648 |
ount | +0.604 |
Jas | +0.602 |
paints | +0.585 |
yl | +0.584 |
Neg logit contributions | |
tum | -0.444 |
thirst | -0.374 |
night | -0.372 |
steak | -0.345 |
lung | -0.331 |
Token | go |
Token ID | 467 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
tum | +0.247 |
thirst | +0.216 |
night | +0.215 |
steak | +0.203 |
lung | +0.196 |
Neg logit contributions | |
ples | -0.251 |
Jas | -0.233 |
ount | -0.231 |
paints | -0.225 |
yl | -0.224 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ples | +3.627 |
ount | +3.277 |
Jas | +3.251 |
ptions | +3.186 |
paints | +3.170 |
Neg logit contributions | |
tum | -2.138 |
thirst | -1.793 |
night | -1.782 |
steak | -1.659 |
leg | -1.636 |
Token | touch |
Token ID | 3638 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
tum | +0.241 |
thirst | +0.213 |
night | +0.212 |
steak | +0.201 |
lung | +0.195 |
Neg logit contributions | |
ples | -0.214 |
Jas | -0.198 |
ount | -0.196 |
paints | -0.192 |
yl | -0.190 |
Token | the |
Token ID | 262 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ples | +1.389 |
ount | +1.296 |
Jas | +1.271 |
yl | +1.237 |
paints | +1.225 |
Neg logit contributions | |
tum | -1.352 |
thirst | -1.181 |
night | -1.159 |
steak | -1.113 |
lung | -1.078 |
Token | staff |
Token ID | 3085 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
ples | +7.597 |
Jas | +7.017 |
ount | +6.918 |
iddling | +6.749 |
typing | +6.616 |
Neg logit contributions | |
tum | -8.046 |
thirst | -6.705 |
dinner | -6.485 |
job | -6.445 |
lesson | -6.379 |
Token | , |
Token ID | 11 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
tum | +0.645 |
thirst | +0.568 |
night | +0.567 |
steak | +0.526 |
lung | +0.511 |
Neg logit contributions | |
ples | -0.616 |
Jas | -0.565 |
ount | -0.563 |
paints | -0.550 |
yl | -0.545 |
Token | even |
Token ID | 772 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
tum | +0.306 |
night | +0.269 |
thirst | +0.267 |
steak | +0.250 |
lung | +0.242 |
Neg logit contributions | |
ples | -0.327 |
Jas | -0.303 |
ount | -0.300 |
paints | -0.294 |
yl | -0.290 |
Token | though |
Token ID | 996 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ples | +0.391 |
ount | +0.363 |
Jas | +0.362 |
yl | +0.351 |
paints | +0.351 |
Neg logit contributions | |
tum | -0.331 |
thirst | -0.286 |
night | -0.284 |
steak | -0.266 |
lung | -0.257 |
Token | he |
Token ID | 339 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ples | +0.468 |
ount | +0.433 |
Jas | +0.432 |
yl | +0.419 |
paints | +0.419 |
Neg logit contributions | |
tum | -0.400 |
thirst | -0.345 |
night | -0.343 |
steak | -0.322 |
lung | -0.311 |
Token | and |
Token ID | 290 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ples | +0.910 |
Jas | +0.838 |
ount | +0.836 |
yl | +0.814 |
paints | +0.808 |
Neg logit contributions | |
tum | -0.834 |
thirst | -0.717 |
night | -0.717 |
steak | -0.673 |
lung | -0.653 |
Token | comes |
Token ID | 2058 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ples | +4.455 |
ount | +4.003 |
ydia | +3.897 |
yl | +3.778 |
written | +3.736 |
Neg logit contributions | |
tum | -6.115 |
night | -5.374 |
sled | -5.054 |
steak | -5.036 |
thirst | -5.028 |
Token | to |
Token ID | 284 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ples | +3.155 |
ount | +2.979 |
violet | +2.873 |
Jas | +2.860 |
yl | +2.855 |
Neg logit contributions | |
tum | -1.664 |
night | -1.318 |
thirst | -1.302 |
steak | -1.178 |
leg | -1.173 |
Token | see |
Token ID | 766 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ples | +1.899 |
ount | +1.748 |
Jas | +1.656 |
paints | +1.640 |
yl | +1.635 |
Neg logit contributions | |
tum | -1.988 |
thirst | -1.730 |
night | -1.729 |
steak | -1.635 |
dinner | -1.598 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ples | +2.609 |
ount | +2.319 |
yl | +2.297 |
Jas | +2.284 |
ydia | +2.282 |
Neg logit contributions | |
tum | -3.933 |
night | -3.433 |
steak | -3.422 |
thirst | -3.404 |
dinner | -3.325 |
Token | She |
Token ID | 1375 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ples | +2.416 |
ount | +2.157 |
ptions | +2.033 |
Jas | +2.007 |
yl | +1.996 |
Neg logit contributions | |
tum | -3.830 |
night | -3.280 |
thirst | -3.187 |
steak | -3.109 |
lung | -3.062 |
Token | sees |
Token ID | 7224 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ples | +7.681 |
ount | +7.236 |
od | +7.191 |
written | +6.834 |
ydia | +6.681 |
Neg logit contributions | |
tum | -7.678 |
leg | -6.354 |
drowned | -6.173 |
sled | -6.138 |
night | -5.971 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ples | +3.390 |
ount | +3.085 |
Jas | +3.029 |
yl | +3.014 |
ydia | +2.966 |
Neg logit contributions | |
tum | -2.966 |
steak | -2.565 |
thirst | -2.472 |
night | -2.450 |
dinner | -2.366 |
Token | broken |
Token ID | 5445 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ples | +3.814 |
ount | +3.716 |
Jas | +3.637 |
yl | +3.305 |
Kay | +3.300 |
Neg logit contributions | |
tum | -4.033 |
steak | -3.317 |
lung | -3.305 |
thirst | -3.266 |
leg | -3.233 |
Token | comb |
Token ID | 1974 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
ount | +3.119 |
ples | +3.077 |
Jas | +2.986 |
ptions | +2.748 |
ydia | +2.712 |
Neg logit contributions | |
tum | -3.463 |
lung | -2.913 |
thirst | -2.876 |
steak | -2.868 |
night | -2.865 |
Token | and |
Token ID | 290 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
ples | +1.051 |
ount | +0.974 |
Jas | +0.971 |
yl | +0.932 |
ydia | +0.924 |
Neg logit contributions | |
tum | -1.014 |
thirst | -0.874 |
night | -0.873 |
steak | -0.828 |
lung | -0.810 |
Token | It |
Token ID | 632 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ples | +3.825 |
ptions | +3.529 |
ount | +3.408 |
paints | +3.362 |
Jas | +3.352 |
Neg logit contributions | |
tum | -3.648 |
night | -3.010 |
thirst | -2.928 |
steak | -2.902 |
lung | -2.858 |
Token | is |
Token ID | 318 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ples | +6.973 |
ount | +6.495 |
ptions | +6.414 |
ydia | +6.319 |
Jem | +6.214 |
Neg logit contributions | |
tum | -5.223 |
night | -4.525 |
lung | -4.208 |
steak | -4.091 |
leg | -4.035 |
Token | their |
Token ID | 511 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ples | +3.905 |
ount | +3.629 |
paints | +3.558 |
Jas | +3.434 |
ptions | +3.431 |
Neg logit contributions | |
tum | -2.248 |
thirst | -1.869 |
night | -1.776 |
steak | -1.737 |
lung | -1.701 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
tum | +1.450 |
thirst | +1.358 |
night | +1.330 |
steak | +1.147 |
lung | +1.117 |
Neg logit contributions | |
paints | -2.004 |
ples | -1.984 |
Jas | -1.961 |
yl | -1.882 |
blo | -1.879 |
Token | . |
Token ID | 13 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
ples | +5.238 |
ydia | +5.145 |
ount | +5.023 |
Jas | +5.006 |
violet | +4.936 |
Neg logit contributions | |
tum | -3.721 |
night | -2.944 |
lung | -2.940 |
thirst | -2.927 |
steak | -2.922 |
Token | She |
Token ID | 1375 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ples | +4.547 |
ptions | +4.187 |
ount | +3.927 |
paints | +3.853 |
iddling | +3.809 |
Neg logit contributions | |
tum | -4.956 |
night | -3.947 |
His | -3.800 |
thirst | -3.776 |
steak | -3.766 |
Token | comes |
Token ID | 2058 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ples | +8.288 |
ount | +7.966 |
ptions | +7.883 |
ydia | +7.821 |
Jas | +7.479 |
Neg logit contributions | |
tum | -7.016 |
lung | -5.935 |
night | -5.910 |
steak | -5.621 |
drowned | -5.582 |
Token | into |
Token ID | 656 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ples | +0.564 |
ount | +0.524 |
Jas | +0.522 |
yl | +0.507 |
paints | +0.507 |
Neg logit contributions | |
tum | -0.432 |
thirst | -0.368 |
night | -0.366 |
steak | -0.341 |
lung | -0.330 |
Token | the |
Token ID | 262 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ples | +2.320 |
ount | +2.181 |
Jas | +2.063 |
ydia | +2.051 |
paints | +2.038 |
Neg logit contributions | |
tum | -1.946 |
thirst | -1.664 |
night | -1.633 |
steak | -1.620 |
lung | -1.566 |
Token | room |
Token ID | 2119 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ples | +0.674 |
ount | +0.609 |
Jas | +0.604 |
yl | +0.580 |
ydia | +0.567 |
Neg logit contributions | |
tum | -0.928 |
thirst | -0.814 |
night | -0.811 |
steak | -0.782 |
lung | -0.761 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ples | +2.608 |
ount | +2.436 |
ydia | +2.392 |
Jas | +2.389 |
yl | +2.316 |
Neg logit contributions | |
tum | -2.283 |
night | -1.901 |
thirst | -1.878 |
steak | -1.813 |
lung | -1.741 |
Token | steak |
Token ID | 26320 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
thirst | +4.055 |
tum | +3.842 |
night | +3.453 |
drowned | +3.372 |
edly | +3.370 |
Neg logit contributions | |
paints | -5.829 |
written | -5.581 |
mirror | -5.537 |
ples | -5.457 |
typing | -5.442 |
Token | . |
Token ID | 13 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
tum | +3.904 |
thirst | +3.606 |
night | +3.543 |
bye | +3.289 |
lung | +3.271 |
Neg logit contributions | |
ples | -2.488 |
blo | -2.320 |
paints | -2.267 |
ount | -2.230 |
written | -2.227 |
Token |
|
Token ID | 198 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
ples | +0.654 |
ount | +0.605 |
Jas | +0.604 |
yl | +0.589 |
paints | +0.586 |
Neg logit contributions | |
tum | -0.506 |
thirst | -0.430 |
night | -0.427 |
steak | -0.398 |
lung | -0.382 |
Token |
|
Token ID | 198 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
tum | +0.062 |
thirst | +0.054 |
night | +0.053 |
steak | +0.050 |
lung | +0.048 |
Neg logit contributions | |
ples | -0.071 |
Jas | -0.067 |
ount | -0.066 |
yl | -0.065 |
paints | -0.064 |
Token | While |
Token ID | 3633 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ples | +0.094 |
ount | +0.088 |
Jas | +0.088 |
yl | +0.085 |
paints | +0.085 |
Neg logit contributions | |
tum | -0.057 |
thirst | -0.047 |
night | -0.047 |
steak | -0.043 |
lung | -0.041 |
Token | his |
Token ID | 465 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
tum | +1.643 |
night | +1.471 |
thirst | +1.431 |
lung | +1.311 |
steak | +1.298 |
Neg logit contributions | |
ples | -1.796 |
Jas | -1.757 |
yl | -1.684 |
paints | -1.681 |
blo | -1.667 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
thirst | +6.118 |
alas | +6.004 |
Sadly | +5.939 |
bye | +5.869 |
night | +5.790 |
Neg logit contributions | |
paints | -7.094 |
mirror | -6.674 |
paintings | -6.673 |
typing | -6.597 |
makeup | -6.419 |
Token | was |
Token ID | 373 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
tum | +2.708 |
thirst | +2.494 |
night | +2.456 |
steak | +2.272 |
lung | +2.245 |
Neg logit contributions | |
ples | -1.906 |
paints | -1.681 |
Jas | -1.678 |
yl | -1.648 |
written | -1.613 |
Token | busy |
Token ID | 8179 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
tum | +1.651 |
night | +1.510 |
thirst | +1.508 |
bye | +1.418 |
lung | +1.402 |
Neg logit contributions | |
ples | -0.946 |
ount | -0.841 |
Jas | -0.840 |
paints | -0.820 |
blo | -0.812 |
Token | preparing |
Token ID | 10629 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
tum | +2.410 |
thirst | +2.218 |
night | +2.169 |
bye | +2.051 |
lung | +2.013 |
Neg logit contributions | |
ples | -1.633 |
Jas | -1.431 |
blo | -1.430 |
paints | -1.423 |
ount | -1.404 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
tum | +2.346 |
thirst | +2.114 |
night | +2.063 |
bye | +1.952 |
drowned | +1.897 |
Neg logit contributions | |
ples | -2.129 |
paints | -2.013 |
Jas | -2.000 |
blo | -1.972 |
yl | -1.919 |
Token | maybe |
Token ID | 3863 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
tum | +1.842 |
night | +1.696 |
thirst | +1.678 |
drowned | +1.479 |
steak | +1.470 |
Neg logit contributions | |
ples | -1.745 |
Jas | -1.618 |
ount | -1.600 |
blo | -1.579 |
paints | -1.561 |
Token | I |
Token ID | 314 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
tum | +1.836 |
thirst | +1.648 |
night | +1.621 |
drowned | +1.417 |
lung | +1.413 |
Neg logit contributions | |
ples | -1.850 |
paints | -1.693 |
blo | -1.686 |
Jas | -1.685 |
yl | -1.651 |
Token | can |
Token ID | 460 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
ples | +1.193 |
Jas | +1.104 |
ount | +1.072 |
yl | +1.044 |
ydia | +1.039 |
Neg logit contributions | |
tum | -1.567 |
thirst | -1.395 |
night | -1.373 |
steak | -1.296 |
lung | -1.280 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
tum | +1.133 |
night | +1.026 |
thirst | +1.014 |
steak | +0.951 |
lung | +0.912 |
Neg logit contributions | |
ples | -1.139 |
ount | -1.055 |
paints | -1.034 |
Jas | -1.028 |
blo | -1.023 |
Token | it |
Token ID | 340 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
tum | +2.101 |
night | +1.897 |
thirst | +1.883 |
lung | +1.709 |
bye | +1.679 |
Neg logit contributions | |
ples | -1.769 |
blo | -1.639 |
ount | -1.624 |
paints | -1.611 |
Jas | -1.581 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
tum | +3.285 |
thirst | +3.001 |
night | +2.924 |
lung | +2.744 |
steak | +2.662 |
Neg logit contributions | |
ples | -2.641 |
blo | -2.520 |
ount | -2.520 |
paints | -2.382 |
Jas | -2.364 |
Token | He |
Token ID | 679 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
uch | +7.957 |
footing | +7.952 |
thirst | +7.912 |
tum | +7.332 |
current | +7.216 |
Neg logit contributions | |
She | -5.251 |
Kay | -5.056 |
mirror | -4.876 |
ples | -4.833 |
Paula | -4.732 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
tum | +3.369 |
thirst | +3.072 |
night | +3.038 |
lung | +2.921 |
steak | +2.881 |
Neg logit contributions | |
ples | -2.296 |
Jas | -2.097 |
yl | -2.083 |
paints | -2.076 |
violet | -2.073 |
Token | and |
Token ID | 290 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ples | +0.363 |
Jas | +0.332 |
ount | +0.332 |
yl | +0.320 |
paints | +0.319 |
Neg logit contributions | |
tum | -0.414 |
thirst | -0.365 |
night | -0.363 |
steak | -0.343 |
lung | -0.334 |
Token | looked |
Token ID | 3114 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ples | +0.223 |
Jas | +0.199 |
ount | +0.199 |
paints | +0.190 |
yl | +0.190 |
Neg logit contributions | |
tum | -0.369 |
thirst | -0.331 |
night | -0.330 |
steak | -0.315 |
lung | -0.308 |
Token | to |
Token ID | 284 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
ples | +0.880 |
Jas | +0.815 |
ount | +0.814 |
yl | +0.789 |
paints | +0.781 |
Neg logit contributions | |
tum | -0.857 |
thirst | -0.745 |
night | -0.740 |
steak | -0.696 |
lung | -0.666 |
Token | The |
Token ID | 464 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
tum | +5.003 |
night | +4.616 |
thirst | +4.448 |
steak | +4.288 |
dinner | +4.138 |
Neg logit contributions | |
ples | -2.276 |
ount | -2.103 |
Jas | -2.037 |
Mel | -1.956 |
ptions | -1.943 |
Token | waves |
Token ID | 9813 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
tum | +2.379 |
night | +2.231 |
thirst | +2.142 |
steak | +1.899 |
edly | +1.894 |
Neg logit contributions | |
ples | -2.611 |
blo | -2.525 |
paints | -2.518 |
Jas | -2.489 |
ount | -2.415 |
Token | are |
Token ID | 389 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
tum | +2.310 |
thirst | +2.121 |
night | +2.104 |
steak | +2.029 |
lung | +1.936 |
Neg logit contributions | |
ples | -1.357 |
ount | -1.224 |
Jas | -1.183 |
yl | -1.173 |
paints | -1.165 |
Token | too |
Token ID | 1165 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
tum | +2.479 |
night | +2.321 |
thirst | +2.198 |
steak | +2.074 |
bye | +2.044 |
Neg logit contributions | |
ples | -2.055 |
blo | -1.894 |
ount | -1.843 |
Jas | -1.833 |
paints | -1.799 |
Token | strong |
Token ID | 1913 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
tum | +4.455 |
thirst | +4.130 |
night | +4.097 |
edly | +3.859 |
steak | +3.616 |
Neg logit contributions | |
ples | -3.299 |
yl | -3.006 |
blo | -2.929 |
grown | -2.907 |
Jas | -2.860 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
tum | +1.889 |
thirst | +1.723 |
night | +1.607 |
steak | +1.525 |
lung | +1.513 |
Neg logit contributions | |
ples | -1.430 |
ount | -1.275 |
Jas | -1.252 |
yl | -1.207 |
paints | -1.206 |
Token | But |
Token ID | 887 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
uch | +7.423 |
steak | +7.112 |
night | +6.938 |
thirst | +6.877 |
lung | +6.817 |
Neg logit contributions | |
Jas | -6.505 |
Kay | -5.675 |
paints | -5.519 |
Jenn | -5.366 |
drawn | -5.327 |
Token | no |
Token ID | 645 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
tum | +4.594 |
night | +4.588 |
steak | +4.174 |
ages | +4.159 |
thirst | +4.149 |
Neg logit contributions | |
Jas | -4.194 |
Kay | -3.954 |
ples | -3.763 |
yl | -3.749 |
Jenn | -3.691 |
Token | one |
Token ID | 530 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
tum | +3.947 |
thirst | +3.531 |
edly | +3.386 |
night | +3.280 |
ages | +3.258 |
Neg logit contributions | |
ples | -3.479 |
yl | -3.244 |
Jas | -3.243 |
paints | -3.121 |
Kay | -3.072 |
Token | was |
Token ID | 373 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
tum | +1.289 |
thirst | +1.181 |
night | +1.168 |
steak | +1.116 |
lung | +1.088 |
Neg logit contributions | |
ples | -0.697 |
Jas | -0.624 |
yl | -0.617 |
ount | -0.598 |
paints | -0.592 |
Token | there |
Token ID | 612 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
tum | +0.898 |
night | +0.796 |
thirst | +0.785 |
steak | +0.732 |
lung | +0.713 |
Neg logit contributions | |
ples | -0.739 |
Jas | -0.667 |
ount | -0.666 |
yl | -0.649 |
blo | -0.647 |
Token | to |
Token ID | 284 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
tum | +2.402 |
thirst | +2.265 |
night | +2.175 |
lung | +1.998 |
uch | +1.966 |
Neg logit contributions | |
ples | -2.489 |
Jas | -2.359 |
Kay | -2.335 |
ount | -2.326 |
paints | -2.309 |
Token | walk |
Token ID | 2513 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
tum | +1.403 |
night | +1.247 |
thirst | +1.237 |
steak | +1.171 |
lung | +1.104 |
Neg logit contributions | |
ples | -1.388 |
Jas | -1.288 |
ount | -1.284 |
blo | -1.243 |
Kay | -1.240 |
Token | home |
Token ID | 1363 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
tum | +1.881 |
thirst | +1.678 |
night | +1.636 |
steak | +1.527 |
lung | +1.513 |
Neg logit contributions | |
ples | -1.589 |
ount | -1.475 |
Jas | -1.468 |
yl | -1.410 |
blo | -1.391 |
Token | . |
Token ID | 13 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
tum | +2.649 |
thirst | +2.397 |
night | +2.382 |
steak | +2.220 |
lung | +2.172 |
Neg logit contributions | |
ples | -1.766 |
Jas | -1.665 |
ount | -1.640 |
yl | -1.585 |
blo | -1.570 |
Token | So |
Token ID | 1406 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
tum | +3.337 |
thirst | +3.196 |
night | +3.186 |
lung | +2.945 |
uch | +2.928 |
Neg logit contributions | |
ples | -4.015 |
Kay | -3.933 |
ount | -3.929 |
Jas | -3.908 |
paints | -3.647 |
Token | , |
Token ID | 11 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
tum | +6.636 |
thirst | +6.552 |
night | +6.350 |
lung | +6.262 |
uch | +6.110 |
Neg logit contributions | |
Kay | -4.315 |
yl | -4.113 |
Jas | -3.705 |
blo | -3.626 |
Jem | -3.542 |
Token | he |
Token ID | 339 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
night | +7.173 |
tum | +7.130 |
thirst | +7.025 |
lung | +6.658 |
uch | +6.533 |
Neg logit contributions | |
Kay | -6.659 |
blo | -5.912 |
yl | -5.742 |
Jas | -5.670 |
Sylvia | -5.566 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
tum | +2.851 |
thirst | +2.562 |
night | +2.493 |
steak | +2.438 |
lung | +2.327 |
Neg logit contributions | |
ples | -1.738 |
yl | -1.594 |
Jas | -1.591 |
ount | -1.529 |
paints | -1.525 |
Token | his |
Token ID | 465 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
tum | +3.943 |
thirst | +3.568 |
uch | +3.459 |
night | +3.366 |
lung | +3.111 |
Neg logit contributions | |
Jas | -4.462 |
ples | -4.389 |
Kay | -4.369 |
yl | -4.274 |
blo | -4.173 |
Token | friend |
Token ID | 1545 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
tum | +0.922 |
night | +0.817 |
thirst | +0.805 |
steak | +0.738 |
lung | +0.699 |
Neg logit contributions | |
ples | -1.460 |
Jas | -1.388 |
yl | -1.362 |
ount | -1.355 |
paints | -1.352 |
Token | for |
Token ID | 329 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
tum | +0.618 |
thirst | +0.553 |
night | +0.542 |
steak | +0.504 |
lung | +0.497 |
Neg logit contributions | |
ples | -0.662 |
Jas | -0.625 |
ount | -0.621 |
yl | -0.601 |
paints | -0.598 |
Token | the |
Token ID | 262 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
tum | +0.512 |
night | +0.449 |
thirst | +0.447 |
steak | +0.401 |
lung | +0.396 |
Neg logit contributions | |
ples | -0.565 |
Jas | -0.524 |
ount | -0.520 |
paints | -0.516 |
yl | -0.507 |
Token | tunnel |
Token ID | 13275 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ples | +0.524 |
ount | +0.476 |
Jas | +0.475 |
yl | +0.457 |
paints | +0.456 |
Neg logit contributions | |
tum | -0.623 |
thirst | -0.550 |
night | -0.546 |
steak | -0.517 |
lung | -0.504 |
Token | and |
Token ID | 290 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
tum | +0.664 |
thirst | +0.584 |
night | +0.575 |
steak | +0.537 |
lung | +0.529 |
Neg logit contributions | |
ples | -0.712 |
ount | -0.663 |
Jas | -0.659 |
paints | -0.641 |
yl | -0.640 |
Token | be |
Token ID | 307 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
tum | +1.290 |
night | +1.154 |
thirst | +1.145 |
steak | +1.085 |
lung | +1.041 |
Neg logit contributions | |
ples | -1.067 |
Jas | -1.002 |
paints | -0.983 |
ount | -0.975 |
blo | -0.960 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ples | +3.179 |
ount | +3.048 |
Jas | +2.913 |
yl | +2.868 |
paints | +2.859 |
Neg logit contributions | |
tum | -1.960 |
thirst | -1.728 |
night | -1.581 |
steak | -1.513 |
dinner | -1.463 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
tum | +1.914 |
thirst | +1.716 |
night | +1.663 |
steak | +1.538 |
lung | +1.527 |
Neg logit contributions | |
ples | -1.632 |
ount | -1.455 |
Jas | -1.453 |
yl | -1.430 |
blo | -1.419 |
Token | Mom |
Token ID | 11254 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
footing | +7.750 |
night | +7.365 |
uch | +7.334 |
thirst | +7.271 |
drowned | +7.133 |
Neg logit contributions | |
Jas | -5.354 |
violet | -5.296 |
paints | -5.182 |
Kay | -5.011 |
ples | -5.002 |
Token | o |
Token ID | 78 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
ples | +0.085 |
Jas | +0.077 |
ount | +0.077 |
yl | +0.075 |
paints | +0.074 |
Neg logit contributions | |
tum | -0.104 |
thirst | -0.092 |
night | -0.091 |
steak | -0.086 |
lung | -0.084 |
Token | thought |
Token ID | 1807 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
tum | +1.741 |
thirst | +1.569 |
night | +1.526 |
steak | +1.476 |
lung | +1.458 |
Neg logit contributions | |
ples | -1.350 |
Jas | -1.242 |
yl | -1.224 |
ount | -1.210 |
paints | -1.198 |
Token | about |
Token ID | 546 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
tum | +0.798 |
thirst | +0.701 |
night | +0.691 |
steak | +0.648 |
lung | +0.645 |
Neg logit contributions | |
ples | -0.724 |
Jas | -0.677 |
ount | -0.662 |
paints | -0.649 |
yl | -0.646 |
Token | it |
Token ID | 340 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
ples | +0.107 |
Jas | +0.099 |
ount | +0.098 |
yl | +0.095 |
paints | +0.095 |
Neg logit contributions | |
tum | -0.116 |
thirst | -0.102 |
night | -0.102 |
steak | -0.095 |
lung | -0.093 |
Token | of |
Token ID | 286 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
tum | +0.677 |
thirst | +0.613 |
night | +0.606 |
steak | +0.570 |
lung | +0.555 |
Neg logit contributions | |
ples | -0.531 |
Jas | -0.485 |
ount | -0.482 |
yl | -0.467 |
paints | -0.465 |
Token | the |
Token ID | 262 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
tum | +0.411 |
night | +0.367 |
thirst | +0.361 |
steak | +0.335 |
lung | +0.330 |
Neg logit contributions | |
ples | -0.350 |
Jas | -0.325 |
ount | -0.317 |
paints | -0.312 |
yl | -0.310 |
Token | hill |
Token ID | 12788 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
tum | +0.703 |
thirst | +0.622 |
night | +0.619 |
steak | +0.545 |
lung | +0.532 |
Neg logit contributions | |
ples | -0.960 |
Jas | -0.908 |
ount | -0.906 |
paints | -0.906 |
blo | -0.896 |
Token | . |
Token ID | 13 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
tum | +1.082 |
thirst | +0.971 |
night | +0.961 |
steak | +0.912 |
lung | +0.892 |
Neg logit contributions | |
ples | -0.786 |
Jas | -0.721 |
ount | -0.716 |
yl | -0.688 |
paints | -0.676 |
Token | So |
Token ID | 1406 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
thirst | +4.115 |
tum | +3.985 |
night | +3.861 |
lung | +3.712 |
footing | +3.662 |
Neg logit contributions | |
ount | -4.199 |
ples | -4.136 |
Jas | -4.121 |
Kay | -4.103 |
paints | -3.972 |
Token | , |
Token ID | 11 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
thirst | +6.048 |
tum | +6.007 |
night | +5.856 |
lung | +5.612 |
edly | +5.568 |
Neg logit contributions | |
yl | -3.288 |
Kay | -3.276 |
Jas | -2.921 |
blo | -2.899 |
ples | -2.810 |
Token | he |
Token ID | 339 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
thirst | +7.005 |
night | +6.878 |
tum | +6.825 |
edly | +6.357 |
forehead | +6.170 |
Neg logit contributions | |
Kay | -5.520 |
blo | -5.077 |
written | -5.074 |
Carrie | -5.043 |
drawn | -5.029 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
tum | +2.892 |
thirst | +2.570 |
night | +2.545 |
steak | +2.452 |
lung | +2.381 |
Neg logit contributions | |
ples | -1.973 |
Jas | -1.861 |
yl | -1.835 |
paints | -1.786 |
ount | -1.732 |
Token | running |
Token ID | 2491 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
ples | +1.430 |
ount | +1.329 |
Jas | +1.248 |
yl | +1.199 |
ydia | +1.198 |
Neg logit contributions | |
tum | -1.967 |
thirst | -1.760 |
night | -1.732 |
steak | -1.704 |
lung | -1.654 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ples | +0.121 |
Jas | +0.113 |
ount | +0.113 |
yl | +0.109 |
paints | +0.109 |
Neg logit contributions | |
tum | -0.098 |
thirst | -0.084 |
night | -0.083 |
steak | -0.078 |
lung | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
tum | +4.041 |
thirst | +3.951 |
night | +3.844 |
lung | +3.596 |
steak | +3.503 |
Neg logit contributions | |
ples | -3.241 |
ount | -3.224 |
Jas | -3.089 |
Kay | -3.023 |
paints | -2.944 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ples | +0.564 |
ount | +0.517 |
Jas | +0.516 |
yl | +0.498 |
paints | +0.497 |
Neg logit contributions | |
tum | -0.633 |
thirst | -0.558 |
night | -0.554 |
steak | -0.525 |
lung | -0.509 |
Token | |
Token ID | 220 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
tum | +2.532 |
thirst | +2.361 |
night | +2.274 |
lung | +2.172 |
steak | +2.100 |
Neg logit contributions | |
ples | -2.601 |
ount | -2.546 |
Jas | -2.513 |
Kay | -2.490 |
violet | -2.349 |
Token |
|
Token ID | 198 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
tum | +1.240 |
thirst | +1.117 |
night | +1.110 |
steak | +1.026 |
lung | +1.011 |
Neg logit contributions | |
ples | -1.204 |
ount | -1.162 |
Jas | -1.154 |
Kay | -1.087 |
paints | -1.084 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
tum | +1.584 |
thirst | +1.435 |
night | +1.422 |
lung | +1.305 |
steak | +1.298 |
Neg logit contributions | |
ples | -1.436 |
Jas | -1.384 |
ount | -1.380 |
yl | -1.332 |
Kay | -1.322 |
Token | But |
Token ID | 1537 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
tum | +2.671 |
thirst | +2.346 |
night | +2.325 |
lung | +2.113 |
steak | +1.986 |
Neg logit contributions | |
ples | -2.975 |
ount | -2.898 |
Kay | -2.811 |
Jas | -2.791 |
yl | -2.764 |
Token | , |
Token ID | 11 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
tum | +5.141 |
night | +4.630 |
thirst | +4.499 |
lung | +4.183 |
ages | +4.094 |
Neg logit contributions | |
Kay | -4.801 |
yl | -4.756 |
blo | -4.598 |
ples | -4.556 |
Jas | -4.448 |
Token | because |
Token ID | 780 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
tum | +8.462 |
night | +8.300 |
thirst | +7.851 |
uch | +7.448 |
lung | +7.376 |
Neg logit contributions | |
Kay | -4.616 |
written | -4.220 |
blo | -4.219 |
yl | -4.188 |
grown | -4.173 |
Token | Bob |
Token ID | 5811 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
tum | +5.334 |
night | +5.092 |
thirst | +4.950 |
edly | +4.436 |
bye | +4.389 |
Neg logit contributions | |
Jas | -3.346 |
Kay | -3.342 |
blo | -3.268 |
ples | -3.209 |
paints | -3.108 |
Token | was |
Token ID | 373 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
tum | +2.349 |
night | +2.102 |
thirst | +2.079 |
steak | +1.952 |
bye | +1.890 |
Neg logit contributions | |
ples | -1.909 |
paints | -1.712 |
yl | -1.700 |
Jas | -1.691 |
ount | -1.658 |
Token | so |
Token ID | 523 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
tum | +0.555 |
night | +0.493 |
thirst | +0.485 |
steak | +0.456 |
lung | +0.443 |
Neg logit contributions | |
ples | -0.531 |
Jas | -0.489 |
ount | -0.487 |
yl | -0.471 |
blo | -0.470 |
Token | lazy |
Token ID | 16931 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
tum | +2.383 |
night | +2.214 |
thirst | +2.120 |
steak | +2.053 |
lung | +2.010 |
Neg logit contributions | |
ples | -1.830 |
ount | -1.711 |
blo | -1.684 |
Jas | -1.678 |
yl | -1.668 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
tum | +3.643 |
night | +3.357 |
thirst | +3.332 |
steak | +3.193 |
bye | +3.112 |
Neg logit contributions | |
ples | -2.366 |
paints | -2.137 |
yl | -2.078 |
blo | -2.069 |
Jas | -2.044 |
Token | a |
Token ID | 257 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
tum | +2.623 |
night | +2.499 |
thirst | +2.310 |
bye | +2.281 |
steak | +2.259 |
Neg logit contributions | |
ples | -2.048 |
blo | -1.945 |
ount | -1.916 |
paints | -1.831 |
Jas | -1.825 |
Token | burning |
Token ID | 9482 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
tum | +3.979 |
night | +3.878 |
bye | +3.605 |
thirst | +3.561 |
steak | +3.483 |
Neg logit contributions | |
ples | -4.060 |
blo | -3.862 |
yl | -3.727 |
violet | -3.663 |
mirror | -3.585 |
Token | sensation |
Token ID | 18098 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
tum | +2.292 |
night | +2.069 |
thirst | +2.046 |
bye | +1.888 |
steak | +1.843 |
Neg logit contributions | |
ples | -2.540 |
blo | -2.329 |
paints | -2.288 |
Jas | -2.275 |
yl | -2.224 |
Token | on |
Token ID | 319 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
tum | +1.890 |
thirst | +1.709 |
night | +1.682 |
steak | +1.591 |
lung | +1.549 |
Neg logit contributions | |
ples | -1.579 |
Jas | -1.402 |
ount | -1.386 |
blo | -1.367 |
paints | -1.358 |
Token | his |
Token ID | 465 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
tum | +3.990 |
night | +3.778 |
thirst | +3.623 |
bye | +3.497 |
uch | +3.471 |
Neg logit contributions | |
ples | -3.418 |
Jas | -3.127 |
Kay | -3.064 |
els | -3.057 |
paints | -3.017 |
Token | paw |
Token ID | 41827 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
night | +6.402 |
bye | +5.978 |
alas | +5.583 |
tum | +5.579 |
time | +5.572 |
Neg logit contributions | |
ples | -6.794 |
paints | -6.612 |
blo | -6.132 |
els | -6.070 |
mirror | -5.951 |
Token | and |
Token ID | 290 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
tum | +3.190 |
night | +3.041 |
thirst | +3.019 |
bye | +2.755 |
steak | +2.727 |
Neg logit contributions | |
ples | -2.502 |
blo | -2.177 |
paints | -2.176 |
written | -2.138 |
ount | -2.103 |
Token | quickly |
Token ID | 2952 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
tum | +3.083 |
night | +2.870 |
thirst | +2.759 |
bye | +2.617 |
uch | +2.592 |
Neg logit contributions | |
ples | -2.778 |
Jas | -2.639 |
blo | -2.594 |
paints | -2.582 |
written | -2.481 |
Token | pulled |
Token ID | 5954 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
tum | +1.911 |
night | +1.747 |
thirst | +1.707 |
steak | +1.665 |
lung | +1.616 |
Neg logit contributions | |
ples | -1.587 |
Jas | -1.396 |
paints | -1.381 |
blo | -1.379 |
ount | -1.359 |
Token | it |
Token ID | 340 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
tum | +3.284 |
thirst | +2.992 |
night | +2.972 |
bye | +2.777 |
steak | +2.700 |
Neg logit contributions | |
ples | -2.185 |
Jas | -2.012 |
paints | -1.915 |
els | -1.876 |
yl | -1.872 |
Token | fell |
Token ID | 3214 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
tum | +3.505 |
night | +3.221 |
thirst | +3.213 |
steak | +3.078 |
dinner | +2.905 |
Neg logit contributions | |
ples | -2.246 |
paints | -1.891 |
drawn | -1.864 |
yl | -1.853 |
Jas | -1.848 |
Token | down |
Token ID | 866 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
tum | +2.505 |
thirst | +2.309 |
night | +2.207 |
steak | +2.159 |
dinner | +1.999 |
Neg logit contributions | |
ples | -2.028 |
Jas | -1.841 |
blo | -1.815 |
ount | -1.811 |
paints | -1.780 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
tum | +0.419 |
thirst | +0.372 |
night | +0.367 |
steak | +0.346 |
lung | +0.336 |
Neg logit contributions | |
ples | -0.355 |
Jas | -0.329 |
ount | -0.326 |
yl | -0.317 |
paints | -0.312 |
Token | He |
Token ID | 679 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
tum | +1.707 |
thirst | +1.603 |
night | +1.540 |
lung | +1.425 |
steak | +1.411 |
Neg logit contributions | |
ples | -1.920 |
Jas | -1.890 |
Kay | -1.802 |
ount | -1.788 |
paints | -1.788 |
Token | hurt |
Token ID | 5938 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
tum | +4.593 |
night | +4.353 |
thirst | +4.254 |
steak | +4.033 |
bye | +3.994 |
Neg logit contributions | |
ples | -3.037 |
paints | -2.870 |
yl | -2.740 |
drawn | -2.721 |
written | -2.689 |
Token | his |
Token ID | 465 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
tum | +3.290 |
night | +3.014 |
thirst | +2.888 |
uch | +2.706 |
bye | +2.616 |
Neg logit contributions | |
Jas | -4.262 |
ples | -4.156 |
Kay | -4.031 |
mirror | -3.898 |
yl | -3.898 |
Token | leg |
Token ID | 1232 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
night | +5.862 |
bye | +5.294 |
tum | +5.174 |
time | +4.983 |
thirst | +4.786 |
Neg logit contributions | |
paints | -6.806 |
yl | -6.763 |
mirror | -6.675 |
ples | -6.588 |
els | -6.523 |
Token | and |
Token ID | 290 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
tum | +2.006 |
thirst | +1.856 |
night | +1.834 |
steak | +1.724 |
bye | +1.619 |
Neg logit contributions | |
ples | -1.754 |
blo | -1.545 |
paints | -1.544 |
yl | -1.521 |
drawn | -1.515 |
Token | started |
Token ID | 2067 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
tum | +3.165 |
night | +2.987 |
thirst | +2.946 |
steak | +2.724 |
bye | +2.696 |
Neg logit contributions | |
ples | -2.956 |
Jas | -2.846 |
paints | -2.823 |
written | -2.768 |
drawn | -2.749 |
Token | to |
Token ID | 284 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
tum | +0.715 |
thirst | +0.635 |
night | +0.631 |
steak | +0.589 |
lung | +0.555 |
Neg logit contributions | |
ples | -0.839 |
Jas | -0.778 |
ount | -0.764 |
paints | -0.762 |
yl | -0.752 |
Token | suffer |
Token ID | 8659 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
tum | +1.605 |
night | +1.442 |
thirst | +1.428 |
steak | +1.352 |
bye | +1.288 |
Neg logit contributions | |
ples | -1.556 |
paints | -1.436 |
Jas | -1.431 |
blo | -1.425 |
ount | -1.416 |
Token | my |
Token ID | 1820 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
tum | +0.758 |
thirst | +0.705 |
night | +0.694 |
steak | +0.671 |
lung | +0.653 |
Neg logit contributions | |
ples | -0.230 |
Jas | -0.190 |
ount | -0.182 |
paints | -0.177 |
yl | -0.176 |
Token | fell |
Token ID | 3214 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
tum | +2.374 |
thirst | +2.265 |
night | +2.234 |
steak | +2.095 |
bye | +2.042 |
Neg logit contributions | |
ples | -1.555 |
Jas | -1.417 |
yl | -1.385 |
paints | -1.381 |
drawn | -1.335 |
Token | down |
Token ID | 866 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
tum | +2.419 |
thirst | +2.259 |
night | +2.110 |
steak | +2.066 |
lung | +1.948 |
Neg logit contributions | |
ples | -1.921 |
Jas | -1.758 |
blo | -1.737 |
ount | -1.708 |
paints | -1.707 |
Token | and |
Token ID | 290 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
tum | +0.901 |
thirst | +0.800 |
night | +0.773 |
steak | +0.728 |
lung | +0.710 |
Neg logit contributions | |
ples | -0.848 |
Jas | -0.797 |
ount | -0.785 |
yl | -0.775 |
blo | -0.767 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
tum | +2.406 |
thirst | +2.226 |
night | +2.189 |
steak | +2.099 |
bye | +1.994 |
Neg logit contributions | |
ples | -2.435 |
Jas | -2.319 |
paints | -2.299 |
blo | -2.276 |
drawn | -2.258 |
Token | his |
Token ID | 465 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
tum | +2.470 |
night | +2.070 |
thirst | +2.051 |
uch | +1.878 |
bye | +1.814 |
Neg logit contributions | |
Jas | -3.697 |
ples | -3.695 |
Kay | -3.463 |
grown | -3.388 |
yl | -3.377 |
Token | knee |
Token ID | 10329 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
night | +5.085 |
bye | +4.789 |
His | +4.601 |
Sadly | +4.553 |
By | +4.505 |
Neg logit contributions | |
mirror | -7.226 |
paints | -7.039 |
makeup | -7.034 |
jewelry | -6.849 |
blo | -6.694 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
tum | +2.305 |
thirst | +2.158 |
night | +2.114 |
steak | +2.053 |
lung | +1.919 |
Neg logit contributions | |
ples | -1.552 |
blo | -1.339 |
ount | -1.335 |
Jas | -1.332 |
paints | -1.324 |
Token | Max |
Token ID | 5436 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
tum | +1.989 |
thirst | +1.963 |
night | +1.812 |
steak | +1.660 |
bye | +1.648 |
Neg logit contributions | |
ples | -2.778 |
Jas | -2.732 |
paints | -2.612 |
Kay | -2.609 |
ydia | -2.573 |
Token | bark |
Token ID | 21405 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
tum | +3.710 |
night | +3.516 |
thirst | +3.500 |
steak | +3.382 |
bye | +3.324 |
Neg logit contributions | |
ples | -2.691 |
paints | -2.409 |
blo | -2.397 |
yl | -2.393 |
drawn | -2.374 |
Token | ed |
Token ID | 276 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
tum | +1.357 |
thirst | +1.212 |
night | +1.175 |
steak | +1.164 |
lung | +1.128 |
Neg logit contributions | |
ples | -1.188 |
ount | -1.051 |
Jas | -1.051 |
yl | -1.021 |
paints | -1.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
tum | +0.570 |
night | +0.503 |
thirst | +0.501 |
steak | +0.465 |
lung | +0.454 |
Neg logit contributions | |
ples | -0.498 |
Jas | -0.458 |
ount | -0.455 |
yl | -0.443 |
paints | -0.442 |
Token | big |
Token ID | 1263 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
tum | +0.223 |
thirst | +0.198 |
night | +0.198 |
steak | +0.183 |
lung | +0.177 |
Neg logit contributions | |
ples | -0.220 |
Jas | -0.200 |
ount | -0.199 |
paints | -0.197 |
yl | -0.193 |
Token | , |
Token ID | 11 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
ples | +1.212 |
ount | +1.151 |
Jas | +1.134 |
yl | +1.093 |
ydia | +1.084 |
Neg logit contributions | |
tum | -1.063 |
thirst | -0.896 |
night | -0.890 |
steak | -0.858 |
lung | -0.835 |
Token | mean |
Token ID | 1612 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ples | +0.853 |
ount | +0.783 |
Jas | +0.778 |
yl | +0.751 |
paints | +0.746 |
Neg logit contributions | |
tum | -0.914 |
thirst | -0.796 |
night | -0.785 |
steak | -0.752 |
lung | -0.732 |
Token | cat |
Token ID | 3797 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
ples | +2.319 |
ount | +2.188 |
Jas | +2.131 |
blo | +2.075 |
paints | +2.065 |
Neg logit contributions | |
tum | -1.601 |
night | -1.300 |
thirst | -1.270 |
steak | -1.238 |
lung | -1.214 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
tum | +1.107 |
thirst | +0.995 |
night | +0.980 |
steak | +0.927 |
lung | +0.895 |
Neg logit contributions | |
ples | -0.879 |
ount | -0.796 |
Jas | -0.787 |
yl | -0.770 |
paints | -0.759 |
Token |
|
Token ID | 198 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
night | +8.126 |
thirst | +7.721 |
tum | +7.562 |
uch | +7.456 |
bye | +7.295 |
Neg logit contributions | |
Kay | -4.651 |
Jas | -4.360 |
Jem | -4.127 |
Carrie | -4.057 |
She | -4.034 |
Token |
|
Token ID | 198 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
tum | +5.579 |
thirst | +5.471 |
night | +5.328 |
steak | +4.875 |
lung | +4.798 |
Neg logit contributions | |
Jas | -2.974 |
Kay | -2.930 |
yl | -2.911 |
ount | -2.892 |
ples | -2.860 |
Token | Spot |
Token ID | 32565 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
tum | +6.121 |
night | +5.743 |
thirst | +5.522 |
steak | +4.776 |
stomach | +4.750 |
Neg logit contributions | |
Kay | -5.494 |
ples | -5.407 |
Mel | -5.222 |
ount | -5.118 |
yl | -5.060 |
Token | 's |
Token ID | 338 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
tum | +2.621 |
night | +2.390 |
thirst | +2.346 |
steak | +2.295 |
lung | +2.182 |
Neg logit contributions | |
ples | -1.888 |
Jas | -1.712 |
yl | -1.686 |
ount | -1.645 |
Kay | -1.607 |
Token | friends |
Token ID | 2460 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
tum | +1.717 |
night | +1.629 |
thirst | +1.549 |
steak | +1.480 |
bye | +1.384 |
Neg logit contributions | |
ples | -2.356 |
Jas | -2.317 |
yl | -2.268 |
paints | -2.231 |
ydia | -2.214 |
Token | things |
Token ID | 1243 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ples | +0.375 |
ount | +0.344 |
Jas | +0.344 |
yl | +0.332 |
paints | +0.331 |
Neg logit contributions | |
tum | -0.397 |
thirst | -0.348 |
night | -0.346 |
steak | -0.327 |
lung | -0.318 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ples | +0.538 |
Jas | +0.496 |
ount | +0.496 |
yl | +0.479 |
paints | +0.478 |
Neg logit contributions | |
tum | -0.510 |
thirst | -0.443 |
night | -0.442 |
steak | -0.416 |
lung | -0.403 |
Token |
|
Token ID | 198 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
tum | +3.068 |
thirst | +2.805 |
night | +2.722 |
uch | +2.574 |
leg | +2.530 |
Neg logit contributions | |
ples | -2.490 |
Jas | -2.279 |
ount | -2.241 |
Kay | -2.200 |
paints | -2.171 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
tum | +0.509 |
thirst | +0.438 |
night | +0.437 |
steak | +0.396 |
lung | +0.390 |
Neg logit contributions | |
ples | -0.672 |
Jas | -0.636 |
ount | -0.632 |
yl | -0.616 |
paints | -0.612 |
Token | Eventually |
Token ID | 28724 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
tum | +2.313 |
thirst | +1.989 |
night | +1.930 |
lung | +1.731 |
leg | +1.712 |
Neg logit contributions | |
ples | -2.372 |
ount | -2.191 |
Jas | -2.184 |
blo | -2.167 |
yl | -2.163 |
Token | , |
Token ID | 11 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
tum | +4.976 |
thirst | +4.421 |
uch | +4.298 |
bye | +4.213 |
hind | +4.210 |
Neg logit contributions | |
ples | -3.637 |
blo | -3.415 |
Jas | -3.396 |
Kay | -3.374 |
yl | -3.325 |
Token | Henry |
Token ID | 8616 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
tum | +7.939 |
uch | +7.148 |
thirst | +7.115 |
erved | +7.033 |
knee | +7.021 |
Neg logit contributions | |
blo | -5.051 |
Kay | -4.920 |
written | -4.862 |
ples | -4.643 |
Jem | -4.592 |
Token | became |
Token ID | 2627 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
tum | +0.139 |
thirst | +0.123 |
night | +0.121 |
steak | +0.115 |
lung | +0.111 |
Neg logit contributions | |
ples | -0.125 |
Jas | -0.114 |
ount | -0.114 |
yl | -0.111 |
paints | -0.111 |
Token | the |
Token ID | 262 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
ples | +0.186 |
Jas | +0.172 |
ount | +0.172 |
paints | +0.166 |
yl | +0.166 |
Neg logit contributions | |
tum | -0.175 |
thirst | -0.152 |
night | -0.151 |
steak | -0.142 |
lung | -0.137 |
Token | most |
Token ID | 749 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
tum | +0.139 |
thirst | +0.120 |
night | +0.119 |
steak | +0.111 |
lung | +0.107 |
Neg logit contributions | |
ples | -0.170 |
Jas | -0.160 |
ount | -0.158 |
paints | -0.155 |
yl | -0.154 |
Token | knowledgeable |
Token ID | 29549 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
ples | +0.508 |
ount | +0.465 |
Jas | +0.464 |
yl | +0.447 |
paints | +0.445 |
Neg logit contributions | |
tum | -0.586 |
thirst | -0.517 |
night | -0.514 |
steak | -0.487 |
lung | -0.473 |
Token | Mama |
Token ID | 40084 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
tum | +0.694 |
thirst | +0.611 |
night | +0.600 |
steak | +0.514 |
lung | +0.506 |
Neg logit contributions | |
ples | -1.045 |
Jas | -1.007 |
ount | -0.983 |
yl | -0.975 |
Kay | -0.974 |
Token | ! |
Token ID | 0 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
ples | +2.144 |
ount | +2.008 |
Jas | +1.973 |
paints | +1.943 |
ydia | +1.933 |
Neg logit contributions | |
tum | -1.943 |
night | -1.666 |
thirst | -1.627 |
steak | -1.601 |
lung | -1.537 |
Token | A |
Token ID | 317 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
tum | +1.196 |
thirst | +1.098 |
night | +1.081 |
steak | +0.996 |
lung | +0.976 |
Neg logit contributions | |
ples | -0.880 |
Jas | -0.807 |
ount | -0.807 |
paints | -0.771 |
Kay | -0.767 |
Token | red |
Token ID | 2266 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
tum | +0.685 |
thirst | +0.610 |
night | +0.598 |
steak | +0.526 |
lung | +0.517 |
Neg logit contributions | |
ples | -0.858 |
Jas | -0.789 |
paints | -0.785 |
yl | -0.784 |
ount | -0.776 |
Token | balloon |
Token ID | 21190 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
tum | +1.423 |
thirst | +1.289 |
night | +1.231 |
drowned | +1.084 |
steak | +1.055 |
Neg logit contributions | |
ples | -1.968 |
paints | -1.854 |
yl | -1.844 |
violet | -1.803 |
blo | -1.803 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
ples | +1.208 |
Jas | +1.123 |
ount | +1.115 |
ydia | +1.072 |
yl | +1.065 |
Neg logit contributions | |
tum | -1.252 |
night | -1.093 |
thirst | -1.079 |
steak | -1.034 |
lung | -1.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
uch | +8.021 |
thirst | +7.595 |
footing | +7.440 |
tum | +7.368 |
drowned | +7.230 |
Neg logit contributions | |
Kay | -4.645 |
She | -4.271 |
ples | -4.247 |
mirror | -4.231 |
blo | -4.211 |
Token |
|
Token ID | 198 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
tum | +6.205 |
thirst | +6.157 |
night | +5.802 |
uch | +5.373 |
current | +5.347 |
Neg logit contributions | |
Kay | -3.328 |
Kay | -3.292 |
Jas | -3.274 |
yl | -3.179 |
ples | -3.162 |
Token | M |
Token ID | 44 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
tum | +6.097 |
thirst | +5.657 |
night | +5.353 |
uch | +5.068 |
elbow | +4.927 |
Neg logit contributions | |
ples | -4.993 |
Kay | -4.808 |
blo | -4.722 |
Kay | -4.613 |
ivia | -4.612 |
Token | ama |
Token ID | 1689 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
tum | +2.448 |
thirst | +2.146 |
night | +2.066 |
drowned | +1.907 |
recharge | +1.877 |
Neg logit contributions | |
ples | -3.529 |
yl | -3.448 |
Jas | -3.366 |
ount | -3.350 |
els | -3.334 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ples | +1.437 |
ount | +1.347 |
Jas | +1.309 |
paints | +1.267 |
ydia | +1.265 |
Neg logit contributions | |
tum | -1.490 |
night | -1.295 |
thirst | -1.284 |
steak | -1.227 |
lung | -1.182 |
Token | he |
Token ID | 339 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
tum | +0.383 |
thirst | +0.335 |
night | +0.333 |
steak | +0.300 |
lung | +0.296 |
Neg logit contributions | |
ples | -0.449 |
Jas | -0.427 |
ount | -0.420 |
paints | -0.413 |
yl | -0.407 |
Token | had |
Token ID | 550 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ples | +0.181 |
ount | +0.165 |
Jas | +0.165 |
paints | +0.159 |
yl | +0.159 |
Neg logit contributions | |
tum | -0.203 |
thirst | -0.179 |
night | -0.178 |
steak | -0.168 |
lung | -0.163 |
Token | a |
Token ID | 257 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
tum | +1.843 |
night | +1.705 |
thirst | +1.651 |
steak | +1.557 |
bye | +1.533 |
Neg logit contributions | |
ples | -1.772 |
Jas | -1.668 |
paints | -1.662 |
blo | -1.610 |
ount | -1.604 |
Token | cut |
Token ID | 2005 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
tum | +1.131 |
night | +1.042 |
thirst | +1.028 |
bye | +0.930 |
steak | +0.928 |
Neg logit contributions | |
ples | -1.128 |
paints | -1.057 |
Jas | -1.047 |
yl | -1.040 |
blo | -1.026 |
Token | on |
Token ID | 319 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
tum | +1.865 |
thirst | +1.692 |
night | +1.657 |
steak | +1.539 |
lung | +1.486 |
Neg logit contributions | |
ples | -1.531 |
Jas | -1.386 |
ount | -1.379 |
paints | -1.370 |
yl | -1.340 |
Token | his |
Token ID | 465 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
tum | +0.728 |
night | +0.629 |
thirst | +0.624 |
steak | +0.548 |
bye | +0.539 |
Neg logit contributions | |
ples | -1.033 |
Jas | -0.968 |
paints | -0.950 |
ount | -0.944 |
yl | -0.933 |
Token | cheek |
Token ID | 19353 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
night | +6.742 |
time | +6.238 |
bye | +6.232 |
thirst | +6.130 |
alas | +5.978 |
Neg logit contributions | |
paints | -6.302 |
mirror | -6.189 |
blo | -5.696 |
ples | -5.540 |
wardrobe | -5.517 |
Token | . |
Token ID | 13 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
tum | +1.921 |
thirst | +1.776 |
night | +1.707 |
steak | +1.643 |
current | +1.561 |
Neg logit contributions | |
ples | -1.363 |
Jas | -1.206 |
ount | -1.205 |
yl | -1.165 |
paints | -1.163 |
Token | It |
Token ID | 632 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
ples | +0.707 |
ount | +0.634 |
Jas | +0.632 |
yl | +0.613 |
paints | +0.608 |
Neg logit contributions | |
tum | -0.923 |
thirst | -0.809 |
night | -0.807 |
steak | -0.774 |
lung | -0.749 |
Token | was |
Token ID | 373 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
tum | +0.797 |
thirst | +0.717 |
night | +0.715 |
steak | +0.673 |
lung | +0.647 |
Neg logit contributions | |
ples | -0.645 |
Jas | -0.583 |
ount | -0.579 |
paints | -0.576 |
yl | -0.567 |
Token | red |
Token ID | 2266 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
tum | +0.334 |
night | +0.293 |
thirst | +0.289 |
steak | +0.266 |
lung | +0.260 |
Neg logit contributions | |
ples | -0.394 |
Jas | -0.365 |
ount | -0.362 |
paints | -0.354 |
blo | -0.351 |
Token | He |
Token ID | 679 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
tum | +2.747 |
thirst | +2.576 |
night | +2.529 |
uch | +2.404 |
drowned | +2.344 |
Neg logit contributions | |
ples | -2.473 |
Jas | -2.314 |
ount | -2.307 |
paints | -2.244 |
Kay | -2.241 |
Token | felt |
Token ID | 2936 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
tum | +2.628 |
night | +2.400 |
thirst | +2.399 |
steak | +2.250 |
time | +2.197 |
Neg logit contributions | |
ples | -1.394 |
Jas | -1.186 |
yl | -1.180 |
paints | -1.162 |
ount | -1.151 |
Token | a |
Token ID | 257 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
tum | +1.266 |
night | +1.141 |
thirst | +1.104 |
steak | +1.047 |
bye | +1.021 |
Neg logit contributions | |
ples | -1.149 |
ount | -1.057 |
Jas | -1.045 |
blo | -1.035 |
paints | -1.018 |
Token | tug |
Token ID | 27762 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
tum | +3.356 |
night | +3.151 |
thirst | +3.019 |
bye | +2.891 |
steak | +2.832 |
Neg logit contributions | |
ples | -3.477 |
blo | -3.242 |
yl | -3.180 |
mirror | -3.030 |
violet | -3.030 |
Token | on |
Token ID | 319 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
tum | +1.238 |
thirst | +1.095 |
night | +1.075 |
steak | +1.011 |
lung | +0.982 |
Neg logit contributions | |
ples | -0.962 |
Jas | -0.859 |
yl | -0.850 |
ount | -0.847 |
paints | -0.823 |
Token | his |
Token ID | 465 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
tum | +2.362 |
thirst | +2.112 |
night | +2.079 |
uch | +1.984 |
bye | +1.924 |
Neg logit contributions | |
ples | -2.900 |
paints | -2.681 |
Jas | -2.679 |
Kay | -2.670 |
blo | -2.614 |
Token | fishing |
Token ID | 12478 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
night | +6.021 |
thirst | +5.766 |
alas | +5.615 |
tum | +5.609 |
time | +5.594 |
Neg logit contributions | |
ples | -6.150 |
paints | -6.146 |
mirror | -5.884 |
blo | -5.871 |
prints | -5.809 |
Token | line |
Token ID | 1627 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
night | +4.196 |
tum | +4.054 |
thirst | +3.946 |
drowned | +3.530 |
uch | +3.400 |
Neg logit contributions | |
ples | -4.898 |
yl | -4.733 |
blo | -4.580 |
paints | -4.568 |
Jas | -4.481 |
Token | and |
Token ID | 290 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
tum | +0.779 |
thirst | +0.695 |
night | +0.682 |
steak | +0.640 |
lung | +0.625 |
Neg logit contributions | |
ples | -0.768 |
Jas | -0.710 |
ount | -0.708 |
yl | -0.682 |
paints | -0.681 |
Token | pulled |
Token ID | 5954 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
tum | +1.775 |
night | +1.604 |
thirst | +1.590 |
steak | +1.499 |
lung | +1.463 |
Neg logit contributions | |
ples | -1.220 |
Jas | -1.118 |
paints | -1.070 |
blo | -1.067 |
ount | -1.062 |
Token | up |
Token ID | 510 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
tum | +1.225 |
thirst | +1.086 |
night | +1.074 |
steak | +0.991 |
lung | +0.975 |
Neg logit contributions | |
ples | -1.057 |
Jas | -0.980 |
ount | -0.942 |
yl | -0.936 |
paints | -0.928 |
Token | to |
Token ID | 284 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
tum | +2.536 |
thirst | +2.345 |
night | +2.180 |
lung | +2.130 |
steak | +2.130 |
Neg logit contributions | |
ples | -2.504 |
Jas | -2.438 |
Kay | -2.334 |
written | -2.314 |
yl | -2.305 |
Token | jump |
Token ID | 4391 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
tum | +1.107 |
night | +0.973 |
thirst | +0.970 |
steak | +0.918 |
lung | +0.868 |
Neg logit contributions | |
ples | -1.113 |
Jas | -1.070 |
ount | -1.036 |
Kay | -1.016 |
paints | -1.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
tum | +0.822 |
thirst | +0.729 |
night | +0.715 |
steak | +0.682 |
lung | +0.665 |
Neg logit contributions | |
ples | -0.698 |
Jas | -0.653 |
ount | -0.649 |
yl | -0.622 |
paints | -0.617 |
Token | But |
Token ID | 887 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
tum | +4.103 |
thirst | +3.879 |
night | +3.764 |
uch | +3.718 |
lung | +3.705 |
Neg logit contributions | |
Kay | -4.132 |
ount | -4.120 |
ples | -4.059 |
Jas | -3.974 |
violet | -3.754 |
Token | then |
Token ID | 788 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
tum | +5.547 |
night | +5.173 |
thirst | +4.760 |
ages | +4.616 |
lung | +4.545 |
Neg logit contributions | |
Kay | -4.779 |
blo | -4.733 |
yl | -4.673 |
Jas | -4.373 |
ples | -4.310 |
Token | , |
Token ID | 11 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
tum | +4.086 |
thirst | +3.778 |
night | +3.658 |
hind | +3.342 |
edly | +3.325 |
Neg logit contributions | |
yl | -2.957 |
Kay | -2.941 |
ples | -2.922 |
blo | -2.857 |
Jas | -2.837 |
Token | Bob |
Token ID | 5811 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
tum | +7.876 |
night | +7.361 |
thirst | +7.156 |
hind | +6.934 |
ages | +6.823 |
Neg logit contributions | |
Kay | -5.226 |
blo | -4.575 |
yl | -4.390 |
Jas | -4.365 |
grown | -4.363 |
Token | o |
Token ID | 78 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
tum | +0.664 |
thirst | +0.590 |
night | +0.585 |
steak | +0.553 |
lung | +0.527 |
Neg logit contributions | |
ples | -0.636 |
Jas | -0.583 |
ount | -0.578 |
yl | -0.573 |
paints | -0.555 |
Token | fell |
Token ID | 3214 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
tum | +2.077 |
thirst | +1.910 |
night | +1.898 |
steak | +1.820 |
lung | +1.731 |
Neg logit contributions | |
ples | -1.435 |
Jas | -1.311 |
yl | -1.284 |
ount | -1.248 |
paints | -1.237 |
Token | into |
Token ID | 656 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
tum | +2.287 |
thirst | +2.101 |
night | +2.001 |
steak | +1.970 |
lung | +1.841 |
Neg logit contributions | |
ples | -1.903 |
Jas | -1.790 |
blo | -1.740 |
ount | -1.718 |
paints | -1.698 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
tum | +2.347 |
night | +2.215 |
thirst | +2.100 |
bye | +2.041 |
uch | +1.944 |
Neg logit contributions | |
Jas | -1.754 |
ples | -1.732 |
yl | -1.647 |
Kay | -1.629 |
paints | -1.581 |
Token | away |
Token ID | 1497 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
tum | +1.073 |
thirst | +0.936 |
night | +0.910 |
steak | +0.872 |
lung | +0.862 |
Neg logit contributions | |
ples | -1.138 |
Jas | -1.065 |
ount | -1.048 |
Kay | -1.024 |
yl | -1.022 |
Token | . |
Token ID | 13 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
tum | +1.061 |
night | +0.939 |
thirst | +0.937 |
steak | +0.891 |
lung | +0.859 |
Neg logit contributions | |
ples | -1.007 |
Jas | -0.920 |
ount | -0.918 |
blo | -0.910 |
yl | -0.903 |
Token | The |
Token ID | 383 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
tum | +0.999 |
thirst | +0.879 |
night | +0.854 |
steak | +0.805 |
lung | +0.784 |
Neg logit contributions | |
ples | -1.322 |
Jas | -1.249 |
ount | -1.242 |
Kay | -1.202 |
paints | -1.183 |
Token | bunny |
Token ID | 44915 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
tum | +2.065 |
night | +1.840 |
thirst | +1.815 |
steak | +1.608 |
time | +1.602 |
Neg logit contributions | |
ples | -2.045 |
blo | -1.926 |
paints | -1.880 |
violet | -1.862 |
yl | -1.844 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
tum | +2.971 |
night | +2.684 |
thirst | +2.651 |
steak | +2.604 |
lung | +2.436 |
Neg logit contributions | |
ples | -2.252 |
blo | -2.075 |
yl | -2.001 |
paints | -1.953 |
Jas | -1.950 |
Token | his |
Token ID | 465 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
tum | +0.659 |
night | +0.580 |
thirst | +0.576 |
steak | +0.530 |
lung | +0.525 |
Neg logit contributions | |
ples | -0.566 |
Jas | -0.524 |
ount | -0.508 |
blo | -0.506 |
yl | -0.504 |
Token | steak |
Token ID | 26320 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
tum | +6.168 |
thirst | +5.633 |
drowned | +5.602 |
night | +5.559 |
edly | +5.431 |
Neg logit contributions | |
paints | -5.997 |
blo | -5.988 |
ples | -5.776 |
violet | -5.736 |
freshly | -5.613 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
tum | +4.373 |
night | +3.967 |
thirst | +3.794 |
bye | +3.646 |
drowned | +3.575 |
Neg logit contributions | |
blo | -3.447 |
ples | -3.372 |
written | -3.007 |
paints | -2.961 |
yl | -2.946 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
tum | +2.058 |
night | +1.833 |
thirst | +1.810 |
steak | +1.727 |
lung | +1.669 |
Neg logit contributions | |
ples | -1.707 |
blo | -1.592 |
Jas | -1.580 |
Kay | -1.528 |
paints | -1.503 |
Token | huge |
Token ID | 3236 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
tum | +2.111 |
night | +1.898 |
thirst | +1.880 |
time | +1.657 |
steak | +1.656 |
Neg logit contributions | |
ples | -1.902 |
blo | -1.820 |
paints | -1.767 |
violet | -1.746 |
yl | -1.707 |
Token | tree |
Token ID | 5509 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
tum | +1.696 |
thirst | +1.528 |
night | +1.493 |
steak | +1.328 |
drowned | +1.321 |
Neg logit contributions | |
ples | -1.824 |
blo | -1.680 |
paints | -1.645 |
violet | -1.625 |
yl | -1.611 |
Token | ground |
Token ID | 2323 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
tum | +5.165 |
thirst | +4.997 |
night | +4.967 |
time | +4.497 |
drowned | +4.357 |
Neg logit contributions | |
ples | -3.424 |
blo | -3.415 |
paints | -3.242 |
violet | -3.211 |
mirror | -3.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
tum | +2.604 |
thirst | +2.355 |
night | +2.342 |
steak | +2.213 |
lung | +2.188 |
Neg logit contributions | |
ples | -1.939 |
blo | -1.796 |
paints | -1.746 |
Jas | -1.741 |
ount | -1.702 |
Token | started |
Token ID | 2067 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
tum | +5.122 |
thirst | +4.656 |
night | +4.439 |
time | +4.427 |
team | +4.373 |
Neg logit contributions | |
paints | -3.476 |
blo | -3.414 |
ples | -3.393 |
written | -3.210 |
mirror | -3.189 |
Token | to |
Token ID | 284 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
tum | +1.887 |
thirst | +1.704 |
night | +1.646 |
steak | +1.524 |
bye | +1.500 |
Neg logit contributions | |
ples | -1.825 |
blo | -1.700 |
paints | -1.689 |
Jas | -1.659 |
violet | -1.610 |
Token | stretch |
Token ID | 7539 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
tum | +3.153 |
night | +2.778 |
thirst | +2.770 |
bye | +2.518 |
steak | +2.508 |
Neg logit contributions | |
ples | -3.102 |
blo | -3.031 |
paints | -2.992 |
violet | -2.849 |
mirror | -2.842 |
Token | his |
Token ID | 465 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
tum | +3.361 |
night | +3.013 |
thirst | +3.008 |
steak | +2.791 |
uch | +2.780 |
Neg logit contributions | |
ples | -2.432 |
Jas | -2.355 |
blo | -2.249 |
paints | -2.170 |
Kay | -2.168 |
Token | muscles |
Token ID | 12749 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
night | +6.262 |
thirst | +5.895 |
bye | +5.884 |
tum | +5.853 |
unfortunately | +5.750 |
Neg logit contributions | |
blo | -6.233 |
paints | -6.087 |
mirror | -5.843 |
ples | -5.747 |
ey | -5.662 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
tum | +2.577 |
thirst | +2.339 |
night | +2.305 |
steak | +2.166 |
lung | +2.102 |
Neg logit contributions | |
ples | -1.723 |
blo | -1.580 |
ount | -1.523 |
paints | -1.522 |
Jas | -1.495 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
tum | +2.565 |
thirst | +2.407 |
night | +2.336 |
steak | +2.205 |
uch | +2.175 |
Neg logit contributions | |
ples | -2.855 |
Jas | -2.704 |
ount | -2.660 |
paints | -2.593 |
violet | -2.577 |
Token | he |
Token ID | 339 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
tum | +2.450 |
thirst | +2.314 |
night | +2.254 |
steak | +2.039 |
edly | +2.019 |
Neg logit contributions | |
ples | -2.141 |
Jas | -2.058 |
yl | -2.027 |
Kay | -1.974 |
paints | -1.964 |
Token | heard |
Token ID | 2982 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
tum | +3.304 |
night | +3.145 |
thirst | +3.126 |
steak | +2.969 |
bye | +2.900 |
Neg logit contributions | |
ples | -1.738 |
drawn | -1.505 |
yl | -1.499 |
blo | -1.497 |
paints | -1.496 |
Token | ac |
Token ID | 936 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
tum | +3.200 |
night | +3.040 |
thirst | +2.982 |
bye | +2.787 |
steak | +2.752 |
Neg logit contributions | |
ples | -2.843 |
blo | -2.561 |
paints | -2.440 |
ount | -2.404 |
drawn | -2.396 |
Token | he |
Token ID | 258 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
tum | +2.149 |
thirst | +1.907 |
night | +1.907 |
steak | +1.785 |
lung | +1.724 |
Neg logit contributions | |
ples | -1.386 |
ount | -1.237 |
yl | -1.218 |
Jas | -1.189 |
paints | -1.184 |
Token | . |
Token ID | 13 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
tum | +3.768 |
night | +3.496 |
thirst | +3.373 |
bye | +3.232 |
steak | +3.143 |
Neg logit contributions | |
ples | -2.360 |
blo | -2.139 |
Jas | -2.134 |
yl | -2.062 |
ount | -2.029 |
Token | He |
Token ID | 679 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
tum | +1.101 |
thirst | +0.981 |
night | +0.976 |
steak | +0.888 |
lung | +0.847 |
Neg logit contributions | |
ples | -1.467 |
Jas | -1.416 |
ount | -1.393 |
paints | -1.347 |
Kay | -1.346 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
tum | +2.567 |
night | +2.361 |
thirst | +2.326 |
steak | +2.245 |
bye | +2.179 |
Neg logit contributions | |
ples | -2.003 |
paints | -1.837 |
drawn | -1.787 |
Jas | -1.786 |
blo | -1.785 |
Token | his |
Token ID | 465 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
tum | +1.899 |
night | +1.776 |
thirst | +1.680 |
bye | +1.634 |
steak | +1.616 |
Neg logit contributions | |
ples | -1.937 |
blo | -1.803 |
ount | -1.781 |
paints | -1.764 |
drawn | -1.749 |
Token | head |
Token ID | 1182 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
night | +5.346 |
His | +5.334 |
bye | +5.185 |
steak | +4.905 |
edly | +4.694 |
Neg logit contributions | |
blo | -6.737 |
paints | -6.593 |
mirror | -6.447 |
makeup | -6.160 |
ples | -5.906 |
Token | spin |
Token ID | 7906 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
tum | +1.513 |
night | +1.366 |
thirst | +1.360 |
steak | +1.279 |
bye | +1.197 |
Neg logit contributions | |
ples | -1.428 |
ount | -1.283 |
blo | -1.260 |
Jas | -1.244 |
paints | -1.241 |
Token | . |
Token ID | 13 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
tum | +1.871 |
thirst | +1.686 |
night | +1.630 |
steak | +1.587 |
lung | +1.532 |
Neg logit contributions | |
ples | -1.460 |
ount | -1.325 |
Jas | -1.314 |
paints | -1.267 |
yl | -1.255 |
Token | He |
Token ID | 679 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
tum | +0.988 |
thirst | +0.878 |
night | +0.867 |
steak | +0.795 |
lung | +0.760 |
Neg logit contributions | |
ples | -1.347 |
Jas | -1.299 |
ount | -1.279 |
paints | -1.238 |
Kay | -1.234 |
Token | felt |
Token ID | 2936 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
tum | +2.309 |
night | +2.112 |
thirst | +2.062 |
steak | +2.024 |
bye | +1.932 |
Neg logit contributions | |
ples | -1.955 |
paints | -1.787 |
Jas | -1.764 |
blo | -1.739 |
drawn | -1.730 |
Token | my |
Token ID | 1820 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
tum | +1.030 |
thirst | +0.953 |
night | +0.941 |
steak | +0.910 |
lung | +0.885 |
Neg logit contributions | |
ples | -0.298 |
Jas | -0.243 |
ount | -0.231 |
paints | -0.230 |
yl | -0.225 |
Token | fell |
Token ID | 3214 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
tum | +4.458 |
night | +4.330 |
thirst | +4.329 |
bye | +4.070 |
steak | +3.958 |
Neg logit contributions | |
paints | -3.130 |
ples | -3.129 |
drawn | -2.922 |
written | -2.881 |
yl | -2.839 |
Token | down |
Token ID | 866 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
tum | +2.535 |
thirst | +2.363 |
night | +2.238 |
steak | +2.182 |
lung | +2.051 |
Neg logit contributions | |
ples | -1.936 |
Jas | -1.801 |
blo | -1.781 |
paints | -1.741 |
yl | -1.735 |
Token | and |
Token ID | 290 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
tum | +1.621 |
thirst | +1.458 |
night | +1.405 |
steak | +1.321 |
lung | +1.294 |
Neg logit contributions | |
ples | -1.377 |
Jas | -1.323 |
yl | -1.300 |
blo | -1.275 |
ount | -1.271 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
tum | +2.889 |
night | +2.710 |
thirst | +2.699 |
steak | +2.558 |
bye | +2.485 |
Neg logit contributions | |
ples | -2.825 |
Jas | -2.718 |
paints | -2.705 |
blo | -2.704 |
drawn | -2.663 |
Token | his |
Token ID | 465 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
tum | +2.482 |
night | +2.172 |
thirst | +2.085 |
steak | +1.902 |
uch | +1.893 |
Neg logit contributions | |
ples | -3.619 |
Jas | -3.613 |
Kay | -3.405 |
yl | -3.355 |
grown | -3.353 |
Token | knee |
Token ID | 10329 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
night | +5.278 |
bye | +4.741 |
steak | +4.696 |
thirst | +4.632 |
tum | +4.619 |
Neg logit contributions | |
mirror | -6.715 |
blo | -6.418 |
paints | -6.409 |
makeup | -6.334 |
ples | -6.228 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
tum | +2.938 |
thirst | +2.794 |
night | +2.733 |
steak | +2.656 |
lung | +2.468 |
Neg logit contributions | |
ples | -1.826 |
blo | -1.573 |
ount | -1.546 |
drawn | -1.544 |
written | -1.542 |
Token | |
Token ID | 220 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
tum | +1.951 |
thirst | +1.855 |
night | +1.853 |
steak | +1.716 |
lung | +1.656 |
Neg logit contributions | |
ples | -1.804 |
Jas | -1.775 |
Kay | -1.707 |
ount | -1.703 |
yl | -1.651 |
Token |
|
Token ID | 198 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
tum | +1.479 |
thirst | +1.359 |
night | +1.348 |
steak | +1.253 |
lung | +1.216 |
Neg logit contributions | |
ples | -1.381 |
ount | -1.333 |
Jas | -1.332 |
yl | -1.255 |
paints | -1.247 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
tum | +1.075 |
thirst | +0.978 |
night | +0.962 |
steak | +0.896 |
lung | +0.872 |
Neg logit contributions | |
ples | -1.046 |
Jas | -1.008 |
ount | -0.985 |
yl | -0.977 |
Kay | -0.953 |
Token | and |
Token ID | 290 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
tum | +0.422 |
thirst | +0.379 |
night | +0.372 |
steak | +0.353 |
lung | +0.343 |
Neg logit contributions | |
ples | -0.361 |
ount | -0.331 |
Jas | -0.329 |
paints | -0.319 |
yl | -0.319 |
Token | angry |
Token ID | 7954 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
ples | +0.752 |
ount | +0.679 |
Jas | +0.677 |
yl | +0.655 |
paints | +0.646 |
Neg logit contributions | |
tum | -0.961 |
thirst | -0.853 |
night | -0.849 |
steak | -0.800 |
lung | -0.780 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ples | +1.630 |
Jas | +1.508 |
ount | +1.503 |
paints | +1.461 |
yl | +1.455 |
Neg logit contributions | |
tum | -1.572 |
night | -1.351 |
thirst | -1.332 |
steak | -1.263 |
lung | -1.228 |
Token | She |
Token ID | 1375 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
ples | +1.904 |
ount | +1.654 |
yl | +1.608 |
Jas | +1.528 |
ptions | +1.519 |
Neg logit contributions | |
tum | -3.865 |
night | -3.407 |
thirst | -3.377 |
steak | -3.199 |
leg | -3.180 |
Token | did |
Token ID | 750 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
ples | +1.222 |
ount | +1.130 |
Jas | +1.112 |
yl | +1.073 |
paints | +1.066 |
Neg logit contributions | |
tum | -1.314 |
thirst | -1.146 |
night | -1.143 |
steak | -1.073 |
lung | -1.045 |
Token | not |
Token ID | 407 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ples | +1.449 |
ount | +1.355 |
Jas | +1.350 |
paints | +1.313 |
yl | +1.311 |
Neg logit contributions | |
tum | -0.650 |
thirst | -0.518 |
night | -0.513 |
steak | -0.466 |
lung | -0.435 |
Token | like |
Token ID | 588 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
ples | +4.275 |
Jas | +3.897 |
paints | +3.815 |
ount | +3.787 |
els | +3.739 |
Neg logit contributions | |
tum | -4.054 |
night | -3.665 |
thirst | -3.518 |
steak | -3.362 |
leg | -3.253 |
Token | the |
Token ID | 262 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ples | +1.386 |
ount | +1.273 |
Jas | +1.251 |
yl | +1.217 |
ydia | +1.199 |
Neg logit contributions | |
tum | -1.392 |
thirst | -1.193 |
night | -1.189 |
steak | -1.149 |
lung | -1.108 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
ples | +0.903 |
ount | +0.833 |
Jas | +0.829 |
yl | +0.799 |
paints | +0.792 |
Neg logit contributions | |
tum | -0.804 |
thirst | -0.688 |
night | -0.684 |
steak | -0.650 |
lung | -0.632 |
Token | . |
Token ID | 13 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
ples | +0.460 |
Jas | +0.423 |
ount | +0.422 |
yl | +0.407 |
paints | +0.407 |
Neg logit contributions | |
tum | -0.477 |
thirst | -0.417 |
night | -0.414 |
steak | -0.391 |
lung | -0.380 |
Token | She |
Token ID | 1375 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
ples | +0.877 |
ount | +0.746 |
Jas | +0.727 |
yl | +0.723 |
paints | +0.680 |
Neg logit contributions | |
tum | -2.135 |
night | -1.916 |
thirst | -1.916 |
steak | -1.845 |
lung | -1.819 |
Token | She |
Token ID | 1375 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
ples | +1.644 |
ount | +1.433 |
ptions | +1.395 |
yl | +1.377 |
Jas | +1.363 |
Neg logit contributions | |
tum | -3.388 |
night | -3.002 |
thirst | -2.900 |
steak | -2.873 |
lung | -2.815 |
Token | goes |
Token ID | 2925 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ples | +4.905 |
Jas | +4.581 |
ptions | +4.402 |
yl | +4.376 |
ount | +4.371 |
Neg logit contributions | |
tum | -5.959 |
night | -5.238 |
steak | -5.049 |
thirst | -5.012 |
lung | -4.903 |
Token | to |
Token ID | 284 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ples | +4.972 |
Jas | +4.421 |
ount | +4.379 |
od | +4.356 |
violet | +4.337 |
Neg logit contributions | |
tum | -2.283 |
night | -1.905 |
thirst | -1.772 |
steak | -1.630 |
leg | -1.607 |
Token | them |
Token ID | 606 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
ples | +0.552 |
ount | +0.502 |
Jas | +0.498 |
yl | +0.481 |
paints | +0.480 |
Neg logit contributions | |
tum | -0.648 |
thirst | -0.571 |
night | -0.569 |
steak | -0.542 |
lung | -0.525 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ples | +0.972 |
Jas | +0.895 |
ount | +0.891 |
yl | +0.864 |
paints | +0.857 |
Neg logit contributions | |
tum | -0.933 |
thirst | -0.807 |
night | -0.805 |
steak | -0.761 |
lung | -0.739 |
Token | She |
Token ID | 1375 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ples | +1.326 |
ount | +1.152 |
yl | +1.116 |
Jas | +1.109 |
ptions | +1.087 |
Neg logit contributions | |
tum | -2.732 |
night | -2.436 |
thirst | -2.370 |
steak | -2.335 |
lung | -2.275 |
Token | says |
Token ID | 1139 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ples | +4.139 |
Jas | +3.718 |
ount | +3.650 |
yl | +3.558 |
ptions | +3.552 |
Neg logit contributions | |
tum | -5.454 |
night | -4.674 |
steak | -4.635 |
thirst | -4.567 |
lung | -4.490 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ples | +1.250 |
ount | +1.158 |
Jas | +1.148 |
paints | +1.111 |
ydia | +1.110 |
Neg logit contributions | |
tum | -0.889 |
night | -0.734 |
thirst | -0.731 |
steak | -0.690 |
lung | -0.656 |
Token | " |
Token ID | 366 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ples | +1.779 |
ount | +1.631 |
Jas | +1.612 |
yl | +1.555 |
ydia | +1.552 |
Neg logit contributions | |
tum | -2.167 |
thirst | -1.837 |
night | -1.822 |
steak | -1.771 |
lung | -1.730 |
Token | Hi |
Token ID | 17250 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
ples | +1.457 |
ount | +1.294 |
Jas | +1.292 |
paints | +1.215 |
yl | +1.213 |
Neg logit contributions | |
tum | -2.354 |
night | -2.152 |
thirst | -2.095 |
steak | -2.083 |
lung | -2.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ples | +1.477 |
ount | +1.374 |
Jas | +1.355 |
ydia | +1.323 |
paints | +1.319 |
Neg logit contributions | |
tum | -1.038 |
night | -0.868 |
thirst | -0.862 |
steak | -0.822 |
lung | -0.776 |
Token | a |
Token ID | 257 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
tum | +0.025 |
thirst | +0.022 |
night | +0.022 |
steak | +0.020 |
lung | +0.019 |
Neg logit contributions | |
ples | -0.031 |
Jas | -0.029 |
ount | -0.029 |
paints | -0.028 |
yl | -0.028 |
Token | big |
Token ID | 1263 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ples | +2.487 |
ount | +2.340 |
Jas | +2.266 |
ydia | +2.189 |
ptions | +2.127 |
Neg logit contributions | |
tum | -2.274 |
steak | -1.910 |
thirst | -1.870 |
lung | -1.821 |
night | -1.817 |
Token | bush |
Token ID | 24484 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ples | +2.482 |
ount | +2.389 |
Jas | +2.305 |
ydia | +2.245 |
ptions | +2.189 |
Neg logit contributions | |
tum | -2.008 |
steak | -1.669 |
thirst | -1.654 |
night | -1.618 |
lung | -1.571 |
Token | with |
Token ID | 351 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ples | +3.532 |
Jas | +3.286 |
ount | +3.270 |
ydia | +3.224 |
ptions | +3.174 |
Neg logit contributions | |
tum | -2.522 |
steak | -2.022 |
thirst | -2.020 |
night | -2.016 |
time | -1.872 |
Token | red |
Token ID | 2266 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
ples | +2.983 |
ount | +2.843 |
Jas | +2.773 |
yl | +2.712 |
ydia | +2.711 |
Neg logit contributions | |
tum | -2.118 |
thirst | -1.740 |
steak | -1.657 |
night | -1.608 |
lung | -1.515 |
Token | flowers |
Token ID | 12734 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
ples | +1.118 |
ount | +1.043 |
Jas | +1.043 |
yl | +0.998 |
ydia | +0.996 |
Neg logit contributions | |
tum | -1.070 |
thirst | -0.915 |
night | -0.908 |
steak | -0.866 |
lung | -0.831 |
Token | . |
Token ID | 13 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
ples | +5.069 |
Jas | +4.982 |
ydia | +4.899 |
ount | +4.828 |
ptions | +4.780 |
Neg logit contributions | |
tum | -3.257 |
thirst | -2.558 |
steak | -2.532 |
dinner | -2.415 |
lung | -2.395 |
Token | They |
Token ID | 1119 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
tum | +0.680 |
thirst | +0.613 |
night | +0.610 |
steak | +0.564 |
lung | +0.561 |
Neg logit contributions | |
ples | -0.607 |
Jas | -0.564 |
ount | -0.559 |
paints | -0.543 |
Kay | -0.532 |
Token | wanted |
Token ID | 2227 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
ples | +1.999 |
ount | +1.848 |
Jas | +1.734 |
yl | +1.728 |
ydia | +1.715 |
Neg logit contributions | |
tum | -2.416 |
thirst | -2.100 |
night | -2.017 |
steak | -1.966 |
lung | -1.893 |
Token | to |
Token ID | 284 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
ples | +1.666 |
ount | +1.560 |
Jas | +1.541 |
ydia | +1.494 |
yl | +1.488 |
Neg logit contributions | |
tum | -1.017 |
thirst | -0.822 |
night | -0.809 |
steak | -0.778 |
lung | -0.724 |
Token | cut |
Token ID | 2005 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
ples | +1.629 |
ount | +1.485 |
Jas | +1.459 |
yl | +1.420 |
ydia | +1.412 |
Neg logit contributions | |
tum | -1.625 |
thirst | -1.386 |
night | -1.346 |
steak | -1.276 |
lung | -1.243 |
Token |
|
Token ID | 198 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
ples | +1.136 |
ount | +1.045 |
Jas | +1.041 |
paints | +1.019 |
yl | +1.008 |
Neg logit contributions | |
tum | -0.829 |
night | -0.691 |
thirst | -0.690 |
steak | -0.644 |
lung | -0.616 |
Token | So |
Token ID | 2396 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ples | +1.737 |
ount | +1.609 |
Jas | +1.607 |
paints | +1.558 |
yl | +1.554 |
Neg logit contributions | |
tum | -1.351 |
thirst | -1.146 |
night | -1.144 |
steak | -1.049 |
time | -1.023 |
Token | , |
Token ID | 11 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
tum | +0.523 |
thirst | +0.462 |
night | +0.453 |
steak | +0.436 |
lung | +0.426 |
Neg logit contributions | |
ples | -0.570 |
Jas | -0.536 |
yl | -0.521 |
ount | -0.518 |
paints | -0.514 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ples | +0.051 |
Jas | +0.046 |
ount | +0.046 |
paints | +0.044 |
yl | +0.044 |
Neg logit contributions | |
tum | -0.074 |
thirst | -0.066 |
night | -0.066 |
steak | -0.063 |
lung | -0.061 |
Token | took |
Token ID | 1718 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
tum | +0.428 |
thirst | +0.379 |
night | +0.369 |
steak | +0.353 |
lung | +0.341 |
Neg logit contributions | |
ples | -0.403 |
Jas | -0.370 |
ount | -0.365 |
paints | -0.362 |
yl | -0.358 |
Token | the |
Token ID | 262 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ples | +0.669 |
ount | +0.617 |
Jas | +0.613 |
yl | +0.591 |
paints | +0.589 |
Neg logit contributions | |
tum | -0.666 |
thirst | -0.580 |
night | -0.580 |
steak | -0.545 |
lung | -0.527 |
Token | purse |
Token ID | 27517 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
ples | +4.062 |
ount | +3.619 |
Jas | +3.536 |
od | +3.313 |
ptions | +3.201 |
Neg logit contributions | |
tum | -5.343 |
thirst | -4.284 |
night | -4.216 |
leg | -4.210 |
steak | -4.112 |
Token | and |
Token ID | 290 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
tum | +1.653 |
thirst | +1.519 |
night | +1.440 |
steak | +1.363 |
lung | +1.349 |
Neg logit contributions | |
ples | -1.466 |
ount | -1.392 |
paints | -1.385 |
yl | -1.380 |
Jas | -1.380 |
Token | put |
Token ID | 1234 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ples | +0.153 |
Jas | +0.141 |
ount | +0.140 |
paints | +0.136 |
yl | +0.135 |
Neg logit contributions | |
tum | -0.174 |
thirst | -0.154 |
night | -0.153 |
steak | -0.145 |
lung | -0.141 |
Token | her |
Token ID | 607 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
ples | +3.571 |
ount | +3.411 |
Jas | +3.279 |
ydia | +3.164 |
ptions | +3.158 |
Neg logit contributions | |
tum | -2.761 |
thirst | -2.334 |
night | -2.288 |
steak | -2.229 |
dinner | -2.160 |
Token | favorite |
Token ID | 4004 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ples | +1.486 |
ount | +1.366 |
Jas | +1.365 |
ydia | +1.285 |
yl | +1.273 |
Neg logit contributions | |
tum | -1.682 |
thirst | -1.462 |
night | -1.414 |
steak | -1.352 |
lung | -1.326 |
Token | find |
Token ID | 1064 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ples | +1.046 |
ount | +0.950 |
Jas | +0.938 |
paints | +0.909 |
yl | +0.893 |
Neg logit contributions | |
tum | -1.282 |
thirst | -1.129 |
night | -1.110 |
steak | -1.060 |
lung | -1.046 |
Token | anything |
Token ID | 1997 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ples | +3.929 |
ount | +3.756 |
Jas | +3.673 |
typing | +3.519 |
ydia | +3.508 |
Neg logit contributions | |
tum | -2.736 |
thirst | -2.306 |
night | -2.163 |
steak | -2.076 |
lung | -2.036 |
Token | . |
Token ID | 13 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
ples | +2.783 |
Jas | +2.592 |
ount | +2.557 |
ydia | +2.471 |
ptions | +2.455 |
Neg logit contributions | |
tum | -2.341 |
thirst | -1.955 |
night | -1.922 |
steak | -1.883 |
dinner | -1.794 |
Token | Then |
Token ID | 3244 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
ples | +0.105 |
Jas | +0.094 |
ount | +0.094 |
paints | +0.090 |
yl | +0.089 |
Neg logit contributions | |
tum | -0.172 |
thirst | -0.155 |
night | -0.154 |
steak | -0.147 |
lung | -0.144 |
Token | she |
Token ID | 673 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
tum | +0.873 |
thirst | +0.784 |
night | +0.777 |
steak | +0.745 |
lung | +0.729 |
Neg logit contributions | |
ples | -0.658 |
Jas | -0.611 |
yl | -0.592 |
Kay | -0.586 |
blo | -0.582 |
Token | went |
Token ID | 1816 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ples | +0.170 |
Jas | +0.151 |
ount | +0.151 |
yl | +0.144 |
paints | +0.144 |
Neg logit contributions | |
tum | -0.309 |
thirst | -0.279 |
night | -0.278 |
steak | -0.266 |
lung | -0.260 |
Token | outside |
Token ID | 2354 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
ples | +6.209 |
ount | +5.695 |
od | +5.436 |
Jas | +5.427 |
ptions | +5.389 |
Neg logit contributions | |
tum | -2.758 |
night | -2.251 |
dinner | -2.114 |
thirst | -2.062 |
steak | -2.014 |
Token | and |
Token ID | 290 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ples | +0.156 |
Jas | +0.146 |
ount | +0.145 |
yl | +0.141 |
paints | +0.141 |
Neg logit contributions | |
tum | -0.128 |
thirst | -0.110 |
night | -0.109 |
steak | -0.102 |
lung | -0.099 |
Token | searched |
Token ID | 16499 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ples | +1.319 |
ount | +1.186 |
Jas | +1.127 |
ydia | +1.080 |
yl | +1.079 |
Neg logit contributions | |
tum | -2.123 |
thirst | -1.911 |
night | -1.901 |
steak | -1.762 |
lung | -1.736 |
Token | between |
Token ID | 1022 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ples | +2.588 |
ount | +2.450 |
Jas | +2.360 |
ydia | +2.355 |
yl | +2.332 |
Neg logit contributions | |
tum | -1.728 |
thirst | -1.466 |
night | -1.439 |
steak | -1.329 |
dinner | -1.297 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ples | +2.976 |
ount | +2.863 |
violet | +2.583 |
yl | +2.574 |
ydia | +2.542 |
Neg logit contributions | |
tum | -3.175 |
thirst | -2.764 |
steak | -2.635 |
dinner | -2.610 |
night | -2.585 |
Token | and |
Token ID | 290 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
tum | +1.417 |
thirst | +1.270 |
night | +1.228 |
lung | +1.155 |
steak | +1.144 |
Neg logit contributions | |
ples | -1.288 |
Jas | -1.189 |
ount | -1.179 |
paints | -1.176 |
blo | -1.152 |
Token | kisses |
Token ID | 36544 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ples | +0.673 |
ount | +0.601 |
Jas | +0.593 |
yl | +0.575 |
ydia | +0.554 |
Neg logit contributions | |
tum | -1.147 |
thirst | -1.028 |
night | -1.028 |
steak | -0.991 |
lung | -0.960 |
Token | them |
Token ID | 606 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
tum | +0.907 |
thirst | +0.835 |
night | +0.815 |
steak | +0.784 |
lung | +0.777 |
Neg logit contributions | |
ples | -0.386 |
Jas | -0.342 |
ount | -0.331 |
paints | -0.316 |
yl | -0.314 |
Token | . |
Token ID | 13 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
tum | +3.388 |
thirst | +3.064 |
night | +2.914 |
lung | +2.877 |
current | +2.869 |
Neg logit contributions | |
ples | -2.025 |
paints | -1.834 |
ount | -1.830 |
blo | -1.826 |
Jas | -1.796 |
Token | She |
Token ID | 1375 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ples | +1.191 |
ount | +1.057 |
yl | +1.045 |
Jas | +1.026 |
ptions | +0.988 |
Neg logit contributions | |
tum | -1.980 |
night | -1.736 |
thirst | -1.734 |
steak | -1.675 |
lung | -1.612 |
Token | is |
Token ID | 318 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ples | +2.211 |
ount | +1.979 |
Jas | +1.976 |
ptions | +1.917 |
yl | +1.910 |
Neg logit contributions | |
tum | -3.147 |
night | -2.775 |
thirst | -2.747 |
steak | -2.717 |
lung | -2.598 |
Token | proud |
Token ID | 6613 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
ples | +2.397 |
ount | +2.188 |
Jas | +2.138 |
yl | +2.116 |
paints | +2.098 |
Neg logit contributions | |
tum | -2.009 |
thirst | -1.745 |
night | -1.644 |
steak | -1.636 |
lung | -1.544 |
Token | of |
Token ID | 286 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
ples | +0.432 |
ount | +0.396 |
Jas | +0.395 |
yl | +0.382 |
paints | +0.381 |
Neg logit contributions | |
tum | -0.457 |
thirst | -0.400 |
night | -0.398 |
steak | -0.376 |
lung | -0.365 |
Token | them |
Token ID | 606 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
ples | +1.062 |
ount | +0.945 |
Jas | +0.918 |
paints | +0.892 |
yl | +0.886 |
Neg logit contributions | |
tum | -1.711 |
thirst | -1.553 |
night | -1.532 |
steak | -1.488 |
lung | -1.437 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
tum | +1.243 |
thirst | +1.113 |
night | +1.098 |
steak | +1.027 |
lung | +1.017 |
Neg logit contributions | |
ples | -0.925 |
ount | -0.846 |
Jas | -0.834 |
paints | -0.817 |
blo | -0.814 |
Token |
|
Token ID | 198 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
ples | +2.412 |
yl | +2.180 |
ount | +2.171 |
ptions | +2.111 |
Jas | +2.101 |
Neg logit contributions | |
tum | -2.597 |
night | -2.184 |
thirst | -2.170 |
steak | -2.108 |
lung | -1.993 |
Token | In |
Token ID | 818 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ples | +0.890 |
ount | +0.832 |
Jas | +0.830 |
paints | +0.810 |
yl | +0.808 |
Neg logit contributions | |
tum | -0.506 |
thirst | -0.417 |
night | -0.415 |
steak | -0.381 |
lung | -0.361 |
Token | the |
Token ID | 262 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
ples | +2.078 |
ount | +1.985 |
Jas | +1.820 |
yl | +1.782 |
paints | +1.780 |
Neg logit contributions | |
tum | -1.806 |
thirst | -1.556 |
night | -1.515 |
steak | -1.472 |
dinner | -1.420 |
Token | end |
Token ID | 886 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
tum | +0.138 |
thirst | +0.118 |
night | +0.118 |
steak | +0.109 |
lung | +0.106 |
Neg logit contributions | |
ples | -0.180 |
Jas | -0.168 |
ount | -0.167 |
paints | -0.163 |
yl | -0.162 |
Token | , |
Token ID | 11 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
ples | +5.570 |
ount | +5.100 |
ydia | +4.964 |
ptions | +4.920 |
violet | +4.873 |
Neg logit contributions | |
tum | -2.488 |
time | -1.769 |
night | -1.721 |
team | -1.686 |
thirst | -1.659 |
Token | Sally |
Token ID | 25737 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ples | +1.298 |
ount | +1.177 |
Jas | +1.119 |
yl | +1.098 |
paints | +1.096 |
Neg logit contributions | |
tum | -1.497 |
thirst | -1.321 |
night | -1.302 |
steak | -1.229 |
dinner | -1.193 |
Token | and |
Token ID | 290 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ples | +0.321 |
Jas | +0.295 |
ount | +0.295 |
yl | +0.284 |
paints | +0.284 |
Neg logit contributions | |
tum | -0.335 |
thirst | -0.293 |
night | -0.292 |
steak | -0.275 |
lung | -0.267 |
Token | Jill |
Token ID | 22772 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ples | +0.436 |
ount | +0.385 |
Jas | +0.377 |
yl | +0.357 |
paints | +0.356 |
Neg logit contributions | |
tum | -0.897 |
night | -0.813 |
thirst | -0.811 |
steak | -0.777 |
lung | -0.760 |
Token | were |
Token ID | 547 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
tum | +0.185 |
thirst | +0.163 |
night | +0.161 |
steak | +0.154 |
lung | +0.149 |
Neg logit contributions | |
ples | -0.176 |
Jas | -0.163 |
ount | -0.162 |
paints | -0.157 |
yl | -0.156 |
Token | so |
Token ID | 523 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
ples | +1.512 |
ount | +1.392 |
Jas | +1.363 |
paints | +1.346 |
yl | +1.343 |
Neg logit contributions | |
tum | -1.380 |
thirst | -1.195 |
night | -1.168 |
steak | -1.107 |
lung | -1.075 |
Token | tired |
Token ID | 10032 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
ples | +0.066 |
Jas | +0.061 |
ount | +0.061 |
yl | +0.059 |
paints | +0.059 |
Neg logit contributions | |
tum | -0.067 |
thirst | -0.059 |
night | -0.059 |
steak | -0.055 |
lung | -0.054 |
Token | that |
Token ID | 326 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ples | +0.114 |
Jas | +0.105 |
ount | +0.105 |
yl | +0.101 |
paints | +0.101 |
Neg logit contributions | |
tum | -0.127 |
thirst | -0.112 |
night | -0.111 |
steak | -0.105 |
lung | -0.102 |
Token | They |
Token ID | 1119 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
tum | +0.261 |
thirst | +0.228 |
night | +0.227 |
steak | +0.211 |
lung | +0.205 |
Neg logit contributions | |
ples | -0.311 |
Jas | -0.293 |
ount | -0.292 |
paints | -0.280 |
Kay | -0.279 |
Token | loved |
Token ID | 6151 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
ples | +0.763 |
ount | +0.705 |
Jas | +0.701 |
yl | +0.681 |
paints | +0.674 |
Neg logit contributions | |
tum | -0.715 |
thirst | -0.621 |
night | -0.615 |
steak | -0.578 |
lung | -0.560 |
Token | it |
Token ID | 340 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ples | +0.112 |
Jas | +0.103 |
ount | +0.102 |
paints | +0.099 |
yl | +0.099 |
Neg logit contributions | |
tum | -0.117 |
thirst | -0.103 |
night | -0.103 |
steak | -0.096 |
lung | -0.094 |
Token | and |
Token ID | 290 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
tum | +3.107 |
thirst | +2.766 |
night | +2.697 |
steak | +2.522 |
lung | +2.504 |
Neg logit contributions | |
ples | -2.389 |
blo | -2.224 |
Jas | -2.175 |
paints | -2.120 |
yl | -2.107 |
Token | asked |
Token ID | 1965 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
tum | +0.069 |
thirst | +0.060 |
night | +0.060 |
steak | +0.057 |
lung | +0.055 |
Neg logit contributions | |
ples | -0.070 |
Jas | -0.065 |
ount | -0.064 |
paints | -0.062 |
yl | -0.062 |
Token | Tim |
Token ID | 5045 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
tum | +1.084 |
thirst | +0.952 |
night | +0.941 |
steak | +0.883 |
lung | +0.879 |
Neg logit contributions | |
ples | -1.105 |
Jas | -1.052 |
ount | -1.013 |
Kay | -0.989 |
yl | -0.987 |
Token | my |
Token ID | 1820 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ples | +0.627 |
Jas | +0.537 |
ount | +0.535 |
yl | +0.504 |
paints | +0.495 |
Neg logit contributions | |
tum | -1.514 |
night | -1.374 |
thirst | -1.368 |
steak | -1.320 |
lung | -1.289 |
Token | how |
Token ID | 703 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
ples | +0.357 |
ount | +0.330 |
Jas | +0.330 |
yl | +0.319 |
paints | +0.319 |
Neg logit contributions | |
tum | -0.324 |
thirst | -0.281 |
night | -0.279 |
steak | -0.262 |
lung | -0.254 |
Token | he |
Token ID | 339 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
tum | +0.449 |
thirst | +0.388 |
night | +0.384 |
steak | +0.357 |
lung | +0.352 |
Neg logit contributions | |
ples | -0.555 |
Jas | -0.523 |
ount | -0.516 |
paints | -0.506 |
yl | -0.503 |
Token | made |
Token ID | 925 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
tum | +0.991 |
thirst | +0.877 |
night | +0.869 |
steak | +0.835 |
lung | +0.812 |
Neg logit contributions | |
ples | -0.708 |
Jas | -0.627 |
paints | -0.626 |
ount | -0.622 |
yl | -0.610 |
Token | it |
Token ID | 340 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
ples | +0.623 |
ount | +0.576 |
Jas | +0.571 |
yl | +0.554 |
paints | +0.553 |
Neg logit contributions | |
tum | -0.583 |
thirst | -0.506 |
night | -0.503 |
steak | -0.477 |
lung | -0.459 |
Token | � |
Token ID | 129 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ples | +1.069 |
ount | +0.993 |
Jas | +0.986 |
paints | +0.957 |
yl | +0.949 |
Neg logit contributions | |
tum | -0.934 |
thirst | -0.793 |
night | -0.791 |
steak | -0.742 |
lung | -0.720 |
Token | � |
Token ID | 241 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ples | +2.114 |
Jas | +1.968 |
ount | +1.947 |
paints | +1.944 |
yl | +1.889 |
Neg logit contributions | |
tum | -2.340 |
thirst | -2.091 |
night | -2.056 |
steak | -1.923 |
lung | -1.892 |
Token | Who |
Token ID | 8241 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ples | +3.045 |
ount | +2.845 |
els | +2.715 |
ptions | +2.714 |
paints | +2.710 |
Neg logit contributions | |
tum | -2.774 |
night | -2.394 |
thirst | -2.381 |
steak | -2.285 |
bye | -2.189 |
Token | are |
Token ID | 389 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ples | +0.199 |
Jas | +0.181 |
ount | +0.181 |
paints | +0.175 |
yl | +0.174 |
Neg logit contributions | |
tum | -0.246 |
thirst | -0.218 |
night | -0.217 |
steak | -0.205 |
lung | -0.200 |
Token | you |
Token ID | 345 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ples | +2.869 |
ount | +2.634 |
Jas | +2.590 |
paints | +2.514 |
ydia | +2.506 |
Neg logit contributions | |
tum | -1.755 |
thirst | -1.436 |
night | -1.433 |
steak | -1.372 |
lung | -1.298 |
Token | ? |
Token ID | 30 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
ples | +3.261 |
ount | +3.063 |
Jas | +3.040 |
paints | +2.865 |
ptions | +2.862 |
Neg logit contributions | |
tum | -2.583 |
thirst | -2.230 |
night | -2.194 |
lung | -2.107 |
steak | -2.077 |
Token | â |
Token ID | 22940 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ples | +1.807 |
Jas | +1.663 |
ount | +1.659 |
yl | +1.622 |
paints | +1.619 |
Neg logit contributions | |
tum | -1.543 |
night | -1.315 |
thirst | -1.306 |
steak | -1.249 |
lung | -1.224 |
Token | € |
Token ID | 26391 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
ples | +2.270 |
Jas | +2.137 |
ount | +2.110 |
paints | +2.087 |
yl | +2.035 |
Neg logit contributions | |
tum | -1.721 |
night | -1.577 |
thirst | -1.519 |
bye | -1.381 |
steak | -1.376 |
Token |
|
Token ID | 198 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
ples | +1.503 |
ount | +1.401 |
Jas | +1.385 |
paints | +1.355 |
ydia | +1.346 |
Neg logit contributions | |
tum | -1.124 |
thirst | -0.928 |
night | -0.927 |
steak | -0.872 |
lung | -0.836 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ples | +1.189 |
ount | +1.097 |
Jas | +1.085 |
paints | +1.068 |
yl | +1.053 |
Neg logit contributions | |
tum | -0.860 |
night | -0.719 |
thirst | -0.719 |
steak | -0.676 |
lung | -0.644 |
Token | The |
Token ID | 464 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
ples | +2.273 |
ount | +2.109 |
Jas | +2.099 |
paints | +2.087 |
yl | +2.034 |
Neg logit contributions | |
tum | -1.311 |
night | -1.079 |
thirst | -1.078 |
steak | -1.016 |
time | -0.967 |
Token | € |
Token ID | 26391 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
ples | +1.147 |
Jas | +1.068 |
ount | +1.064 |
paints | +1.040 |
yl | +1.033 |
Neg logit contributions | |
tum | -0.917 |
night | -0.807 |
thirst | -0.796 |
steak | -0.730 |
lung | -0.704 |
Token | The |
Token ID | 383 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
ples | +1.475 |
ount | +1.374 |
Jas | +1.356 |
paints | +1.330 |
yl | +1.323 |
Neg logit contributions | |
tum | -1.079 |
thirst | -0.894 |
night | -0.888 |
steak | -0.839 |
lung | -0.805 |
Token | bear |
Token ID | 6842 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
tum | +0.036 |
night | +0.031 |
thirst | +0.031 |
steak | +0.029 |
lung | +0.028 |
Neg logit contributions | |
ples | -0.036 |
Jas | -0.033 |
ount | -0.033 |
paints | -0.032 |
yl | -0.032 |
Token | thought |
Token ID | 1807 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
tum | +0.625 |
thirst | +0.556 |
night | +0.549 |
steak | +0.525 |
lung | +0.511 |
Neg logit contributions | |
ples | -0.496 |
Jas | -0.450 |
ount | -0.445 |
paints | -0.438 |
yl | -0.437 |
Token | that |
Token ID | 326 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
tum | +0.004 |
thirst | +0.004 |
night | +0.004 |
steak | +0.004 |
lung | +0.004 |
Neg logit contributions | |
ples | -0.004 |
Jas | -0.004 |
ount | -0.004 |
yl | -0.004 |
paints | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ples | +0.389 |
ount | +0.357 |
Jas | +0.357 |
yl | +0.343 |
paints | +0.343 |
Neg logit contributions | |
tum | -0.425 |
thirst | -0.373 |
night | -0.371 |
steak | -0.351 |
lung | -0.341 |
Token | a |
Token ID | 257 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ples | +2.539 |
ount | +2.381 |
Jas | +2.332 |
paints | +2.286 |
yl | +2.279 |
Neg logit contributions | |
tum | -2.029 |
thirst | -1.765 |
night | -1.701 |
steak | -1.655 |
lung | -1.578 |
Token | great |
Token ID | 1049 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
tum | +0.190 |
thirst | +0.166 |
night | +0.166 |
steak | +0.155 |
lung | +0.150 |
Neg logit contributions | |
ples | -0.184 |
Jas | -0.168 |
ount | -0.167 |
yl | -0.165 |
paints | -0.163 |
Token | idea |
Token ID | 2126 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
ples | +0.340 |
Jas | +0.314 |
ount | +0.314 |
yl | +0.304 |
paints | +0.303 |
Neg logit contributions | |
tum | -0.305 |
thirst | -0.265 |
night | -0.263 |
steak | -0.247 |
lung | -0.239 |
Token | so |
Token ID | 523 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ples | +1.128 |
ount | +1.035 |
Jas | +1.026 |
paints | +0.997 |
yl | +0.982 |
Neg logit contributions | |
tum | -1.208 |
night | -1.059 |
thirst | -1.047 |
steak | -1.002 |
lung | -0.963 |
Token | they |
Token ID | 484 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
tum | +0.212 |
thirst | +0.183 |
night | +0.180 |
steak | +0.168 |
lung | +0.164 |
Neg logit contributions | |
ples | -0.257 |
Jas | -0.242 |
ount | -0.238 |
yl | -0.234 |
Kay | -0.232 |
Token | sorry |
Token ID | 7926 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ples | +2.491 |
ount | +2.272 |
Jas | +2.200 |
paints | +2.195 |
ptions | +2.186 |
Neg logit contributions | |
tum | -1.936 |
thirst | -1.678 |
night | -1.584 |
steak | -1.525 |
lung | -1.487 |
Token | , |
Token ID | 11 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
ples | +0.511 |
ount | +0.474 |
Jas | +0.473 |
paints | +0.459 |
yl | +0.459 |
Neg logit contributions | |
tum | -0.397 |
thirst | -0.339 |
night | -0.337 |
steak | -0.314 |
lung | -0.303 |
Token | mum |
Token ID | 25682 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ples | +0.121 |
Jas | +0.113 |
ount | +0.112 |
yl | +0.109 |
paints | +0.109 |
Neg logit contributions | |
tum | -0.101 |
thirst | -0.088 |
night | -0.088 |
steak | -0.081 |
lung | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
ples | +3.443 |
ount | +3.333 |
Jas | +3.215 |
ptions | +3.197 |
ydia | +3.182 |
Neg logit contributions | |
tum | -2.761 |
night | -2.417 |
thirst | -2.273 |
steak | -2.216 |
lung | -2.139 |
Token | I |
Token ID | 314 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ples | +0.509 |
ount | +0.470 |
Jas | +0.469 |
yl | +0.453 |
paints | +0.452 |
Neg logit contributions | |
tum | -0.494 |
thirst | -0.430 |
night | -0.428 |
steak | -0.401 |
lung | -0.390 |
Token | learned |
Token ID | 4499 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
tum | +0.194 |
thirst | +0.171 |
night | +0.169 |
steak | +0.162 |
lung | +0.156 |
Neg logit contributions | |
ples | -0.175 |
Jas | -0.161 |
ount | -0.161 |
yl | -0.156 |
paints | -0.155 |
Token | my |
Token ID | 616 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
tum | +1.045 |
thirst | +0.941 |
night | +0.917 |
steak | +0.833 |
lung | +0.826 |
Neg logit contributions | |
ples | -0.967 |
Jas | -0.921 |
paints | -0.908 |
ount | -0.894 |
Kay | -0.888 |
Token | lesson |
Token ID | 11483 |
Feature activation | -8.00e-03 |
Pos logit contributions | |
tum | +0.185 |
thirst | +0.133 |
night | +0.129 |
steak | +0.103 |
lung | +0.092 |
Neg logit contributions | |
ples | -0.672 |
Jas | -0.643 |
paints | -0.636 |
ount | -0.636 |
yl | -0.632 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
tum | +0.015 |
thirst | +0.013 |
night | +0.013 |
steak | +0.012 |
lung | +0.012 |
Neg logit contributions | |
ples | -0.012 |
Jas | -0.011 |
ount | -0.011 |
yl | -0.011 |
paints | -0.011 |
Token | I |
Token ID | 314 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ples | +0.202 |
Jas | +0.186 |
ount | +0.185 |
paints | +0.179 |
yl | +0.179 |
Neg logit contributions | |
tum | -0.210 |
thirst | -0.184 |
night | -0.182 |
steak | -0.173 |
lung | -0.167 |
Token | don |
Token ID | 836 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
ples | +0.336 |
ount | +0.309 |
Jas | +0.309 |
yl | +0.298 |
paints | +0.298 |
Neg logit contributions | |
tum | -0.335 |
thirst | -0.292 |
night | -0.291 |
steak | -0.274 |
lung | -0.266 |
Token | height |
Token ID | 6001 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
ples | +0.518 |
ount | +0.478 |
Jas | +0.474 |
yl | +0.458 |
paints | +0.457 |
Neg logit contributions | |
tum | -0.540 |
thirst | -0.473 |
night | -0.469 |
steak | -0.446 |
lung | -0.433 |
Token | . |
Token ID | 13 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
ples | +0.442 |
ount | +0.407 |
Jas | +0.407 |
yl | +0.393 |
paints | +0.392 |
Neg logit contributions | |
tum | -0.433 |
thirst | -0.378 |
night | -0.375 |
steak | -0.354 |
lung | -0.343 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ples | +1.293 |
ount | +1.131 |
Jas | +1.113 |
yl | +1.109 |
paints | +1.086 |
Neg logit contributions | |
tum | -2.003 |
thirst | -1.759 |
night | -1.738 |
steak | -1.692 |
lung | -1.652 |
Token | 's |
Token ID | 338 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ples | +1.417 |
Jas | +1.316 |
ount | +1.304 |
yl | +1.262 |
ydia | +1.252 |
Neg logit contributions | |
tum | -2.080 |
night | -1.835 |
thirst | -1.818 |
steak | -1.778 |
lung | -1.745 |
Token | tower |
Token ID | 10580 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
tum | +1.931 |
thirst | +1.830 |
night | +1.820 |
steak | +1.564 |
drowned | +1.562 |
Neg logit contributions | |
ples | -2.512 |
paints | -2.506 |
Jas | -2.418 |
mirror | -2.328 |
blo | -2.304 |
Token | is |
Token ID | 318 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ples | +0.056 |
ount | +0.050 |
Jas | +0.050 |
paints | +0.048 |
yl | +0.048 |
Neg logit contributions | |
tum | -0.094 |
thirst | -0.085 |
night | -0.084 |
steak | -0.080 |
lung | -0.078 |
Token | big |
Token ID | 1263 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
ples | +0.258 |
Jas | +0.237 |
ount | +0.237 |
paints | +0.229 |
yl | +0.228 |
Neg logit contributions | |
tum | -0.267 |
thirst | -0.234 |
night | -0.233 |
steak | -0.219 |
lung | -0.213 |
Token | in |
Token ID | 287 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ples | +0.933 |
ount | +0.875 |
Jas | +0.872 |
yl | +0.844 |
ydia | +0.834 |
Neg logit contributions | |
tum | -0.776 |
night | -0.662 |
thirst | -0.659 |
steak | -0.628 |
lung | -0.606 |
Token | width |
Token ID | 9647 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
tum | +0.320 |
night | +0.283 |
thirst | +0.283 |
steak | +0.260 |
lung | +0.254 |
Neg logit contributions | |
ples | -0.282 |
Jas | -0.260 |
ount | -0.254 |
paints | -0.250 |
yl | -0.249 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
ples | +0.364 |
ount | +0.334 |
Jas | +0.334 |
yl | +0.322 |
paints | +0.321 |
Neg logit contributions | |
tum | -0.393 |
thirst | -0.345 |
night | -0.343 |
steak | -0.324 |
lung | -0.315 |
Token | You |
Token ID | 921 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ples | +0.422 |
ount | +0.393 |
Jas | +0.393 |
yl | +0.381 |
paints | +0.381 |
Neg logit contributions | |
tum | -0.305 |
thirst | -0.259 |
night | -0.257 |
steak | -0.239 |
lung | -0.230 |
Token | , |
Token ID | 11 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
tum | +1.604 |
thirst | +1.436 |
night | +1.380 |
uch | +1.294 |
lung | +1.276 |
Neg logit contributions | |
ples | -1.808 |
Jas | -1.737 |
ount | -1.663 |
Kay | -1.659 |
yl | -1.656 |
Token | " |
Token ID | 366 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
tum | +0.724 |
thirst | +0.656 |
night | +0.656 |
steak | +0.620 |
lung | +0.607 |
Neg logit contributions | |
ples | -0.423 |
Jas | -0.384 |
ount | -0.375 |
yl | -0.362 |
paints | -0.357 |
Token | Is |
Token ID | 3792 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
tum | +0.569 |
thirst | +0.514 |
night | +0.511 |
steak | +0.482 |
lung | +0.472 |
Neg logit contributions | |
ples | -0.297 |
ount | -0.266 |
Jas | -0.265 |
yl | -0.253 |
paints | -0.251 |
Token | the |
Token ID | 262 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
tum | +0.563 |
thirst | +0.502 |
night | +0.493 |
steak | +0.456 |
lung | +0.450 |
Neg logit contributions | |
ples | -0.516 |
Jas | -0.483 |
ount | -0.478 |
paints | -0.470 |
yl | -0.468 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ples | +2.083 |
ount | +1.895 |
Jas | +1.886 |
violet | +1.752 |
paints | +1.749 |
Neg logit contributions | |
tum | -2.171 |
night | -1.818 |
steak | -1.811 |
thirst | -1.808 |
lung | -1.759 |
Token | man |
Token ID | 582 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ples | +2.081 |
ount | +1.911 |
Jas | +1.898 |
paints | +1.810 |
violet | +1.801 |
Neg logit contributions | |
tum | -1.869 |
night | -1.597 |
steak | -1.539 |
thirst | -1.537 |
lung | -1.482 |
Token | going |
Token ID | 1016 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
tum | +0.606 |
thirst | +0.541 |
night | +0.532 |
steak | +0.498 |
lung | +0.485 |
Neg logit contributions | |
ples | -0.534 |
ount | -0.493 |
Jas | -0.486 |
yl | -0.473 |
paints | -0.473 |
Token | to |
Token ID | 284 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
ples | +0.395 |
ount | +0.366 |
Jas | +0.366 |
yl | +0.354 |
paints | +0.354 |
Neg logit contributions | |
tum | -0.338 |
thirst | -0.291 |
night | -0.290 |
steak | -0.271 |
lung | -0.262 |
Token | jail |
Token ID | 7356 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
tum | +1.387 |
night | +1.253 |
thirst | +1.238 |
steak | +1.134 |
lung | +1.081 |
Neg logit contributions | |
ples | -1.294 |
Jas | -1.229 |
ount | -1.220 |
Kay | -1.194 |
paints | -1.183 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
tum | +1.043 |
thirst | +0.938 |
night | +0.909 |
steak | +0.852 |
lung | +0.840 |
Neg logit contributions | |
ples | -0.876 |
ount | -0.812 |
Jas | -0.810 |
paints | -0.782 |
yl | -0.778 |
Token | His |
Token ID | 2399 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
tum | +3.751 |
thirst | +3.547 |
night | +3.434 |
uch | +3.377 |
lung | +3.232 |
Neg logit contributions | |
ples | -2.855 |
Jas | -2.842 |
Kay | -2.800 |
Jem | -2.681 |
ount | -2.661 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ples | +0.556 |
ount | +0.515 |
Jas | +0.514 |
paints | +0.500 |
yl | +0.498 |
Neg logit contributions | |
tum | -0.439 |
thirst | -0.375 |
night | -0.372 |
steak | -0.348 |
lung | -0.336 |
Token | He |
Token ID | 1544 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
tum | +0.308 |
thirst | +0.263 |
night | +0.261 |
steak | +0.240 |
lung | +0.232 |
Neg logit contributions | |
ples | -0.400 |
Jas | -0.377 |
ount | -0.374 |
yl | -0.365 |
ydia | -0.361 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
tum | +0.636 |
thirst | +0.568 |
night | +0.563 |
steak | +0.538 |
lung | +0.524 |
Neg logit contributions | |
ples | -0.470 |
Jas | -0.430 |
ount | -0.417 |
yl | -0.416 |
paints | -0.412 |
Token | a |
Token ID | 257 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
tum | +0.269 |
thirst | +0.225 |
night | +0.221 |
steak | +0.200 |
lung | +0.194 |
Neg logit contributions | |
ples | -0.487 |
Jas | -0.468 |
ount | -0.458 |
yl | -0.453 |
paints | -0.448 |
Token | bird |
Token ID | 6512 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
ples | +1.469 |
ount | +1.350 |
Jas | +1.315 |
paints | +1.268 |
ydia | +1.254 |
Neg logit contributions | |
tum | -1.788 |
thirst | -1.547 |
night | -1.537 |
steak | -1.496 |
lung | -1.459 |
Token | . |
Token ID | 13 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
ples | +1.187 |
Jas | +1.092 |
ount | +1.085 |
paints | +1.045 |
yl | +1.037 |
Neg logit contributions | |
tum | -1.173 |
thirst | -1.018 |
night | -1.017 |
steak | -0.957 |
lung | -0.934 |
Token | The |
Token ID | 383 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
tum | +1.108 |
thirst | +0.984 |
night | +0.982 |
steak | +0.898 |
lung | +0.862 |
Neg logit contributions | |
ples | -1.249 |
Jas | -1.181 |
ount | -1.159 |
yl | -1.143 |
Kay | -1.137 |
Token | bird |
Token ID | 6512 |
Feature activation | -4.02e-05 |
Pos logit contributions | |
tum | +1.112 |
night | +1.021 |
thirst | +0.996 |
steak | +0.914 |
lung | +0.866 |
Neg logit contributions | |
ples | -1.006 |
yl | -0.943 |
paints | -0.943 |
Jas | -0.935 |
blo | -0.929 |
Token | said |
Token ID | 531 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
tum | +0.000 |
thirst | +0.000 |
night | +0.000 |
steak | +0.000 |
lung | +0.000 |
Neg logit contributions | |
ples | -0.000 |
Jas | -0.000 |
ount | -0.000 |
yl | -0.000 |
paints | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
tum | +0.294 |
thirst | +0.258 |
night | +0.257 |
steak | +0.236 |
lung | +0.230 |
Neg logit contributions | |
ples | -0.334 |
Jas | -0.311 |
ount | -0.308 |
yl | -0.304 |
paints | -0.302 |
Token | That |
Token ID | 2504 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
tum | +0.645 |
thirst | +0.578 |
night | +0.571 |
steak | +0.544 |
lung | +0.527 |
Neg logit contributions | |
ples | -0.403 |
ount | -0.361 |
Jas | -0.356 |
yl | -0.349 |
paints | -0.345 |
Token | sits |
Token ID | 10718 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ples | +1.795 |
ount | +1.594 |
Jas | +1.571 |
yl | +1.553 |
ydia | +1.521 |
Neg logit contributions | |
tum | -2.565 |
night | -2.250 |
thirst | -2.240 |
steak | -2.154 |
lung | -2.112 |
Token | next |
Token ID | 1306 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
ples | +0.298 |
Jas | +0.273 |
ount | +0.273 |
yl | +0.263 |
paints | +0.263 |
Neg logit contributions | |
tum | -0.321 |
thirst | -0.282 |
night | -0.280 |
steak | -0.265 |
lung | -0.257 |
Token | to |
Token ID | 284 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
ples | +1.503 |
ount | +1.407 |
Jas | +1.384 |
ydia | +1.343 |
paints | +1.342 |
Neg logit contributions | |
tum | -0.949 |
night | -0.790 |
thirst | -0.765 |
steak | -0.725 |
lung | -0.685 |
Token | Sam |
Token ID | 3409 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ples | +0.405 |
ount | +0.372 |
Jas | +0.371 |
yl | +0.358 |
paints | +0.357 |
Neg logit contributions | |
tum | -0.427 |
thirst | -0.374 |
night | -0.372 |
steak | -0.352 |
lung | -0.341 |
Token | on |
Token ID | 319 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ples | +0.540 |
Jas | +0.497 |
ount | +0.497 |
yl | +0.480 |
paints | +0.478 |
Neg logit contributions | |
tum | -0.536 |
thirst | -0.466 |
night | -0.465 |
steak | -0.438 |
lung | -0.425 |
Token | the |
Token ID | 262 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
tum | +0.341 |
thirst | +0.304 |
night | +0.300 |
steak | +0.279 |
lung | +0.273 |
Neg logit contributions | |
ples | -0.294 |
Jas | -0.276 |
ount | -0.266 |
yl | -0.263 |
paints | -0.263 |
Token | slide |
Token ID | 10649 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
tum | +1.234 |
night | +1.150 |
thirst | +1.138 |
steak | +1.062 |
lung | +1.049 |
Neg logit contributions | |
ples | -0.880 |
Jas | -0.838 |
paints | -0.830 |
ount | -0.821 |
Kay | -0.796 |
Token | . |
Token ID | 13 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
tum | +0.516 |
thirst | +0.465 |
night | +0.458 |
steak | +0.433 |
lung | +0.424 |
Neg logit contributions | |
ples | -0.416 |
Jas | -0.384 |
ount | -0.382 |
paints | -0.369 |
yl | -0.367 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ples | +0.665 |
ount | +0.592 |
Jas | +0.583 |
yl | +0.568 |
paints | +0.558 |
Neg logit contributions | |
tum | -1.068 |
thirst | -0.950 |
night | -0.948 |
steak | -0.905 |
lung | -0.881 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ples | +0.239 |
Jas | +0.223 |
ount | +0.222 |
yl | +0.216 |
paints | +0.215 |
Neg logit contributions | |
tum | -0.198 |
thirst | -0.171 |
night | -0.169 |
steak | -0.158 |
lung | -0.153 |
Token | " |
Token ID | 1 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ples | +0.201 |
Jas | +0.186 |
ount | +0.185 |
yl | +0.179 |
paints | +0.179 |
Neg logit contributions | |
tum | -0.189 |
thirst | -0.164 |
night | -0.163 |
steak | -0.153 |
lung | -0.148 |
Token | sad |
Token ID | 6507 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
tum | +0.849 |
thirst | +0.747 |
night | +0.742 |
steak | +0.716 |
lung | +0.694 |
Neg logit contributions | |
ples | -0.718 |
Jas | -0.664 |
ount | -0.645 |
blo | -0.635 |
paints | -0.627 |
Token | . |
Token ID | 13 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
tum | +1.531 |
thirst | +1.391 |
night | +1.336 |
steak | +1.296 |
lung | +1.274 |
Neg logit contributions | |
ples | -1.102 |
Jas | -1.002 |
ount | -1.001 |
blo | -0.963 |
paints | -0.954 |
Token | She |
Token ID | 1375 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
tum | +1.253 |
thirst | +1.135 |
night | +1.123 |
steak | +1.031 |
lung | +1.030 |
Neg logit contributions | |
ples | -1.178 |
Jas | -1.116 |
ount | -1.108 |
Kay | -1.083 |
paints | -1.068 |
Token | played |
Token ID | 2826 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
tum | +0.975 |
thirst | +0.873 |
night | +0.864 |
steak | +0.832 |
lung | +0.802 |
Neg logit contributions | |
ples | -0.720 |
Jas | -0.656 |
ount | -0.643 |
paints | -0.637 |
yl | -0.626 |
Token | with |
Token ID | 351 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
tum | +1.314 |
thirst | +1.142 |
night | +1.135 |
lung | +1.059 |
steak | +1.041 |
Neg logit contributions | |
ples | -1.246 |
Jas | -1.193 |
ount | -1.168 |
yl | -1.133 |
ydia | -1.127 |
Token | him |
Token ID | 683 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
tum | +1.615 |
night | +1.430 |
thirst | +1.416 |
lung | +1.305 |
steak | +1.262 |
Neg logit contributions | |
ples | -1.556 |
Jas | -1.485 |
Kay | -1.474 |
ount | -1.447 |
blo | -1.432 |
Token | in |
Token ID | 287 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
tum | +4.348 |
night | +3.880 |
thirst | +3.851 |
current | +3.585 |
bye | +3.559 |
Neg logit contributions | |
ples | -3.158 |
blo | -3.110 |
paints | -3.044 |
yl | -2.882 |
written | -2.843 |
Token | the |
Token ID | 262 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
ples | +1.466 |
ount | +1.383 |
Jas | +1.339 |
yl | +1.310 |
paints | +1.296 |
Neg logit contributions | |
tum | -1.238 |
thirst | -1.059 |
night | -1.034 |
steak | -1.012 |
lung | -0.970 |
Token | park |
Token ID | 3952 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
ples | +0.306 |
ount | +0.275 |
Jas | +0.275 |
yl | +0.262 |
paints | +0.262 |
Neg logit contributions | |
tum | -0.471 |
thirst | -0.421 |
night | -0.419 |
steak | -0.400 |
lung | -0.391 |
Token | and |
Token ID | 290 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
tum | +1.556 |
thirst | +1.383 |
night | +1.374 |
steak | +1.279 |
lung | +1.273 |
Neg logit contributions | |
ples | -1.476 |
Jas | -1.362 |
ount | -1.336 |
blo | -1.324 |
paints | -1.316 |
Token | at |
Token ID | 379 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
tum | +0.411 |
thirst | +0.364 |
night | +0.362 |
steak | +0.341 |
lung | +0.334 |
Neg logit contributions | |
ples | -0.367 |
Jas | -0.341 |
ount | -0.336 |
paints | -0.327 |
yl | -0.327 |
Token | grab |
Token ID | 5552 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
tum | +0.608 |
night | +0.546 |
thirst | +0.543 |
steak | +0.511 |
lung | +0.492 |
Neg logit contributions | |
ples | -0.563 |
ount | -0.521 |
Jas | -0.513 |
paints | -0.505 |
yl | -0.499 |
Token | a |
Token ID | 257 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
tum | +0.510 |
night | +0.446 |
thirst | +0.444 |
steak | +0.408 |
lung | +0.402 |
Neg logit contributions | |
ples | -0.515 |
ount | -0.471 |
Jas | -0.470 |
yl | -0.460 |
paints | -0.457 |
Token | few |
Token ID | 1178 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
ples | +0.179 |
ount | +0.167 |
Jas | +0.166 |
yl | +0.162 |
paints | +0.162 |
Neg logit contributions | |
tum | -0.122 |
thirst | -0.104 |
night | -0.103 |
steak | -0.095 |
lung | -0.091 |
Token | peanuts |
Token ID | 45612 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ples | +1.641 |
Jas | +1.547 |
ount | +1.529 |
yl | +1.474 |
Kay | +1.465 |
Neg logit contributions | |
tum | -1.416 |
thirst | -1.211 |
night | -1.170 |
steak | -1.120 |
lung | -1.059 |
Token | . |
Token ID | 13 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
tum | +0.858 |
thirst | +0.772 |
night | +0.756 |
steak | +0.701 |
lung | +0.696 |
Neg logit contributions | |
ples | -0.722 |
ount | -0.672 |
Jas | -0.655 |
paints | -0.644 |
yl | -0.640 |
Token | But |
Token ID | 887 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
tum | +3.375 |
thirst | +3.189 |
uch | +2.975 |
night | +2.923 |
drowned | +2.734 |
Neg logit contributions | |
ples | -3.566 |
Kay | -3.461 |
Jas | -3.400 |
ount | -3.342 |
Jem | -3.285 |
Token | the |
Token ID | 262 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
tum | +5.683 |
night | +5.136 |
thirst | +5.080 |
uch | +4.772 |
bye | +4.565 |
Neg logit contributions | |
Kay | -3.907 |
yl | -3.774 |
ples | -3.685 |
Jem | -3.652 |
blo | -3.619 |
Token | peanut |
Token ID | 26636 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
ples | +0.679 |
ount | +0.629 |
Jas | +0.629 |
yl | +0.605 |
paints | +0.605 |
Neg logit contributions | |
tum | -0.583 |
thirst | -0.500 |
night | -0.492 |
steak | -0.467 |
lung | -0.450 |
Token | tree |
Token ID | 5509 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
tum | +1.400 |
night | +1.273 |
thirst | +1.261 |
steak | +1.164 |
lung | +1.144 |
Neg logit contributions | |
ples | -1.134 |
yl | -1.035 |
paints | -1.024 |
Jas | -1.022 |
blo | -1.017 |
Token | was |
Token ID | 373 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
tum | +2.235 |
night | +2.068 |
thirst | +2.022 |
steak | +1.914 |
lung | +1.846 |
Neg logit contributions | |
ples | -1.794 |
yl | -1.656 |
Jas | -1.621 |
paints | -1.620 |
ount | -1.609 |
Token | very |
Token ID | 845 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
tum | +0.553 |
night | +0.490 |
thirst | +0.478 |
steak | +0.445 |
lung | +0.435 |
Neg logit contributions | |
ples | -0.610 |
Jas | -0.559 |
ount | -0.558 |
blo | -0.548 |
yl | -0.545 |
Token | storm |
Token ID | 6388 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
tum | +1.563 |
thirst | +1.385 |
night | +1.381 |
steak | +1.252 |
uch | +1.227 |
Neg logit contributions | |
ples | -1.667 |
paints | -1.546 |
Jas | -1.535 |
blo | -1.533 |
ount | -1.487 |
Token | raged |
Token ID | 49000 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
ples | +0.400 |
ount | +0.368 |
Jas | +0.367 |
yl | +0.354 |
paints | +0.354 |
Neg logit contributions | |
tum | -0.415 |
thirst | -0.364 |
night | -0.362 |
steak | -0.341 |
lung | -0.331 |
Token | on |
Token ID | 319 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
tum | +0.030 |
thirst | +0.026 |
night | +0.026 |
steak | +0.025 |
lung | +0.024 |
Neg logit contributions | |
ples | -0.022 |
Jas | -0.020 |
ount | -0.020 |
yl | -0.019 |
paints | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
tum | +0.876 |
thirst | +0.767 |
night | +0.755 |
steak | +0.710 |
lung | +0.686 |
Neg logit contributions | |
ples | -0.896 |
Jas | -0.821 |
ount | -0.803 |
yl | -0.788 |
paints | -0.785 |
Token | Winds |
Token ID | 22608 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
tum | +1.325 |
night | +1.192 |
thirst | +1.172 |
steak | +1.115 |
lung | +1.081 |
Neg logit contributions | |
ples | -1.356 |
Jas | -1.291 |
ount | -1.278 |
Kay | -1.227 |
paints | -1.199 |
Token | whipped |
Token ID | 30712 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
tum | +0.202 |
thirst | +0.177 |
night | +0.176 |
steak | +0.167 |
lung | +0.161 |
Neg logit contributions | |
ples | -0.182 |
ount | -0.165 |
Jas | -0.165 |
paints | -0.159 |
yl | -0.159 |
Token | and |
Token ID | 290 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
tum | +3.927 |
thirst | +3.396 |
night | +3.256 |
lung | +3.182 |
steak | +3.141 |
Neg logit contributions | |
ples | -3.074 |
Jas | -2.763 |
blo | -2.706 |
paints | -2.706 |
ount | -2.700 |
Token | rain |
Token ID | 6290 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
tum | +2.113 |
night | +1.863 |
thirst | +1.848 |
steak | +1.785 |
lung | +1.708 |
Neg logit contributions | |
ples | -1.916 |
Jas | -1.793 |
blo | -1.730 |
paints | -1.730 |
ount | -1.706 |
Token | fell |
Token ID | 3214 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
tum | +1.070 |
thirst | +0.956 |
night | +0.931 |
steak | +0.922 |
lung | +0.884 |
Neg logit contributions | |
ples | -0.897 |
Jas | -0.812 |
ount | -0.810 |
yl | -0.775 |
paints | -0.775 |
Token | heavily |
Token ID | 7272 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
tum | +1.313 |
thirst | +1.179 |
night | +1.142 |
steak | +1.109 |
lung | +1.053 |
Neg logit contributions | |
ples | -1.179 |
Jas | -1.069 |
ount | -1.065 |
blo | -1.032 |
paints | -1.031 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ples | +0.044 |
ount | +0.040 |
Jas | +0.040 |
yl | +0.038 |
paints | +0.038 |
Neg logit contributions | |
tum | -0.049 |
thirst | -0.043 |
night | -0.043 |
steak | -0.040 |
lung | -0.039 |
Token | that |
Token ID | 326 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
tum | +1.460 |
thirst | +1.282 |
night | +1.273 |
steak | +1.206 |
lung | +1.181 |
Neg logit contributions | |
ples | -1.341 |
Jas | -1.216 |
blo | -1.208 |
ount | -1.187 |
yl | -1.170 |
Token | they |
Token ID | 484 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
tum | +2.137 |
thirst | +1.909 |
night | +1.875 |
steak | +1.753 |
hind | +1.694 |
Neg logit contributions | |
ples | -2.377 |
Jas | -2.277 |
blo | -2.195 |
Kay | -2.171 |
paints | -2.156 |
Token | both |
Token ID | 1111 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
tum | +2.168 |
night | +1.897 |
thirst | +1.888 |
steak | +1.872 |
lung | +1.782 |
Neg logit contributions | |
ples | -1.753 |
Jas | -1.629 |
ount | -1.584 |
blo | -1.578 |
yl | -1.544 |
Token | slept |
Token ID | 21256 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
tum | +2.407 |
steak | +2.134 |
thirst | +2.134 |
night | +2.104 |
lung | +2.017 |
Neg logit contributions | |
ples | -1.869 |
Jas | -1.692 |
blo | -1.648 |
ount | -1.623 |
paints | -1.614 |
Token | for |
Token ID | 329 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
tum | +3.282 |
thirst | +2.755 |
night | +2.680 |
steak | +2.659 |
lung | +2.576 |
Neg logit contributions | |
ples | -3.144 |
blo | -2.877 |
Jas | -2.873 |
yl | -2.756 |
ount | -2.732 |
Token | a |
Token ID | 257 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
tum | +2.576 |
night | +2.210 |
thirst | +2.145 |
steak | +2.031 |
current | +2.025 |
Neg logit contributions | |
ples | -2.556 |
Jas | -2.373 |
blo | -2.303 |
yl | -2.260 |
Kay | -2.252 |
Token | long |
Token ID | 890 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
tum | +3.067 |
thirst | +2.753 |
night | +2.735 |
steak | +2.511 |
edly | +2.493 |
Neg logit contributions | |
ples | -4.003 |
blo | -3.998 |
yl | -3.961 |
violet | -3.750 |
Kay | -3.719 |
Token | , |
Token ID | 11 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
tum | +2.461 |
thirst | +2.191 |
night | +2.118 |
steak | +2.017 |
lung | +1.979 |
Neg logit contributions | |
ples | -3.083 |
blo | -2.853 |
Jas | -2.851 |
yl | -2.816 |
paints | -2.789 |
Token | long |
Token ID | 890 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
tum | +1.613 |
night | +1.424 |
thirst | +1.404 |
steak | +1.315 |
lung | +1.291 |
Neg logit contributions | |
ples | -1.646 |
Jas | -1.532 |
blo | -1.504 |
paints | -1.494 |
ount | -1.472 |
Token | time |
Token ID | 640 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
tum | +1.592 |
thirst | +1.386 |
night | +1.374 |
steak | +1.270 |
lung | +1.217 |
Neg logit contributions | |
ples | -2.230 |
Jas | -2.052 |
blo | -2.049 |
paints | -2.041 |
yl | -1.997 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
tum | +0.988 |
thirst | +0.870 |
night | +0.864 |
steak | +0.820 |
lung | +0.794 |
Neg logit contributions | |
ples | -0.907 |
Jas | -0.831 |
ount | -0.812 |
blo | -0.803 |
paints | -0.796 |
Token | day |
Token ID | 1110 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
tum | +3.116 |
thirst | +2.903 |
night | +2.775 |
edly | +2.597 |
lung | +2.391 |
Neg logit contributions | |
blo | -3.619 |
paints | -3.611 |
ples | -3.541 |
yl | -3.516 |
Jas | -3.464 |
Token | , |
Token ID | 11 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
tum | +2.322 |
thirst | +2.198 |
night | +2.096 |
steak | +1.977 |
lung | +1.926 |
Neg logit contributions | |
ples | -2.157 |
Jas | -2.081 |
ount | -1.989 |
yl | -1.974 |
Kay | -1.959 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
tum | +4.597 |
thirst | +4.400 |
night | +4.268 |
edly | +4.037 |
bye | +3.916 |
Neg logit contributions | |
Jas | -3.626 |
ples | -3.600 |
Melissa | -3.502 |
typing | -3.488 |
paints | -3.403 |
Token | was |
Token ID | 373 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
tum | +2.391 |
thirst | +2.191 |
night | +2.117 |
steak | +2.021 |
time | +1.920 |
Neg logit contributions | |
ples | -1.914 |
Jas | -1.725 |
paints | -1.706 |
yl | -1.670 |
blo | -1.659 |
Token | tired |
Token ID | 10032 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
tum | +2.211 |
night | +2.065 |
thirst | +2.002 |
steak | +1.908 |
bye | +1.842 |
Neg logit contributions | |
ples | -1.927 |
Jas | -1.821 |
blo | -1.785 |
ount | -1.762 |
drawn | -1.749 |
Token | but |
Token ID | 475 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
tum | +2.843 |
thirst | +2.735 |
night | +2.645 |
steak | +2.458 |
uch | +2.443 |
Neg logit contributions | |
ples | -2.235 |
Jas | -2.100 |
ount | -2.085 |
blo | -2.052 |
yl | -2.001 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
tum | +4.320 |
night | +4.051 |
thirst | +3.926 |
uch | +3.777 |
time | +3.687 |
Neg logit contributions | |
Jas | -2.689 |
ples | -2.681 |
blo | -2.674 |
written | -2.672 |
drawn | -2.619 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
tum | +2.571 |
thirst | +2.409 |
night | +2.268 |
uch | +2.177 |
steak | +2.175 |
Neg logit contributions | |
ples | -1.700 |
Jas | -1.640 |
yl | -1.545 |
written | -1.543 |
blo | -1.528 |
Token | He |
Token ID | 679 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
tum | +2.552 |
thirst | +2.532 |
night | +2.206 |
uch | +2.168 |
steak | +2.135 |
Neg logit contributions | |
ples | -2.975 |
Jas | -2.870 |
ydia | -2.722 |
paints | -2.713 |
ount | -2.691 |
Token | went |
Token ID | 1816 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
tum | +4.090 |
thirst | +3.719 |
night | +3.594 |
time | +3.547 |
steak | +3.505 |
Neg logit contributions | |
ples | -2.495 |
blo | -2.226 |
paints | -2.211 |
written | -2.177 |
Jas | -2.163 |
Token | home |
Token ID | 1363 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
tum | +0.309 |
thirst | +0.269 |
night | +0.261 |
steak | +0.244 |
lung | +0.238 |
Neg logit contributions | |
ples | -0.381 |
ount | -0.358 |
Jas | -0.357 |
yl | -0.349 |
paints | -0.348 |