Token | to |
Token ID | 284 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
lor | +0.005 |
ests | +0.005 |
dentist | +0.004 |
fault | +0.004 |
lair | +0.004 |
Neg logit contributions | |
Run | -0.010 |
forth | -0.009 |
gust | -0.009 |
www | -0.009 |
boom | -0.009 |
Token | feel |
Token ID | 1254 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
lor | +0.011 |
ests | +0.011 |
lair | +0.011 |
dentist | +0.011 |
fault | +0.010 |
Neg logit contributions | |
Run | -0.016 |
www | -0.015 |
forth | -0.014 |
gust | -0.014 |
ww | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
Run | +0.057 |
gust | +0.051 |
www | +0.050 |
forth | +0.047 |
ww | +0.046 |
Neg logit contributions | |
lor | -0.068 |
lair | -0.066 |
ests | -0.065 |
dentist | -0.065 |
fault | -0.064 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
Run | +0.017 |
www | +0.016 |
forth | +0.015 |
ww | +0.015 |
ang | +0.014 |
Neg logit contributions | |
dentist | -0.013 |
clinic | -0.013 |
aid | -0.012 |
lair | -0.012 |
fault | -0.012 |
Token | w |
Token ID | 266 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
Run | +0.109 |
www | +0.107 |
ww | +0.101 |
forth | +0.095 |
AW | +0.090 |
Neg logit contributions | |
dentist | -0.073 |
fault | -0.071 |
clinic | -0.071 |
truth | -0.070 |
lair | -0.069 |
Token | obb |
Token ID | 21963 |
Feature activation | +9.34e+00 |
Pos logit contributions | |
Run | +0.125 |
www | +0.116 |
ww | +0.109 |
forth | +0.106 |
gust | +0.102 |
Neg logit contributions | |
dentist | -0.109 |
fault | -0.108 |
lair | -0.106 |
clinic | -0.103 |
lor | -0.103 |
Token | ly |
Token ID | 306 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Run | +0.214 |
www | +0.194 |
Uh | +0.176 |
ww | +0.176 |
gust | +0.170 |
Neg logit contributions | |
fault | -0.193 |
ache | -0.192 |
dentist | -0.182 |
osc | -0.182 |
stitches | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Run | +0.052 |
www | +0.047 |
forth | +0.046 |
gust | +0.046 |
ww | +0.045 |
Neg logit contributions | |
dentist | -0.035 |
ests | -0.034 |
lor | -0.034 |
lair | -0.033 |
fault | -0.033 |
Token | Before |
Token ID | 7413 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
wounds | +0.007 |
fault | +0.007 |
lair | +0.007 |
lor | +0.007 |
cards | +0.006 |
Neg logit contributions | |
Run | -0.007 |
gust | -0.007 |
www | -0.007 |
ww | -0.006 |
ch | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Run | +0.058 |
www | +0.056 |
forth | +0.052 |
ww | +0.052 |
ang | +0.048 |
Neg logit contributions | |
dentist | -0.049 |
lair | -0.045 |
clinic | -0.044 |
fault | -0.044 |
lor | -0.043 |
Token | knew |
Token ID | 2993 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Run | +0.033 |
www | +0.031 |
gust | +0.029 |
ww | +0.029 |
forth | +0.029 |
Neg logit contributions | |
lair | -0.034 |
fault | -0.034 |
dentist | -0.034 |
clinic | -0.034 |
ests | -0.033 |
Token | he |
Token ID | 339 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
Run | +0.046 |
www | +0.045 |
ww | +0.042 |
gust | +0.039 |
forth | +0.039 |
Neg logit contributions | |
dentist | -0.039 |
lair | -0.039 |
fault | -0.037 |
clinic | -0.036 |
wounds | -0.036 |
Token | jumped |
Token ID | 11687 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Run | +0.016 |
www | +0.015 |
ww | +0.014 |
forth | +0.014 |
gust | +0.014 |
Neg logit contributions | |
fault | -0.015 |
dentist | -0.015 |
lair | -0.015 |
clinic | -0.015 |
lor | -0.015 |
Token | ! |
Token ID | 0 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
www | +0.080 |
Run | +0.079 |
ww | +0.076 |
forth | +0.071 |
gust | +0.070 |
Neg logit contributions | |
lair | -0.047 |
fault | -0.046 |
dentist | -0.045 |
aid | -0.045 |
truth | -0.044 |
Token | His |
Token ID | 2399 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
dentist | +0.006 |
lair | +0.006 |
fault | +0.006 |
clinic | +0.006 |
lor | +0.006 |
Neg logit contributions | |
Run | -0.011 |
www | -0.010 |
gust | -0.010 |
ww | -0.010 |
forth | -0.009 |
Token | ears |
Token ID | 11368 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
lor | +0.046 |
dentist | +0.046 |
lair | +0.043 |
clinic | +0.043 |
ests | +0.042 |
Neg logit contributions | |
Run | -0.047 |
www | -0.044 |
forth | -0.044 |
gust | -0.043 |
ww | -0.042 |
Token | flo |
Token ID | 5530 |
Feature activation | +9.27e+00 |
Pos logit contributions | |
Run | +0.059 |
www | +0.058 |
ww | +0.055 |
forth | +0.053 |
gust | +0.050 |
Neg logit contributions | |
dentist | -0.033 |
fault | -0.033 |
lair | -0.033 |
lor | -0.032 |
clinic | -0.032 |
Token | pped |
Token ID | 1496 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Run | +0.218 |
www | +0.216 |
ww | +0.199 |
gust | +0.197 |
boom | +0.186 |
Neg logit contributions | |
lor | -0.190 |
osc | -0.180 |
kit | -0.176 |
ests | -0.168 |
aj | -0.165 |
Token | behind |
Token ID | 2157 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
www | +0.090 |
Run | +0.088 |
ww | +0.084 |
ang | +0.075 |
opter | +0.074 |
Neg logit contributions | |
to | -0.044 |
lair | -0.042 |
tr | -0.042 |
fault | -0.042 |
dentist | -0.042 |
Token | him |
Token ID | 683 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Run | +0.063 |
www | +0.059 |
ww | +0.055 |
gust | +0.055 |
forth | +0.054 |
Neg logit contributions | |
dentist | -0.044 |
lair | -0.044 |
fault | -0.043 |
clinic | -0.043 |
lor | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
dentist | +0.028 |
lair | +0.027 |
ests | +0.027 |
lor | +0.027 |
clinic | +0.027 |
Neg logit contributions | |
Run | -0.023 |
www | -0.022 |
forth | -0.021 |
gust | -0.020 |
ww | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Run | +0.057 |
www | +0.055 |
ww | +0.052 |
gust | +0.048 |
izing | +0.046 |
Neg logit contributions | |
dentist | -0.050 |
lair | -0.048 |
fault | -0.046 |
wounds | -0.046 |
clinic | -0.045 |
Token | tired |
Token ID | 10032 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
Run | +0.030 |
www | +0.028 |
ww | +0.027 |
forth | +0.026 |
gust | +0.025 |
Neg logit contributions | |
dentist | -0.020 |
lair | -0.019 |
fault | -0.019 |
clinic | -0.019 |
parents | -0.018 |
Token | that |
Token ID | 326 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Run | +0.091 |
www | +0.088 |
ww | +0.082 |
forth | +0.080 |
gust | +0.078 |
Neg logit contributions | |
dentist | -0.058 |
fault | -0.056 |
lair | -0.055 |
clinic | -0.054 |
aid | -0.052 |
Token | they |
Token ID | 484 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
Run | +0.008 |
www | +0.008 |
ww | +0.007 |
forth | +0.007 |
gust | +0.007 |
Neg logit contributions | |
dentist | -0.010 |
lair | -0.010 |
fault | -0.010 |
clinic | -0.009 |
lor | -0.009 |
Token | all |
Token ID | 477 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
Run | +0.025 |
www | +0.024 |
ww | +0.023 |
forth | +0.022 |
gust | +0.022 |
Neg logit contributions | |
dentist | -0.018 |
lair | -0.018 |
fault | -0.017 |
clinic | -0.017 |
lor | -0.017 |
Token | just |
Token ID | 655 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
Run | +0.023 |
www | +0.022 |
ww | +0.021 |
gust | +0.020 |
forth | +0.020 |
Neg logit contributions | |
dentist | -0.019 |
lair | -0.019 |
fault | -0.018 |
clinic | -0.018 |
lor | -0.018 |
Token | flo |
Token ID | 5530 |
Feature activation | +9.25e+00 |
Pos logit contributions | |
Run | +0.025 |
www | +0.025 |
ww | +0.024 |
gust | +0.022 |
izing | +0.021 |
Neg logit contributions | |
fault | -0.017 |
lair | -0.017 |
dentist | -0.017 |
aid | -0.016 |
clinic | -0.016 |
Token | pped |
Token ID | 1496 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Run | +0.194 |
www | +0.194 |
ww | +0.178 |
gust | +0.174 |
boom | +0.163 |
Neg logit contributions | |
lor | -0.209 |
clinic | -0.190 |
wounds | -0.189 |
osc | -0.189 |
aj | -0.189 |
Token | down |
Token ID | 866 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Run | +0.055 |
www | +0.052 |
ww | +0.049 |
gust | +0.047 |
forth | +0.046 |
Neg logit contributions | |
fault | -0.044 |
dentist | -0.044 |
lair | -0.043 |
clinic | -0.042 |
lor | -0.041 |
Token | in |
Token ID | 287 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Run | +0.058 |
www | +0.055 |
ww | +0.051 |
forth | +0.051 |
gust | +0.051 |
Neg logit contributions | |
dentist | -0.044 |
lair | -0.043 |
fault | -0.042 |
clinic | -0.042 |
lor | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
Run | +0.052 |
www | +0.048 |
gust | +0.045 |
ww | +0.045 |
forth | +0.044 |
Neg logit contributions | |
dentist | -0.049 |
lair | -0.048 |
fault | -0.047 |
lor | -0.047 |
clinic | -0.047 |
Token | pond |
Token ID | 16723 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Run | +0.075 |
www | +0.072 |
ww | +0.066 |
forth | +0.064 |
gust | +0.062 |
Neg logit contributions | |
dentist | -0.073 |
clinic | -0.072 |
lair | -0.071 |
fault | -0.068 |
lor | -0.068 |
Token | came |
Token ID | 1625 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
Run | +0.028 |
www | +0.026 |
ww | +0.025 |
forth | +0.024 |
gust | +0.024 |
Neg logit contributions | |
dentist | -0.025 |
fault | -0.025 |
lair | -0.025 |
clinic | -0.024 |
ests | -0.024 |
Token | out |
Token ID | 503 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Run | +0.015 |
www | +0.014 |
ww | +0.013 |
forth | +0.013 |
gust | +0.013 |
Neg logit contributions | |
dentist | -0.010 |
lair | -0.010 |
fault | -0.010 |
clinic | -0.009 |
lor | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Run | +0.017 |
www | +0.016 |
ww | +0.015 |
forth | +0.014 |
gust | +0.014 |
Neg logit contributions | |
dentist | -0.015 |
lair | -0.015 |
fault | -0.015 |
clinic | -0.014 |
lor | -0.014 |
Token | perfect |
Token ID | 2818 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Run | +0.043 |
www | +0.040 |
gust | +0.037 |
ww | +0.037 |
forth | +0.037 |
Neg logit contributions | |
dentist | -0.036 |
ests | -0.036 |
lair | -0.035 |
fault | -0.035 |
lor | -0.035 |
Token | w |
Token ID | 266 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
Run | +0.056 |
www | +0.053 |
ww | +0.050 |
forth | +0.049 |
gust | +0.049 |
Neg logit contributions | |
dentist | -0.054 |
lair | -0.052 |
fault | -0.052 |
clinic | -0.051 |
lor | -0.051 |
Token | obb |
Token ID | 21963 |
Feature activation | +9.25e+00 |
Pos logit contributions | |
Run | +0.112 |
www | +0.098 |
forth | +0.096 |
ww | +0.091 |
gust | +0.088 |
Neg logit contributions | |
dentist | -0.112 |
fault | -0.112 |
lair | -0.111 |
lor | -0.111 |
ests | -0.109 |
Token | ly |
Token ID | 306 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Run | +0.219 |
www | +0.184 |
Uh | +0.181 |
gust | +0.171 |
ww | +0.166 |
Neg logit contributions | |
fault | -0.192 |
stitches | -0.177 |
dentist | -0.176 |
aj | -0.175 |
wounds | -0.174 |
Token | shapes |
Token ID | 15268 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Run | +0.076 |
www | +0.072 |
ww | +0.067 |
forth | +0.065 |
gust | +0.065 |
Neg logit contributions | |
dentist | -0.062 |
lair | -0.061 |
fault | -0.060 |
clinic | -0.059 |
lor | -0.059 |
Token | ! |
Token ID | 0 |
Feature activation | -4.62e-03 |
Pos logit contributions | |
Run | +0.028 |
www | +0.027 |
ww | +0.025 |
forth | +0.025 |
gust | +0.024 |
Neg logit contributions | |
dentist | -0.019 |
lair | -0.019 |
fault | -0.019 |
clinic | -0.018 |
lor | -0.018 |
Token | |
Token ID | 220 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
lair | +0.000 |
dentist | +0.000 |
wounds | +0.000 |
fault | +0.000 |
clinic | +0.000 |
Neg logit contributions | |
Run | -0.000 |
www | -0.000 |
ww | -0.000 |
gust | -0.000 |
ang | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
lair | +0.018 |
dentist | +0.017 |
wounds | +0.016 |
patients | +0.015 |
osc | +0.015 |
Neg logit contributions | |
Run | -0.017 |
ank | -0.016 |
www | -0.016 |
ang | -0.015 |
ww | -0.015 |
Token | It |
Token ID | 632 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
lair | +0.003 |
dentist | +0.003 |
fault | +0.003 |
lor | +0.003 |
clinic | +0.003 |
Neg logit contributions | |
Run | -0.007 |
www | -0.007 |
ww | -0.006 |
gust | -0.006 |
forth | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Run | +0.038 |
www | +0.036 |
ww | +0.035 |
gust | +0.034 |
forth | +0.033 |
Neg logit contributions | |
dentist | -0.016 |
lair | -0.015 |
fault | -0.015 |
tr | -0.014 |
clinic | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Run | +0.013 |
www | +0.013 |
ww | +0.012 |
forth | +0.011 |
gust | +0.011 |
Neg logit contributions | |
dentist | -0.007 |
lair | -0.007 |
fault | -0.007 |
clinic | -0.006 |
tr | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
dentist | +0.005 |
lair | +0.004 |
tr | +0.004 |
clinic | +0.004 |
fault | +0.004 |
Neg logit contributions | |
Run | -0.008 |
www | -0.008 |
dd | -0.007 |
forth | -0.007 |
ging | -0.007 |
Token | w |
Token ID | 266 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
Run | +0.090 |
www | +0.087 |
dd | +0.083 |
ww | +0.079 |
ging | +0.075 |
Neg logit contributions | |
dentist | -0.067 |
lair | -0.065 |
clinic | -0.063 |
fault | -0.063 |
tr | -0.062 |
Token | obb |
Token ID | 21963 |
Feature activation | +9.20e+00 |
Pos logit contributions | |
Run | +0.131 |
forth | +0.115 |
www | +0.111 |
ww | +0.106 |
gust | +0.103 |
Neg logit contributions | |
dentist | -0.101 |
ests | -0.097 |
fault | -0.097 |
lair | -0.091 |
clinic | -0.090 |
Token | ly |
Token ID | 306 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Run | +0.250 |
Uh | +0.216 |
www | +0.210 |
gust | +0.198 |
Jump | +0.190 |
Neg logit contributions | |
fault | -0.155 |
kit | -0.151 |
ache | -0.150 |
dentist | -0.142 |
osc | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Run | +0.077 |
www | +0.073 |
ww | +0.068 |
dd | +0.066 |
forth | +0.065 |
Neg logit contributions | |
dentist | -0.046 |
lair | -0.043 |
tr | -0.042 |
fault | -0.042 |
clinic | -0.042 |
Token | but |
Token ID | 475 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
www | +0.053 |
ww | +0.051 |
Run | +0.051 |
ang | +0.047 |
opter | +0.046 |
Neg logit contributions | |
dentist | -0.026 |
lair | -0.025 |
fault | -0.024 |
wounds | -0.023 |
tr | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
www | +0.094 |
Run | +0.092 |
ww | +0.089 |
plets | +0.083 |
AW | +0.082 |
Neg logit contributions | |
dentist | -0.046 |
not | -0.043 |
His | -0.041 |
parents | -0.041 |
fault | -0.040 |
Token | tried |
Token ID | 3088 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
Run | +0.020 |
www | +0.019 |
ww | +0.018 |
gust | +0.018 |
forth | +0.018 |
Neg logit contributions | |
dentist | -0.014 |
lair | -0.013 |
fault | -0.013 |
clinic | -0.013 |
lor | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
Run | +0.025 |
www | +0.024 |
forth | +0.023 |
ww | +0.023 |
gust | +0.022 |
Neg logit contributions | |
dentist | -0.017 |
lair | -0.017 |
lor | -0.017 |
clinic | -0.017 |
fault | -0.016 |
Token | too |
Token ID | 1165 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Run | +0.014 |
www | +0.013 |
gust | +0.012 |
ww | +0.012 |
forth | +0.012 |
Neg logit contributions | |
lor | -0.012 |
lair | -0.012 |
dentist | -0.012 |
fault | -0.011 |
clinic | -0.011 |
Token | small |
Token ID | 1402 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
Run | +0.077 |
forth | +0.073 |
www | +0.069 |
ging | +0.065 |
ww | +0.064 |
Neg logit contributions | |
dentist | -0.050 |
fault | -0.046 |
neys | -0.045 |
tr | -0.043 |
aj | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
Run | +0.067 |
www | +0.063 |
ww | +0.060 |
forth | +0.059 |
gust | +0.059 |
Neg logit contributions | |
dentist | -0.052 |
lair | -0.051 |
lor | -0.050 |
clinic | -0.050 |
fault | -0.049 |
Token | w |
Token ID | 266 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
Run | +0.089 |
www | +0.084 |
ww | +0.080 |
forth | +0.074 |
gust | +0.074 |
Neg logit contributions | |
dentist | -0.073 |
lair | -0.068 |
fault | -0.068 |
wounds | -0.066 |
clinic | -0.066 |
Token | obb |
Token ID | 21963 |
Feature activation | +9.16e+00 |
Pos logit contributions | |
Run | +0.106 |
www | +0.098 |
ww | +0.091 |
forth | +0.088 |
gust | +0.085 |
Neg logit contributions | |
dentist | -0.130 |
fault | -0.129 |
lair | -0.128 |
clinic | -0.124 |
ests | -0.124 |
Token | ly |
Token ID | 306 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Run | +0.197 |
www | +0.174 |
ww | +0.156 |
gust | +0.151 |
Uh | +0.151 |
Neg logit contributions | |
fault | -0.227 |
aj | -0.203 |
dentist | -0.202 |
osc | -0.201 |
kit | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Run | +0.043 |
www | +0.040 |
forth | +0.040 |
gust | +0.039 |
ww | +0.038 |
Neg logit contributions | |
lor | -0.038 |
dentist | -0.038 |
ests | -0.037 |
lair | -0.036 |
clinic | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Run | +0.006 |
www | +0.006 |
gust | +0.006 |
ww | +0.005 |
forth | +0.005 |
Neg logit contributions | |
lair | -0.006 |
lor | -0.005 |
fault | -0.005 |
ests | -0.005 |
dentist | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
Run | +0.008 |
www | +0.007 |
ww | +0.007 |
gust | +0.007 |
forth | +0.007 |
Neg logit contributions | |
dentist | -0.007 |
lair | -0.007 |
fault | -0.007 |
clinic | -0.007 |
lor | -0.007 |
Token | something |
Token ID | 1223 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
lor | +0.018 |
ests | +0.015 |
aj | +0.015 |
clinic | +0.015 |
ages | +0.014 |
Neg logit contributions | |
forth | -0.019 |
www | -0.018 |
gust | -0.018 |
Run | -0.018 |
boom | -0.018 |
Token | legs |
Token ID | 7405 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
lor | +0.020 |
ests | +0.018 |
dentist | +0.018 |
fault | +0.018 |
lair | +0.017 |
Neg logit contributions | |
Run | -0.024 |
www | -0.022 |
gust | -0.022 |
forth | -0.022 |
ww | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
Run | +0.076 |
www | +0.072 |
ww | +0.067 |
forth | +0.065 |
gust | +0.065 |
Neg logit contributions | |
dentist | -0.068 |
lair | -0.067 |
fault | -0.067 |
clinic | -0.065 |
lor | -0.065 |
Token | loose |
Token ID | 9155 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
Run | +0.006 |
gust | +0.005 |
forth | +0.005 |
www | +0.005 |
boom | +0.005 |
Neg logit contributions | |
lor | -0.006 |
ests | -0.006 |
dentist | -0.006 |
clinic | -0.006 |
fault | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Run | +0.124 |
www | +0.119 |
ww | +0.112 |
gust | +0.107 |
forth | +0.106 |
Neg logit contributions | |
dentist | -0.090 |
fault | -0.089 |
lair | -0.089 |
clinic | -0.085 |
lor | -0.084 |
Token | w |
Token ID | 266 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
Run | +0.062 |
www | +0.060 |
ww | +0.056 |
forth | +0.054 |
gust | +0.053 |
Neg logit contributions | |
dentist | -0.050 |
lair | -0.049 |
fault | -0.049 |
clinic | -0.047 |
wounds | -0.047 |
Token | obb |
Token ID | 21963 |
Feature activation | +9.14e+00 |
Pos logit contributions | |
Run | +0.117 |
www | +0.110 |
ww | +0.102 |
forth | +0.101 |
gust | +0.097 |
Neg logit contributions | |
dentist | -0.116 |
fault | -0.116 |
lair | -0.115 |
ests | -0.112 |
clinic | -0.112 |
Token | ly |
Token ID | 306 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Run | +0.204 |
www | +0.190 |
ww | +0.170 |
gust | +0.169 |
Uh | +0.167 |
Neg logit contributions | |
fault | -0.201 |
kit | -0.185 |
osc | -0.181 |
ache | -0.181 |
aj | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
Run | +0.056 |
www | +0.052 |
forth | +0.050 |
gust | +0.050 |
ww | +0.049 |
Neg logit contributions | |
dentist | -0.039 |
lor | -0.037 |
lair | -0.037 |
fault | -0.037 |
ests | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
lair | +0.008 |
fault | +0.007 |
lor | +0.007 |
dentist | +0.007 |
wounds | +0.007 |
Neg logit contributions | |
Run | -0.010 |
gust | -0.009 |
www | -0.008 |
ww | -0.008 |
Uh | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
lair | +0.010 |
fault | +0.009 |
dentist | +0.009 |
clinic | +0.009 |
lor | +0.008 |
Neg logit contributions | |
Run | -0.018 |
www | -0.017 |
ww | -0.016 |
gust | -0.015 |
ang | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Run | +0.030 |
gust | +0.029 |
forth | +0.029 |
ening | +0.029 |
www | +0.029 |
Neg logit contributions | |
aid | -0.026 |
dentist | -0.026 |
clinic | -0.026 |
lor | -0.025 |
Her | -0.025 |
Token | too |
Token ID | 1165 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Run | +0.007 |
www | +0.007 |
ww | +0.006 |
forth | +0.006 |
gust | +0.006 |
Neg logit contributions | |
dentist | -0.005 |
lair | -0.005 |
fault | -0.005 |
clinic | -0.004 |
lor | -0.004 |
Token | high |
Token ID | 1029 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
Run | +0.058 |
forth | +0.052 |
www | +0.052 |
heart | +0.049 |
ww | +0.049 |
Neg logit contributions | |
dentist | -0.036 |
fault | -0.035 |
truth | -0.031 |
neys | -0.031 |
lair | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
Run | +0.136 |
www | +0.131 |
ww | +0.123 |
gust | +0.119 |
forth | +0.115 |
Neg logit contributions | |
fault | -0.092 |
dentist | -0.090 |
lair | -0.089 |
clinic | -0.083 |
lor | -0.082 |
Token | too |
Token ID | 1165 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
www | +0.089 |
Run | +0.089 |
ww | +0.084 |
dd | +0.076 |
ang | +0.076 |
Neg logit contributions | |
dentist | -0.074 |
fault | -0.070 |
lair | -0.069 |
wounds | -0.066 |
heals | -0.065 |
Token | w |
Token ID | 266 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
Run | +0.070 |
www | +0.066 |
forth | +0.064 |
ww | +0.062 |
heart | +0.061 |
Neg logit contributions | |
dentist | -0.051 |
fault | -0.049 |
lair | -0.046 |
to | -0.045 |
neys | -0.044 |
Token | obb |
Token ID | 21963 |
Feature activation | +9.10e+00 |
Pos logit contributions | |
Run | +0.123 |
www | +0.115 |
ww | +0.108 |
forth | +0.103 |
gust | +0.099 |
Neg logit contributions | |
fault | -0.130 |
dentist | -0.129 |
lair | -0.128 |
clinic | -0.123 |
wounds | -0.122 |
Token | ly |
Token ID | 306 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Run | +0.183 |
www | +0.167 |
ww | +0.148 |
gust | +0.145 |
Uh | +0.140 |
Neg logit contributions | |
fault | -0.231 |
dentist | -0.209 |
aj | -0.205 |
lair | -0.204 |
wounds | -0.203 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Run | +0.052 |
www | +0.049 |
forth | +0.047 |
ww | +0.047 |
gust | +0.046 |
Neg logit contributions | |
dentist | -0.033 |
lair | -0.031 |
clinic | -0.031 |
ests | -0.031 |
lor | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Run | +0.052 |
www | +0.052 |
ww | +0.048 |
forth | +0.045 |
gust | +0.045 |
Neg logit contributions | |
fault | -0.038 |
dentist | -0.037 |
lair | -0.037 |
wounds | -0.035 |
clinic | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Run | +0.078 |
www | +0.076 |
ww | +0.072 |
forth | +0.067 |
gust | +0.066 |
Neg logit contributions | |
dentist | -0.066 |
lair | -0.064 |
fault | -0.063 |
wounds | -0.060 |
clinic | -0.060 |
Token | fell |
Token ID | 3214 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Run | +0.028 |
www | +0.027 |
ww | +0.025 |
gust | +0.023 |
forth | +0.023 |
Neg logit contributions | |
dentist | -0.026 |
lair | -0.025 |
fault | -0.024 |
tr | -0.024 |
wounds | -0.024 |
Token | she |
Token ID | 673 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
Run | +0.043 |
www | +0.041 |
ww | +0.038 |
gust | +0.036 |
forth | +0.036 |
Neg logit contributions | |
dentist | -0.036 |
fault | -0.034 |
lair | -0.034 |
clinic | -0.033 |
aid | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
Run | +0.017 |
www | +0.017 |
ww | +0.016 |
gust | +0.015 |
forth | +0.015 |
Neg logit contributions | |
dentist | -0.012 |
lair | -0.012 |
fault | -0.012 |
clinic | -0.012 |
lor | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
dentist | +0.011 |
lair | +0.011 |
fault | +0.011 |
clinic | +0.011 |
lor | +0.011 |
Neg logit contributions | |
Run | -0.015 |
www | -0.014 |
ww | -0.013 |
forth | -0.013 |
gust | -0.013 |
Token | little |
Token ID | 1310 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
Run | +0.005 |
www | +0.004 |
ww | +0.004 |
forth | +0.004 |
dd | +0.004 |
Neg logit contributions | |
dentist | -0.005 |
clinic | -0.004 |
lair | -0.004 |
aid | -0.004 |
fault | -0.004 |
Token | w |
Token ID | 266 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
Run | +0.082 |
www | +0.082 |
ww | +0.077 |
dd | +0.071 |
forth | +0.068 |
Neg logit contributions | |
clinic | -0.077 |
dentist | -0.076 |
fault | -0.075 |
lair | -0.074 |
doctor | -0.072 |
Token | obb |
Token ID | 21963 |
Feature activation | +9.04e+00 |
Pos logit contributions | |
Run | +0.097 |
www | +0.087 |
forth | +0.083 |
ww | +0.083 |
gust | +0.079 |
Neg logit contributions | |
fault | -0.110 |
dentist | -0.110 |
lair | -0.107 |
clinic | -0.107 |
ests | -0.106 |
Token | ly |
Token ID | 306 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Run | +0.217 |
www | +0.190 |
Uh | +0.189 |
gust | +0.178 |
ww | +0.176 |
Neg logit contributions | |
ache | -0.167 |
fault | -0.159 |
kit | -0.157 |
stitches | -0.151 |
osc | -0.150 |
Token | and |
Token ID | 290 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
Run | +0.059 |
www | +0.056 |
ww | +0.053 |
forth | +0.049 |
gust | +0.049 |
Neg logit contributions | |
dentist | -0.058 |
lair | -0.057 |
clinic | -0.057 |
fault | -0.057 |
aid | -0.055 |
Token | not |
Token ID | 407 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Run | +0.075 |
www | +0.071 |
ww | +0.067 |
gust | +0.062 |
forth | +0.062 |
Neg logit contributions | |
dentist | -0.064 |
lair | -0.061 |
fault | -0.061 |
clinic | -0.060 |
wounds | -0.058 |
Token | sure |
Token ID | 1654 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Run | +0.061 |
www | +0.057 |
ww | +0.054 |
forth | +0.051 |
gust | +0.051 |
Neg logit contributions | |
dentist | -0.057 |
fault | -0.056 |
lair | -0.056 |
clinic | -0.054 |
lor | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
dentist | +0.020 |
lair | +0.020 |
clinic | +0.019 |
lor | +0.019 |
ests | +0.018 |
Neg logit contributions | |
Run | -0.034 |
www | -0.033 |
ww | -0.031 |
gust | -0.030 |
forth | -0.030 |
Token | blocks |
Token ID | 7021 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Run | +0.006 |
www | +0.005 |
gust | +0.005 |
forth | +0.005 |
ww | +0.005 |
Neg logit contributions | |
lor | -0.004 |
fault | -0.004 |
lair | -0.004 |
dentist | -0.004 |
clinic | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
Run | +0.044 |
www | +0.042 |
ww | +0.039 |
forth | +0.039 |
gust | +0.038 |
Neg logit contributions | |
dentist | -0.034 |
lair | -0.034 |
fault | -0.033 |
lor | -0.033 |
clinic | -0.032 |
Token | loose |
Token ID | 9155 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
Run | +0.020 |
www | +0.018 |
ww | +0.017 |
forth | +0.017 |
gust | +0.017 |
Neg logit contributions | |
dentist | -0.019 |
lair | -0.018 |
fault | -0.018 |
clinic | -0.018 |
lor | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Run | +0.120 |
www | +0.115 |
ww | +0.108 |
gust | +0.104 |
forth | +0.104 |
Neg logit contributions | |
dentist | -0.093 |
lair | -0.092 |
fault | -0.091 |
clinic | -0.089 |
lor | -0.087 |
Token | w |
Token ID | 266 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
Run | +0.055 |
www | +0.053 |
ww | +0.049 |
forth | +0.047 |
gust | +0.047 |
Neg logit contributions | |
dentist | -0.047 |
lair | -0.045 |
fault | -0.045 |
clinic | -0.044 |
wounds | -0.044 |
Token | obb |
Token ID | 21963 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
Run | +0.103 |
www | +0.096 |
ww | +0.089 |
forth | +0.087 |
gust | +0.085 |
Neg logit contributions | |
dentist | -0.122 |
fault | -0.120 |
lair | -0.120 |
clinic | -0.116 |
ests | -0.116 |
Token | ly |
Token ID | 306 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Run | +0.190 |
www | +0.175 |
ww | +0.158 |
gust | +0.155 |
Uh | +0.150 |
Neg logit contributions | |
fault | -0.211 |
kit | -0.195 |
dentist | -0.193 |
aj | -0.191 |
wounds | -0.191 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
Run | +0.050 |
www | +0.045 |
forth | +0.044 |
gust | +0.044 |
ww | +0.042 |
Neg logit contributions | |
dentist | -0.036 |
lor | -0.036 |
lair | -0.035 |
fault | -0.035 |
ests | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Run | +0.001 |
gust | +0.001 |
www | +0.001 |
boom | +0.001 |
ww | +0.001 |
Neg logit contributions | |
lair | -0.001 |
lor | -0.001 |
dentist | -0.001 |
wounds | -0.000 |
osc | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
fault | +0.011 |
lair | +0.010 |
dentist | +0.010 |
lor | +0.010 |
osc | +0.009 |
Neg logit contributions | |
Run | -0.019 |
www | -0.017 |
ww | -0.016 |
gust | -0.016 |
boom | -0.016 |
Token | When |
Token ID | 2215 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
gust | +0.034 |
ening | +0.034 |
forth | +0.034 |
www | +0.033 |
Run | +0.033 |
Neg logit contributions | |
aid | -0.026 |
clinic | -0.026 |
dentist | -0.025 |
wounds | -0.024 |
lor | -0.024 |
Token | Jill |
Token ID | 22772 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
dentist | +0.019 |
lair | +0.019 |
fault | +0.018 |
clinic | +0.018 |
lor | +0.018 |
Neg logit contributions | |
Run | -0.016 |
www | -0.015 |
ww | -0.014 |
forth | -0.013 |
gust | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Run | +0.026 |
www | +0.025 |
ww | +0.023 |
forth | +0.023 |
gust | +0.023 |
Neg logit contributions | |
dentist | -0.020 |
lair | -0.019 |
fault | -0.019 |
clinic | -0.019 |
lor | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
dentist | +0.039 |
lair | +0.038 |
lor | +0.038 |
fault | +0.037 |
ests | +0.037 |
Neg logit contributions | |
Run | -0.028 |
www | -0.026 |
forth | -0.025 |
gust | -0.024 |
ww | -0.023 |
Token | as |
Token ID | 355 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
dentist | +0.037 |
lair | +0.037 |
clinic | +0.036 |
aid | +0.036 |
wounds | +0.035 |
Neg logit contributions | |
www | -0.050 |
Run | -0.049 |
ww | -0.048 |
gust | -0.042 |
forth | -0.042 |
Token | she |
Token ID | 673 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
Run | +0.013 |
www | +0.013 |
ww | +0.012 |
forth | +0.011 |
gust | +0.011 |
Neg logit contributions | |
dentist | -0.010 |
fault | -0.010 |
lair | -0.009 |
parents | -0.009 |
clinic | -0.009 |
Token | flo |
Token ID | 5530 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
Run | +0.002 |
www | +0.002 |
ww | +0.002 |
forth | +0.002 |
gust | +0.002 |
Neg logit contributions | |
dentist | -0.002 |
fault | -0.002 |
lair | -0.002 |
clinic | -0.002 |
lor | -0.002 |
Token | pped |
Token ID | 1496 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Run | +0.178 |
www | +0.176 |
ww | +0.164 |
gust | +0.158 |
boom | +0.149 |
Neg logit contributions | |
lor | -0.207 |
dentist | -0.202 |
kit | -0.201 |
clinic | -0.200 |
osc | -0.200 |
Token | on |
Token ID | 319 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
www | +0.063 |
Run | +0.060 |
ww | +0.059 |
opter | +0.051 |
izing | +0.051 |
Neg logit contributions | |
dentist | -0.036 |
lair | -0.035 |
fault | -0.035 |
aid | -0.033 |
kit | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Run | +0.050 |
www | +0.046 |
gust | +0.043 |
ww | +0.043 |
forth | +0.043 |
Neg logit contributions | |
dentist | -0.046 |
lair | -0.045 |
fault | -0.044 |
lor | -0.044 |
clinic | -0.044 |
Token | grass |
Token ID | 8701 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Run | +0.041 |
www | +0.041 |
heart | +0.040 |
ww | +0.039 |
Uh | +0.037 |
Neg logit contributions | |
wounds | -0.030 |
dentist | -0.029 |
lair | -0.027 |
address | -0.026 |
aid | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Run | +0.035 |
www | +0.034 |
ww | +0.032 |
forth | +0.031 |
gust | +0.031 |
Neg logit contributions | |
dentist | -0.019 |
lair | -0.019 |
fault | -0.019 |
clinic | -0.018 |
lor | -0.018 |
Token | pictures |
Token ID | 5986 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Run | +0.003 |
www | +0.003 |
gust | +0.003 |
ww | +0.003 |
forth | +0.003 |
Neg logit contributions | |
lor | -0.003 |
lair | -0.003 |
fault | -0.003 |
dentist | -0.003 |
clinic | -0.003 |
Token | on |
Token ID | 319 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
Run | +0.047 |
www | +0.045 |
ww | +0.043 |
forth | +0.041 |
gust | +0.040 |
Neg logit contributions | |
dentist | -0.028 |
lair | -0.027 |
fault | -0.027 |
clinic | -0.026 |
ests | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
Run | +0.079 |
www | +0.074 |
ww | +0.069 |
gust | +0.068 |
forth | +0.067 |
Neg logit contributions | |
lair | -0.075 |
dentist | -0.075 |
fault | -0.074 |
clinic | -0.072 |
lor | -0.072 |
Token | walls |
Token ID | 7714 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Run | +0.016 |
www | +0.015 |
ww | +0.014 |
forth | +0.014 |
gust | +0.014 |
Neg logit contributions | |
dentist | -0.013 |
lair | -0.013 |
fault | -0.013 |
lor | -0.013 |
clinic | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Run | +0.054 |
www | +0.051 |
ww | +0.047 |
gust | +0.047 |
forth | +0.047 |
Neg logit contributions | |
dentist | -0.043 |
lair | -0.042 |
fault | -0.041 |
clinic | -0.041 |
lor | -0.041 |
Token | ratt |
Token ID | 27263 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
Run | +0.025 |
www | +0.024 |
gust | +0.022 |
forth | +0.022 |
ww | +0.022 |
Neg logit contributions | |
dentist | -0.026 |
lor | -0.026 |
ests | -0.025 |
lair | -0.025 |
clinic | -0.025 |
Token | ling |
Token ID | 1359 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
Run | +0.221 |
www | +0.208 |
ww | +0.199 |
Uh | +0.179 |
Jump | +0.175 |
Neg logit contributions | |
ows | -0.159 |
ers | -0.157 |
wounds | -0.156 |
feelings | -0.152 |
iddles | -0.148 |
Token | but |
Token ID | 475 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Run | +0.087 |
www | +0.087 |
ww | +0.082 |
gust | +0.075 |
forth | +0.075 |
Neg logit contributions | |
lair | -0.052 |
fault | -0.051 |
dentist | -0.051 |
clinic | -0.048 |
wounds | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Run | +0.068 |
www | +0.066 |
ww | +0.062 |
gust | +0.058 |
forth | +0.058 |
Neg logit contributions | |
dentist | -0.055 |
fault | -0.055 |
lair | -0.054 |
clinic | -0.052 |
wounds | -0.052 |
Token | soon |
Token ID | 2582 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
Run | +0.028 |
www | +0.025 |
forth | +0.024 |
gust | +0.024 |
ww | +0.024 |
Neg logit contributions | |
dentist | -0.025 |
lair | -0.025 |
fault | -0.024 |
lor | -0.024 |
clinic | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Run | +0.089 |
www | +0.082 |
gust | +0.077 |
ww | +0.077 |
forth | +0.076 |
Neg logit contributions | |
dentist | -0.097 |
lair | -0.097 |
fault | -0.096 |
clinic | -0.095 |
lor | -0.095 |
Token | on |
Token ID | 319 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
dentist | +0.046 |
lair | +0.045 |
fault | +0.045 |
ests | +0.044 |
clinic | +0.043 |
Neg logit contributions | |
Run | -0.061 |
www | -0.058 |
ww | -0.054 |
gust | -0.052 |
forth | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Run | +0.045 |
www | +0.043 |
ww | +0.040 |
forth | +0.039 |
gust | +0.039 |
Neg logit contributions | |
dentist | -0.034 |
lair | -0.033 |
fault | -0.033 |
clinic | -0.032 |
lor | -0.032 |
Token | laughed |
Token ID | 13818 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
Run | +0.048 |
www | +0.046 |
ww | +0.043 |
gust | +0.041 |
forth | +0.041 |
Neg logit contributions | |
dentist | -0.041 |
lair | -0.040 |
fault | -0.039 |
clinic | -0.039 |
ests | -0.038 |
Token | as |
Token ID | 355 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Run | +0.025 |
www | +0.024 |
ww | +0.023 |
forth | +0.022 |
gust | +0.022 |
Neg logit contributions | |
dentist | -0.016 |
lair | -0.016 |
fault | -0.016 |
clinic | -0.016 |
lor | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Run | +0.000 |
www | +0.000 |
ww | +0.000 |
forth | +0.000 |
gust | +0.000 |
Neg logit contributions | |
dentist | -0.000 |
lair | -0.000 |
fault | -0.000 |
clinic | -0.000 |
ests | -0.000 |
Token | flo |
Token ID | 5530 |
Feature activation | +8.97e+00 |
Pos logit contributions | |
Run | +0.062 |
www | +0.060 |
ww | +0.057 |
gust | +0.055 |
izing | +0.053 |
Neg logit contributions | |
dentist | -0.035 |
ests | -0.034 |
lair | -0.034 |
clinic | -0.032 |
fault | -0.032 |
Token | pped |
Token ID | 1496 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Run | +0.171 |
www | +0.170 |
ww | +0.154 |
gust | +0.153 |
boom | +0.141 |
Neg logit contributions | |
lor | -0.217 |
clinic | -0.210 |
osc | -0.208 |
ests | -0.208 |
wounds | -0.207 |
Token | around |
Token ID | 1088 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Run | +0.051 |
www | +0.048 |
ww | +0.045 |
gust | +0.043 |
forth | +0.043 |
Neg logit contributions | |
dentist | -0.048 |
lair | -0.047 |
fault | -0.047 |
clinic | -0.046 |
lor | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Run | +0.050 |
www | +0.047 |
ww | +0.044 |
forth | +0.044 |
gust | +0.043 |
Neg logit contributions | |
dentist | -0.038 |
lair | -0.037 |
fault | -0.037 |
lor | -0.036 |
clinic | -0.036 |
Token | Then |
Token ID | 3244 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
dentist | +0.002 |
lair | +0.002 |
lor | +0.002 |
fault | +0.002 |
wounds | +0.002 |
Neg logit contributions | |
Run | -0.003 |
www | -0.003 |
gust | -0.003 |
ww | -0.003 |
forth | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Run | +0.092 |
www | +0.091 |
ww | +0.084 |
ang | +0.081 |
Uh | +0.077 |
Neg logit contributions | |
dentist | -0.062 |
parents | -0.062 |
patients | -0.057 |
clinic | -0.057 |
office | -0.056 |
Token | car |
Token ID | 1097 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
lor | +0.002 |
lair | +0.002 |
fault | +0.002 |
dentist | +0.002 |
ests | +0.002 |
Neg logit contributions | |
Run | -0.002 |
www | -0.002 |
gust | -0.002 |
forth | -0.002 |
ww | -0.002 |
Token | went |
Token ID | 1816 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Run | +0.007 |
www | +0.007 |
forth | +0.006 |
ww | +0.006 |
gust | +0.006 |
Neg logit contributions | |
dentist | -0.007 |
fault | -0.007 |
lair | -0.007 |
lor | -0.007 |
clinic | -0.007 |
Token | slow |
Token ID | 3105 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
Run | +0.069 |
www | +0.068 |
ww | +0.064 |
gust | +0.058 |
dd | +0.057 |
Neg logit contributions | |
dentist | -0.056 |
lair | -0.054 |
clinic | -0.053 |
fault | -0.053 |
kit | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
Run | +0.124 |
www | +0.120 |
ww | +0.113 |
gust | +0.106 |
Uh | +0.101 |
Neg logit contributions | |
fault | -0.072 |
lair | -0.066 |
dentist | -0.065 |
wounds | -0.063 |
clinic | -0.063 |
Token | w |
Token ID | 266 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
www | +0.071 |
Run | +0.071 |
ww | +0.067 |
heart | +0.058 |
dd | +0.058 |
Neg logit contributions | |
dentist | -0.068 |
fault | -0.065 |
wounds | -0.064 |
lair | -0.064 |
heals | -0.063 |
Token | obb |
Token ID | 21963 |
Feature activation | +8.94e+00 |
Pos logit contributions | |
Run | +0.127 |
www | +0.120 |
ww | +0.112 |
forth | +0.111 |
gust | +0.108 |
Neg logit contributions | |
dentist | -0.097 |
fault | -0.096 |
lair | -0.095 |
ests | -0.095 |
clinic | -0.093 |
Token | ly |
Token ID | 306 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Run | +0.202 |
www | +0.182 |
gust | +0.169 |
Uh | +0.166 |
ww | +0.160 |
Neg logit contributions | |
fault | -0.187 |
kit | -0.176 |
ages | -0.174 |
ests | -0.174 |
aj | -0.173 |
Token | . |
Token ID | 13 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
Run | +0.046 |
www | +0.042 |
gust | +0.041 |
forth | +0.040 |
ww | +0.040 |
Neg logit contributions | |
dentist | -0.037 |
lair | -0.035 |
lor | -0.035 |
fault | -0.035 |
ests | -0.034 |
Token | She |
Token ID | 1375 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Run | +0.014 |
gust | +0.014 |
www | +0.012 |
ww | +0.011 |
boom | +0.011 |
Neg logit contributions | |
lair | -0.016 |
lor | -0.016 |
dentist | -0.015 |
osc | -0.015 |
wounds | -0.015 |
Token | felt |
Token ID | 2936 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Run | +0.002 |
www | +0.002 |
ww | +0.002 |
gust | +0.002 |
forth | +0.002 |
Neg logit contributions | |
dentist | -0.002 |
lair | -0.002 |
fault | -0.002 |
clinic | -0.002 |
lor | -0.002 |
Token | confused |
Token ID | 10416 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Run | +0.080 |
www | +0.078 |
ww | +0.073 |
forth | +0.070 |
gust | +0.068 |
Neg logit contributions | |
dentist | -0.064 |
fault | -0.063 |
lair | -0.062 |
clinic | -0.061 |
wounds | -0.060 |
Token | still |
Token ID | 991 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Run | +0.013 |
www | +0.013 |
ww | +0.012 |
forth | +0.012 |
gust | +0.011 |
Neg logit contributions | |
dentist | -0.010 |
fault | -0.010 |
lair | -0.010 |
clinic | -0.009 |
lor | -0.009 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Run | +0.024 |
www | +0.023 |
forth | +0.022 |
ww | +0.021 |
gust | +0.021 |
Neg logit contributions | |
dentist | -0.022 |
lair | -0.021 |
lor | -0.021 |
ests | -0.021 |
fault | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Run | +0.063 |
www | +0.060 |
ww | +0.056 |
gust | +0.055 |
forth | +0.054 |
Neg logit contributions | |
dentist | -0.058 |
lair | -0.058 |
fault | -0.057 |
lor | -0.056 |
clinic | -0.055 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
Run | +0.018 |
www | +0.016 |
forth | +0.015 |
ww | +0.015 |
ang | +0.014 |
Neg logit contributions | |
dentist | -0.012 |
aid | -0.012 |
clinic | -0.012 |
stomach | -0.011 |
grandmother | -0.011 |
Token | w |
Token ID | 266 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
Run | +0.096 |
www | +0.091 |
ww | +0.085 |
forth | +0.083 |
gust | +0.078 |
Neg logit contributions | |
fault | -0.081 |
dentist | -0.080 |
lair | -0.079 |
clinic | -0.078 |
wounds | -0.075 |
Token | obb |
Token ID | 21963 |
Feature activation | +8.92e+00 |
Pos logit contributions | |
Run | +0.107 |
www | +0.098 |
ww | +0.092 |
forth | +0.090 |
gust | +0.087 |
Neg logit contributions | |
dentist | -0.118 |
fault | -0.117 |
lair | -0.116 |
clinic | -0.114 |
lor | -0.113 |
Token | ly |
Token ID | 306 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Run | +0.199 |
www | +0.174 |
gust | +0.159 |
Uh | +0.157 |
ww | +0.157 |
Neg logit contributions | |
fault | -0.196 |
ache | -0.188 |
osc | -0.179 |
dentist | -0.176 |
kit | -0.175 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Run | +0.046 |
www | +0.043 |
ww | +0.040 |
forth | +0.040 |
gust | +0.040 |
Neg logit contributions | |
dentist | -0.047 |
lair | -0.046 |
fault | -0.045 |
lor | -0.045 |
ests | -0.044 |
Token | so |
Token ID | 523 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Run | +0.029 |
www | +0.027 |
ww | +0.025 |
forth | +0.025 |
gust | +0.025 |
Neg logit contributions | |
dentist | -0.032 |
lair | -0.031 |
fault | -0.031 |
clinic | -0.030 |
lor | -0.030 |
Token | she |
Token ID | 673 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
Run | +0.034 |
www | +0.033 |
ww | +0.031 |
forth | +0.030 |
gust | +0.030 |
Neg logit contributions | |
dentist | -0.036 |
lair | -0.036 |
fault | -0.035 |
clinic | -0.035 |
lor | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Run | +0.014 |
www | +0.013 |
ww | +0.012 |
forth | +0.012 |
gust | +0.012 |
Neg logit contributions | |
dentist | -0.012 |
lair | -0.012 |
fault | -0.012 |
clinic | -0.012 |
lor | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Run | +0.021 |
www | +0.020 |
ww | +0.018 |
gust | +0.018 |
forth | +0.018 |
Neg logit contributions | |
dentist | -0.022 |
lair | -0.022 |
fault | -0.022 |
clinic | -0.022 |
lor | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
Run | +0.032 |
www | +0.030 |
ww | +0.028 |
forth | +0.028 |
gust | +0.028 |
Neg logit contributions | |
lair | -0.023 |
dentist | -0.022 |
fault | -0.022 |
clinic | -0.022 |
lor | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
Run | +0.020 |
www | +0.019 |
ww | +0.018 |
forth | +0.017 |
gust | +0.017 |
Neg logit contributions | |
dentist | -0.016 |
lair | -0.016 |
fault | -0.016 |
clinic | -0.016 |
lor | -0.015 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
dentist | +0.002 |
fault | +0.001 |
lair | +0.001 |
clinic | +0.001 |
aid | +0.001 |
Neg logit contributions | |
Run | -0.002 |
www | -0.002 |
forth | -0.001 |
ww | -0.001 |
ang | -0.001 |
Token | w |
Token ID | 266 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
Run | +0.110 |
www | +0.107 |
ww | +0.099 |
forth | +0.094 |
dd | +0.093 |
Neg logit contributions | |
dentist | -0.077 |
fault | -0.076 |
truth | -0.073 |
stitches | -0.073 |
clinic | -0.072 |
Token | obb |
Token ID | 21963 |
Feature activation | +8.91e+00 |
Pos logit contributions | |
Run | +0.114 |
www | +0.103 |
ww | +0.097 |
forth | +0.096 |
gust | +0.091 |
Neg logit contributions | |
dentist | -0.122 |
fault | -0.120 |
lair | -0.117 |
ests | -0.115 |
lor | -0.115 |
Token | ly |
Token ID | 306 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Run | +0.196 |
www | +0.176 |
Uh | +0.157 |
ww | +0.157 |
gust | +0.153 |
Neg logit contributions | |
fault | -0.206 |
dentist | -0.193 |
ache | -0.189 |
kit | -0.187 |
osc | -0.183 |
Token | . |
Token ID | 13 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Run | +0.037 |
www | +0.035 |
forth | +0.033 |
ww | +0.033 |
gust | +0.033 |
Neg logit contributions | |
dentist | -0.026 |
lair | -0.026 |
lor | -0.026 |
fault | -0.026 |
ests | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
lair | +0.012 |
wounds | +0.011 |
fault | +0.011 |
lor | +0.011 |
dentist | +0.011 |
Neg logit contributions | |
Run | -0.015 |
www | -0.014 |
gust | -0.014 |
ww | -0.014 |
forth | -0.013 |
Token | continued |
Token ID | 3767 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Run | +0.029 |
www | +0.029 |
ww | +0.027 |
gust | +0.026 |
forth | +0.024 |
Neg logit contributions | |
dentist | -0.022 |
lair | -0.021 |
clinic | -0.020 |
fault | -0.020 |
wounds | -0.020 |
Token | their |
Token ID | 511 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
Run | +0.013 |
www | +0.013 |
ww | +0.012 |
forth | +0.012 |
gust | +0.012 |
Neg logit contributions | |
dentist | -0.005 |
lair | -0.005 |
fault | -0.005 |
clinic | -0.005 |
lor | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
Run | +0.019 |
www | +0.018 |
ww | +0.017 |
gust | +0.017 |
forth | +0.017 |
Neg logit contributions | |
dentist | -0.012 |
fault | -0.012 |
lair | -0.012 |
clinic | -0.012 |
wounds | -0.011 |
Token | too |
Token ID | 1165 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
Run | +0.019 |
www | +0.019 |
ww | +0.018 |
dd | +0.016 |
forth | +0.016 |
Neg logit contributions | |
dentist | -0.012 |
fault | -0.012 |
lair | -0.012 |
wounds | -0.011 |
tr | -0.011 |
Token | tall |
Token ID | 7331 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
Run | +0.082 |
forth | +0.077 |
www | +0.076 |
heart | +0.075 |
ening | +0.072 |
Neg logit contributions | |
dentist | -0.050 |
fault | -0.046 |
to | -0.046 |
truth | -0.045 |
neys | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
Run | +0.080 |
www | +0.076 |
ww | +0.072 |
forth | +0.071 |
gust | +0.070 |
Neg logit contributions | |
dentist | -0.050 |
lair | -0.048 |
lor | -0.048 |
clinic | -0.047 |
fault | -0.047 |
Token | w |
Token ID | 266 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
Run | +0.085 |
www | +0.084 |
ww | +0.079 |
dd | +0.076 |
ging | +0.074 |
Neg logit contributions | |
dentist | -0.066 |
fault | -0.063 |
wounds | -0.062 |
heals | -0.061 |
lair | -0.061 |
Token | obb |
Token ID | 21963 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
Run | +0.103 |
www | +0.096 |
ww | +0.089 |
forth | +0.085 |
gust | +0.083 |
Neg logit contributions | |
dentist | -0.124 |
fault | -0.123 |
lair | -0.122 |
clinic | -0.119 |
ests | -0.117 |
Token | ly |
Token ID | 306 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Run | +0.178 |
www | +0.163 |
ww | +0.145 |
gust | +0.144 |
Uh | +0.138 |
Neg logit contributions | |
fault | -0.216 |
dentist | -0.200 |
wounds | -0.198 |
heals | -0.195 |
kit | -0.195 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Run | +0.033 |
www | +0.030 |
forth | +0.030 |
gust | +0.029 |
ww | +0.028 |
Neg logit contributions | |
dentist | -0.022 |
lor | -0.022 |
ests | -0.022 |
lair | -0.021 |
clinic | -0.021 |
Token | The |
Token ID | 383 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Run | +0.006 |
gust | +0.005 |
www | +0.005 |
ww | +0.005 |
Uh | +0.004 |
Neg logit contributions | |
lair | -0.004 |
dentist | -0.004 |
lor | -0.004 |
osc | -0.004 |
wounds | -0.004 |
Token | blocks |
Token ID | 7021 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Run | +0.004 |
www | +0.004 |
ww | +0.004 |
forth | +0.004 |
gust | +0.004 |
Neg logit contributions | |
dentist | -0.003 |
lair | -0.003 |
fault | -0.003 |
clinic | -0.003 |
lor | -0.003 |
Token | fall |
Token ID | 2121 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
Run | +0.033 |
www | +0.032 |
ww | +0.030 |
gust | +0.027 |
forth | +0.027 |
Neg logit contributions | |
dentist | -0.029 |
fault | -0.029 |
lair | -0.029 |
wounds | -0.028 |
clinic | -0.028 |
Token | from |
Token ID | 422 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Run | +0.083 |
www | +0.079 |
ww | +0.074 |
forth | +0.072 |
gust | +0.071 |
Neg logit contributions | |
dentist | -0.061 |
fault | -0.058 |
lair | -0.057 |
clinic | -0.056 |
lor | -0.054 |
Token | running |
Token ID | 2491 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
dentist | +0.010 |
lair | +0.010 |
fault | +0.010 |
lor | +0.009 |
clinic | +0.009 |
Neg logit contributions | |
Run | -0.011 |
www | -0.010 |
ww | -0.010 |
forth | -0.010 |
gust | -0.009 |
Token | around |
Token ID | 1088 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Run | +0.086 |
www | +0.083 |
ww | +0.078 |
gust | +0.073 |
forth | +0.073 |
Neg logit contributions | |
lair | -0.066 |
fault | -0.066 |
dentist | -0.066 |
clinic | -0.065 |
wounds | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Run | +0.027 |
www | +0.026 |
ww | +0.024 |
forth | +0.024 |
gust | +0.024 |
Neg logit contributions | |
dentist | -0.024 |
lair | -0.023 |
fault | -0.023 |
clinic | -0.022 |
lor | -0.022 |
Token | he |
Token ID | 339 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Run | +0.043 |
www | +0.041 |
ww | +0.038 |
forth | +0.038 |
gust | +0.037 |
Neg logit contributions | |
dentist | -0.040 |
lair | -0.039 |
fault | -0.039 |
lor | -0.038 |
clinic | -0.038 |
Token | flo |
Token ID | 5530 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
Run | +0.004 |
www | +0.004 |
ww | +0.003 |
forth | +0.003 |
gust | +0.003 |
Neg logit contributions | |
dentist | -0.004 |
fault | -0.003 |
lair | -0.003 |
lor | -0.003 |
clinic | -0.003 |
Token | pped |
Token ID | 1496 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Run | +0.175 |
www | +0.167 |
ww | +0.155 |
gust | +0.152 |
boom | +0.143 |
Neg logit contributions | |
lor | -0.209 |
clinic | -0.198 |
osc | -0.197 |
wounds | -0.195 |
kit | -0.194 |
Token | down |
Token ID | 866 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Run | +0.046 |
www | +0.045 |
ww | +0.042 |
gust | +0.039 |
forth | +0.038 |
Neg logit contributions | |
dentist | -0.036 |
lair | -0.036 |
fault | -0.036 |
clinic | -0.034 |
wounds | -0.034 |
Token | next |
Token ID | 1306 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Run | +0.056 |
www | +0.053 |
ww | +0.050 |
forth | +0.049 |
gust | +0.049 |
Neg logit contributions | |
dentist | -0.049 |
lair | -0.048 |
fault | -0.047 |
clinic | -0.046 |
lor | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Run | +0.017 |
www | +0.016 |
ww | +0.015 |
forth | +0.015 |
gust | +0.015 |
Neg logit contributions | |
dentist | -0.005 |
lair | -0.005 |
fault | -0.005 |
lor | -0.005 |
clinic | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
dentist | +0.034 |
lair | +0.034 |
fault | +0.034 |
lor | +0.034 |
ests | +0.033 |
Neg logit contributions | |
Run | -0.039 |
www | -0.036 |
forth | -0.034 |
gust | -0.034 |
ww | -0.033 |
Token | that |
Token ID | 326 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
lor | +0.012 |
lair | +0.011 |
ests | +0.011 |
clinic | +0.011 |
aj | +0.011 |
Neg logit contributions | |
Run | -0.010 |
gust | -0.010 |
forth | -0.009 |
www | -0.009 |
boom | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
lor | +0.002 |
lair | +0.002 |
clinic | +0.002 |
fault | +0.002 |
ests | +0.002 |
Neg logit contributions | |
Run | -0.003 |
www | -0.002 |
gust | -0.002 |
forth | -0.002 |
ww | -0.002 |
Token | tower |
Token ID | 10580 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
lor | +0.073 |
clinic | +0.064 |
ests | +0.064 |
osc | +0.063 |
dentist | +0.063 |
Neg logit contributions | |
Run | -0.069 |
gust | -0.067 |
forth | -0.066 |
www | -0.063 |
boom | -0.063 |
Token | was |
Token ID | 373 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
dentist | +0.004 |
lair | +0.004 |
fault | +0.004 |
lor | +0.004 |
clinic | +0.004 |
Neg logit contributions | |
Run | -0.007 |
www | -0.007 |
forth | -0.006 |
ww | -0.006 |
gust | -0.006 |
Token | w |
Token ID | 266 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
Run | +0.021 |
www | +0.020 |
ww | +0.019 |
forth | +0.017 |
gust | +0.017 |
Neg logit contributions | |
dentist | -0.018 |
lair | -0.018 |
fault | -0.018 |
clinic | -0.017 |
wounds | -0.016 |
Token | obb |
Token ID | 21963 |
Feature activation | +8.73e+00 |
Pos logit contributions | |
Run | +0.131 |
www | +0.119 |
ww | +0.112 |
forth | +0.110 |
gust | +0.103 |
Neg logit contributions | |
dentist | -0.110 |
fault | -0.106 |
ests | -0.105 |
lair | -0.104 |
wounds | -0.102 |
Token | ly |
Token ID | 306 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Run | +0.191 |
www | +0.176 |
ww | +0.157 |
gust | +0.154 |
Uh | +0.151 |
Neg logit contributions | |
fault | -0.206 |
dentist | -0.194 |
kit | -0.188 |
wounds | -0.185 |
lair | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Run | +0.068 |
www | +0.065 |
ww | +0.061 |
forth | +0.060 |
gust | +0.060 |
Neg logit contributions | |
dentist | -0.041 |
lair | -0.040 |
fault | -0.040 |
clinic | -0.039 |
lor | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
Run | +0.006 |
gust | +0.005 |
www | +0.005 |
Wow | +0.005 |
ww | +0.005 |
Neg logit contributions | |
lair | -0.005 |
lor | -0.005 |
wounds | -0.005 |
clinic | -0.005 |
fault | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
fault | +0.012 |
lair | +0.011 |
lor | +0.011 |
patients | +0.011 |
clinic | +0.011 |
Neg logit contributions | |
Run | -0.014 |
www | -0.013 |
boom | -0.012 |
ang | -0.012 |
gust | -0.012 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
Run | +0.039 |
www | +0.037 |
gust | +0.035 |
forth | +0.035 |
ww | +0.034 |
Neg logit contributions | |
dentist | -0.036 |
clinic | -0.035 |
lair | -0.034 |
lor | -0.034 |
aid | -0.034 |
Token | but |
Token ID | 475 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Run | +0.014 |
www | +0.014 |
ww | +0.013 |
gust | +0.012 |
forth | +0.012 |
Neg logit contributions | |
dentist | -0.013 |
fault | -0.012 |
lair | -0.012 |
clinic | -0.012 |
wounds | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Run | +0.054 |
www | +0.053 |
ww | +0.050 |
gust | +0.044 |
forth | +0.044 |
Neg logit contributions | |
fault | -0.051 |
dentist | -0.051 |
wounds | -0.049 |
lair | -0.049 |
parents | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Run | +0.038 |
www | +0.036 |
forth | +0.034 |
ww | +0.034 |
gust | +0.033 |
Neg logit contributions | |
dentist | -0.025 |
lair | -0.024 |
fault | -0.024 |
lor | -0.024 |
clinic | -0.024 |
Token | too |
Token ID | 1165 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
Run | +0.012 |
www | +0.012 |
ww | +0.011 |
forth | +0.010 |
gust | +0.010 |
Neg logit contributions | |
dentist | -0.009 |
fault | -0.009 |
lair | -0.009 |
clinic | -0.008 |
wounds | -0.008 |
Token | w |
Token ID | 266 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
Run | +0.069 |
forth | +0.065 |
www | +0.064 |
heart | +0.060 |
ww | +0.060 |
Neg logit contributions | |
dentist | -0.047 |
fault | -0.042 |
truth | -0.041 |
neys | -0.040 |
lair | -0.040 |
Token | obb |
Token ID | 21963 |
Feature activation | +8.73e+00 |
Pos logit contributions | |
Run | +0.120 |
www | +0.111 |
ww | +0.104 |
forth | +0.101 |
gust | +0.095 |
Neg logit contributions | |
fault | -0.122 |
dentist | -0.121 |
lair | -0.119 |
clinic | -0.117 |
ests | -0.115 |
Token | ly |
Token ID | 306 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Run | +0.179 |
www | +0.163 |
ww | +0.147 |
gust | +0.143 |
Uh | +0.135 |
Neg logit contributions | |
fault | -0.223 |
dentist | -0.206 |
lair | -0.201 |
kit | -0.200 |
tr | -0.198 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Run | +0.041 |
www | +0.038 |
forth | +0.038 |
gust | +0.036 |
ww | +0.036 |
Neg logit contributions | |
dentist | -0.030 |
ests | -0.029 |
lor | -0.029 |
lair | -0.028 |
clinic | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
lair | +0.004 |
dentist | +0.004 |
lor | +0.004 |
wounds | +0.004 |
osc | +0.004 |
Neg logit contributions | |
Run | -0.006 |
gust | -0.005 |
www | -0.005 |
Uh | -0.004 |
Wow | -0.004 |
Token | tried |
Token ID | 3088 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
Run | +0.024 |
www | +0.023 |
ww | +0.021 |
forth | +0.020 |
gust | +0.020 |
Neg logit contributions | |
dentist | -0.021 |
lair | -0.021 |
fault | -0.021 |
clinic | -0.020 |
lor | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
lor | +0.002 |
ests | +0.001 |
dentist | +0.001 |
clinic | +0.001 |
lair | +0.001 |
Neg logit contributions | |
Run | -0.002 |
forth | -0.002 |
boom | -0.002 |
www | -0.002 |
gust | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
dentist | +0.015 |
lair | +0.015 |
fault | +0.015 |
clinic | +0.014 |
lor | +0.014 |
Neg logit contributions | |
Run | -0.017 |
www | -0.016 |
ww | -0.015 |
forth | -0.015 |
gust | -0.014 |
Token | smiled |
Token ID | 13541 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
lair | +0.021 |
dentist | +0.021 |
fault | +0.021 |
clinic | +0.021 |
lor | +0.020 |
Neg logit contributions | |
Run | -0.031 |
www | -0.030 |
ww | -0.028 |
forth | -0.028 |
gust | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
Run | +0.023 |
forth | +0.022 |
www | +0.022 |
gust | +0.022 |
ww | +0.020 |
Neg logit contributions | |
dentist | -0.019 |
ests | -0.019 |
lor | -0.019 |
clinic | -0.019 |
lair | -0.019 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Run | +0.023 |
www | +0.022 |
ww | +0.020 |
forth | +0.020 |
gust | +0.020 |
Neg logit contributions | |
dentist | -0.016 |
lair | -0.016 |
fault | -0.015 |
clinic | -0.015 |
lor | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
lair | +0.003 |
clinic | +0.003 |
fault | +0.003 |
dentist | +0.003 |
lor | +0.003 |
Neg logit contributions | |
Run | -0.003 |
www | -0.003 |
forth | -0.003 |
ww | -0.003 |
gust | -0.002 |
Token | daughter |
Token ID | 4957 |
Feature activation | -9.23e+00 |
Pos logit contributions | |
lair | +0.181 |
lor | +0.179 |
ests | +0.163 |
clinic | +0.163 |
tr | +0.157 |
Neg logit contributions | |
Run | -0.127 |
www | -0.121 |
forth | -0.121 |
ahead | -0.115 |
gust | -0.115 |
Token | a |
Token ID | 257 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
lor | +0.213 |
lair | +0.210 |
fault | +0.201 |
ests | +0.199 |
dentist | +0.196 |
Neg logit contributions | |
Run | -0.186 |
forth | -0.182 |
www | -0.175 |
gust | -0.166 |
ww | -0.165 |
Token | big |
Token ID | 1263 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
lair | +0.082 |
fault | +0.077 |
lor | +0.077 |
ests | +0.076 |
dentist | +0.076 |
Neg logit contributions | |
Run | -0.100 |
www | -0.099 |
ww | -0.095 |
gust | -0.093 |
forth | -0.083 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
dentist | +0.006 |
fault | +0.006 |
aid | +0.006 |
clinic | +0.006 |
lair | +0.005 |
Neg logit contributions | |
Run | -0.021 |
www | -0.020 |
ww | -0.019 |
forth | -0.019 |
izing | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
lair | +0.033 |
wounds | +0.031 |
dentist | +0.031 |
ests | +0.031 |
fault | +0.031 |
Neg logit contributions | |
Run | -0.033 |
www | -0.032 |
forth | -0.031 |
gust | -0.030 |
ww | -0.030 |
Token | |
Token ID | 220 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
lair | +0.025 |
dentist | +0.024 |
fault | +0.023 |
ests | +0.023 |
wounds | +0.023 |
Neg logit contributions | |
Run | -0.047 |
www | -0.045 |
ww | -0.042 |
gust | -0.041 |
forth | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Run | +0.028 |
www | +0.026 |
forth | +0.025 |
ww | +0.024 |
gust | +0.023 |
Neg logit contributions | |
dentist | -0.034 |
ests | -0.032 |
lor | -0.032 |
lair | -0.032 |
clinic | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +3.92e-05 |
Pos logit contributions | |
Run | +0.039 |
www | +0.036 |
forth | +0.036 |
gust | +0.034 |
ww | +0.034 |
Neg logit contributions | |
lair | -0.043 |
lor | -0.042 |
dentist | -0.042 |
ests | -0.042 |
fault | -0.042 |
Token | mum |
Token ID | 25682 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Run | +0.000 |
www | +0.000 |
ww | +0.000 |
forth | +0.000 |
gust | +0.000 |
Neg logit contributions | |
dentist | -0.000 |
fault | -0.000 |
lair | -0.000 |
clinic | -0.000 |
aid | -0.000 |
Token | gave |
Token ID | 2921 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
lair | +0.011 |
dentist | +0.011 |
fault | +0.010 |
ests | +0.010 |
lor | +0.010 |
Neg logit contributions | |
Run | -0.011 |
www | -0.011 |
forth | -0.010 |
ww | -0.010 |
gust | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
Run | +0.005 |
www | +0.004 |
forth | +0.004 |
gust | +0.004 |
ww | +0.004 |
Neg logit contributions | |
lair | -0.005 |
dentist | -0.005 |
fault | -0.005 |
ests | -0.005 |
lor | -0.004 |
Token | daughter |
Token ID | 4957 |
Feature activation | -8.83e+00 |
Pos logit contributions | |
lair | +0.143 |
dentist | +0.131 |
ests | +0.126 |
lor | +0.126 |
clinic | +0.125 |
Neg logit contributions | |
Run | -0.136 |
www | -0.135 |
ww | -0.128 |
gust | -0.116 |
forth | -0.115 |
Token | lots |
Token ID | 6041 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
lair | +0.205 |
dentist | +0.199 |
lor | +0.191 |
fault | +0.188 |
ests | +0.185 |
Neg logit contributions | |
Run | -0.177 |
www | -0.175 |
ww | -0.170 |
forth | -0.158 |
ahead | -0.155 |
Token | of |
Token ID | 286 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
lair | +0.001 |
dentist | +0.001 |
fault | +0.001 |
clinic | +0.001 |
lor | +0.001 |
Neg logit contributions | |
Run | -0.001 |
www | -0.001 |
ww | -0.001 |
gust | -0.001 |
forth | -0.001 |
Token | hugs |
Token ID | 40657 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
lair | +0.027 |
lor | +0.027 |
dentist | +0.025 |
fault | +0.024 |
tr | +0.024 |
Neg logit contributions | |
Run | -0.050 |
www | -0.047 |
ww | -0.045 |
gust | -0.045 |
forth | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
lair | +0.012 |
dentist | +0.012 |
fault | +0.011 |
clinic | +0.011 |
wounds | +0.011 |
Neg logit contributions | |
Run | -0.012 |
www | -0.011 |
ww | -0.010 |
forth | -0.010 |
gust | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
lair | +0.022 |
dentist | +0.021 |
fault | +0.019 |
wounds | +0.019 |
ests | +0.019 |
Neg logit contributions | |
Run | -0.031 |
www | -0.029 |
gust | -0.027 |
ww | -0.027 |
ang | -0.026 |
Token | um |
Token ID | 388 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
Run | +0.010 |
www | +0.009 |
ww | +0.009 |
forth | +0.008 |
gust | +0.008 |
Neg logit contributions | |
dentist | -0.014 |
fault | -0.014 |
lair | -0.014 |
clinic | -0.013 |
lor | -0.013 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
dentist | +0.011 |
lair | +0.011 |
fault | +0.011 |
clinic | +0.010 |
lor | +0.010 |
Neg logit contributions | |
Run | -0.013 |
www | -0.013 |
ww | -0.012 |
forth | -0.012 |
gust | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Run | +0.035 |
www | +0.033 |
gust | +0.031 |
forth | +0.031 |
ww | +0.031 |
Neg logit contributions | |
dentist | -0.030 |
lair | -0.029 |
fault | -0.029 |
clinic | -0.028 |
ests | -0.028 |
Token | gave |
Token ID | 2921 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Run | +0.033 |
www | +0.031 |
ww | +0.030 |
gust | +0.029 |
forth | +0.029 |
Neg logit contributions | |
dentist | -0.021 |
lair | -0.020 |
fault | -0.020 |
clinic | -0.020 |
lor | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
Run | +0.010 |
www | +0.009 |
forth | +0.009 |
gust | +0.008 |
ww | +0.008 |
Neg logit contributions | |
lair | -0.010 |
dentist | -0.009 |
clinic | -0.009 |
ests | -0.009 |
fault | -0.009 |
Token | daughter |
Token ID | 4957 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
lair | +0.141 |
dentist | +0.127 |
ests | +0.126 |
clinic | +0.126 |
lor | +0.125 |
Neg logit contributions | |
Run | -0.130 |
www | -0.127 |
ww | -0.119 |
forth | -0.111 |
gust | -0.109 |
Token | another |
Token ID | 1194 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
lair | +0.206 |
dentist | +0.195 |
fault | +0.195 |
lor | +0.192 |
ests | +0.188 |
Neg logit contributions | |
Run | -0.179 |
www | -0.173 |
forth | -0.164 |
ww | -0.164 |
ahead | -0.156 |
Token | hug |
Token ID | 16225 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
lair | +0.051 |
dentist | +0.051 |
fault | +0.049 |
lor | +0.049 |
clinic | +0.048 |
Neg logit contributions | |
Run | -0.080 |
www | -0.076 |
ww | -0.072 |
gust | -0.070 |
forth | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
lair | +0.016 |
dentist | +0.016 |
ests | +0.015 |
fault | +0.015 |
clinic | +0.015 |
Neg logit contributions | |
Run | -0.019 |
www | -0.018 |
forth | -0.017 |
ww | -0.017 |
gust | -0.017 |
Token | ' |
Token ID | 705 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
lair | +0.017 |
dentist | +0.017 |
fault | +0.016 |
ests | +0.016 |
wounds | +0.016 |
Neg logit contributions | |
Run | -0.025 |
www | -0.024 |
ww | -0.023 |
gust | -0.022 |
forth | -0.021 |
Token | That |
Token ID | 2504 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
Run | +0.020 |
www | +0.019 |
gust | +0.018 |
forth | +0.017 |
ww | +0.017 |
Neg logit contributions | |
dentist | -0.018 |
lor | -0.018 |
ests | -0.018 |
clinic | -0.017 |
fault | -0.017 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
Run | +0.016 |
www | +0.015 |
ww | +0.014 |
forth | +0.014 |
gust | +0.013 |
Neg logit contributions | |
dentist | -0.011 |
lair | -0.011 |
fault | -0.011 |
clinic | -0.011 |
lor | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
Run | +0.022 |
www | +0.021 |
ww | +0.020 |
forth | +0.020 |
gust | +0.019 |
Neg logit contributions | |
dentist | -0.016 |
lair | -0.016 |
fault | -0.016 |
clinic | -0.015 |
lor | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Run | +0.013 |
www | +0.012 |
ww | +0.011 |
forth | +0.011 |
gust | +0.011 |
Neg logit contributions | |
fault | -0.013 |
lair | -0.013 |
dentist | -0.013 |
clinic | -0.013 |
lor | -0.013 |
Token | gave |
Token ID | 2921 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Run | +0.013 |
www | +0.013 |
ww | +0.012 |
gust | +0.012 |
forth | +0.012 |
Neg logit contributions | |
dentist | -0.008 |
lair | -0.008 |
lor | -0.008 |
clinic | -0.007 |
fault | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
forth | +0.007 |
www | +0.006 |
Run | +0.006 |
heart | +0.006 |
gust | +0.006 |
Neg logit contributions | |
clinic | -0.009 |
lair | -0.009 |
aj | -0.009 |
tr | -0.009 |
fault | -0.009 |
Token | wife |
Token ID | 3656 |
Feature activation | -8.64e+00 |
Pos logit contributions | |
lor | +0.065 |
ests | +0.064 |
tr | +0.062 |
lair | +0.062 |
fault | +0.059 |
Neg logit contributions | |
Run | -0.145 |
www | -0.142 |
ww | -0.134 |
forth | -0.130 |
gust | -0.129 |
Token | a |
Token ID | 257 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
lair | +0.181 |
fault | +0.180 |
clinic | +0.173 |
lor | +0.173 |
dentist | +0.169 |
Neg logit contributions | |
www | -0.183 |
Run | -0.183 |
ww | -0.178 |
forth | -0.166 |
gust | -0.157 |
Token | big |
Token ID | 1263 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
lair | +0.090 |
lor | +0.089 |
wounds | +0.086 |
ests | +0.084 |
clinic | +0.084 |
Neg logit contributions | |
Run | -0.095 |
www | -0.094 |
ww | -0.093 |
gust | -0.088 |
blur | -0.078 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
dentist | +0.012 |
fault | +0.011 |
lair | +0.011 |
clinic | +0.011 |
aid | +0.010 |
Neg logit contributions | |
Run | -0.033 |
www | -0.031 |
ww | -0.030 |
forth | -0.030 |
izing | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
lair | +0.038 |
wounds | +0.038 |
dentist | +0.036 |
fault | +0.036 |
aj | +0.035 |
Neg logit contributions | |
Run | -0.030 |
www | -0.029 |
forth | -0.027 |
ww | -0.027 |
gust | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
lair | +0.033 |
fault | +0.033 |
lor | +0.032 |
ests | +0.032 |
dentist | +0.032 |
Neg logit contributions | |
Run | -0.033 |
www | -0.030 |
gust | -0.029 |
ww | -0.028 |
forth | -0.028 |
Token | she |
Token ID | 673 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Run | +0.000 |
www | +0.000 |
forth | +0.000 |
ww | +0.000 |
gust | +0.000 |
Neg logit contributions | |
dentist | -0.000 |
parents | -0.000 |
fault | -0.000 |
clinic | -0.000 |
Her | -0.000 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
dentist | +0.006 |
lair | +0.006 |
fault | +0.006 |
clinic | +0.005 |
lor | +0.005 |
Neg logit contributions | |
Run | -0.008 |
www | -0.008 |
ww | -0.008 |
forth | -0.007 |
gust | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ests | +0.020 |
lair | +0.020 |
fault | +0.019 |
lor | +0.018 |
clinic | +0.018 |
Neg logit contributions | |
www | -0.036 |
Run | -0.036 |
ww | -0.034 |
forth | -0.033 |
gust | -0.032 |
Token | give |
Token ID | 1577 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
fault | +0.071 |
lair | +0.070 |
ests | +0.067 |
lor | +0.066 |
dentist | +0.066 |
Neg logit contributions | |
Run | -0.079 |
www | -0.078 |
ww | -0.072 |
forth | -0.070 |
gust | -0.069 |
Token | her |
Token ID | 607 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
lair | +0.003 |
lor | +0.003 |
fault | +0.003 |
clinic | +0.002 |
ests | +0.002 |
Neg logit contributions | |
Run | -0.003 |
www | -0.003 |
forth | -0.003 |
ww | -0.003 |
gust | -0.002 |
Token | daughter |
Token ID | 4957 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
lor | +0.165 |
lair | +0.158 |
isk | +0.143 |
age | +0.137 |
heals | +0.136 |
Neg logit contributions | |
Run | -0.102 |
www | -0.094 |
ww | -0.091 |
gust | -0.090 |
wind | -0.084 |
Token | a |
Token ID | 257 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
lair | +0.219 |
lor | +0.213 |
fault | +0.201 |
ests | +0.199 |
wounds | +0.193 |
Neg logit contributions | |
www | -0.146 |
Run | -0.143 |
ww | -0.138 |
ahead | -0.137 |
after | -0.132 |
Token | teaspoon |
Token ID | 22326 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
lair | +0.080 |
lor | +0.078 |
wounds | +0.077 |
ests | +0.076 |
neys | +0.076 |
Neg logit contributions | |
www | -0.092 |
ww | -0.089 |
Run | -0.088 |
gust | -0.085 |
boom | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
lair | +0.050 |
dentist | +0.050 |
wounds | +0.049 |
lor | +0.048 |
fault | +0.048 |
Neg logit contributions | |
www | -0.059 |
Run | -0.058 |
ww | -0.054 |
forth | -0.052 |
ahead | -0.050 |
Token | The |
Token ID | 383 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
Run | +0.018 |
www | +0.017 |
gust | +0.016 |
ww | +0.016 |
forth | +0.015 |
Neg logit contributions | |
lair | -0.014 |
fault | -0.013 |
wounds | -0.013 |
lor | -0.013 |
dentist | -0.013 |
Token | little |
Token ID | 1310 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
lair | +0.009 |
lor | +0.008 |
fault | +0.008 |
ests | +0.008 |
osc | +0.008 |
Neg logit contributions | |
Run | -0.015 |
www | -0.015 |
gust | -0.014 |
ww | -0.014 |
forth | -0.014 |
Token | she |
Token ID | 673 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
lair | +0.024 |
fault | +0.024 |
dentist | +0.024 |
clinic | +0.023 |
ests | +0.023 |
Neg logit contributions | |
Run | -0.022 |
www | -0.021 |
ww | -0.019 |
forth | -0.019 |
gust | -0.019 |
Token | said |
Token ID | 531 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
fault | +0.031 |
lair | +0.030 |
dentist | +0.030 |
clinic | +0.030 |
lor | +0.029 |
Neg logit contributions | |
Run | -0.032 |
www | -0.031 |
ww | -0.028 |
forth | -0.028 |
gust | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ests | +0.055 |
dentist | +0.055 |
lair | +0.055 |
fault | +0.054 |
clinic | +0.051 |
Neg logit contributions | |
Run | -0.071 |
www | -0.067 |
gust | -0.064 |
forth | -0.062 |
ww | -0.060 |
Token | giving |
Token ID | 3501 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
dentist | +0.052 |
lair | +0.051 |
fault | +0.051 |
clinic | +0.049 |
lor | +0.049 |
Neg logit contributions | |
Run | -0.062 |
www | -0.058 |
ww | -0.055 |
gust | -0.053 |
forth | -0.053 |
Token | her |
Token ID | 607 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
Run | +0.011 |
www | +0.010 |
ww | +0.009 |
forth | +0.009 |
gust | +0.009 |
Neg logit contributions | |
lair | -0.011 |
clinic | -0.011 |
dentist | -0.011 |
ests | -0.010 |
fault | -0.010 |
Token | daughter |
Token ID | 4957 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
lair | +0.135 |
dentist | +0.127 |
ests | +0.127 |
lor | +0.124 |
clinic | +0.123 |
Neg logit contributions | |
Run | -0.134 |
www | -0.130 |
ww | -0.122 |
forth | -0.118 |
gust | -0.113 |
Token | a |
Token ID | 257 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
lair | +0.189 |
ests | +0.184 |
lor | +0.182 |
dentist | +0.180 |
fault | +0.180 |
Neg logit contributions | |
Run | -0.179 |
www | -0.170 |
forth | -0.167 |
ww | -0.159 |
gust | -0.158 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
lair | +0.078 |
ests | +0.075 |
lor | +0.075 |
dentist | +0.075 |
fault | +0.074 |
Neg logit contributions | |
Run | -0.107 |
www | -0.106 |
ww | -0.102 |
gust | -0.098 |
forth | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
lair | +0.021 |
dentist | +0.020 |
ests | +0.020 |
fault | +0.020 |
wounds | +0.019 |
Neg logit contributions | |
Run | -0.025 |
www | -0.024 |
forth | -0.023 |
gust | -0.022 |
ww | -0.022 |
Token | ' |
Token ID | 705 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
lair | +0.026 |
dentist | +0.025 |
fault | +0.024 |
ests | +0.023 |
wounds | +0.023 |
Neg logit contributions | |
Run | -0.053 |
www | -0.051 |
ww | -0.048 |
gust | -0.047 |
forth | -0.045 |
Token | I |
Token ID | 40 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
Run | +0.012 |
www | +0.011 |
gust | +0.011 |
ww | +0.010 |
forth | +0.010 |
Neg logit contributions | |
dentist | -0.011 |
lor | -0.010 |
clinic | -0.010 |
ests | -0.010 |
fault | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
wounds | +0.010 |
lair | +0.010 |
fault | +0.009 |
lor | +0.009 |
patients | +0.009 |
Neg logit contributions | |
Run | -0.013 |
www | -0.012 |
ww | -0.011 |
gust | -0.011 |
forth | -0.011 |
Token | thanked |
Token ID | 26280 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
fault | +0.005 |
lair | +0.005 |
dentist | +0.005 |
ests | +0.005 |
lor | +0.005 |
Neg logit contributions | |
Run | -0.005 |
www | -0.005 |
ww | -0.005 |
forth | -0.005 |
gust | -0.005 |
Token | Max |
Token ID | 5436 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
lair | +0.049 |
fault | +0.049 |
lor | +0.049 |
tr | +0.047 |
neys | +0.046 |
Neg logit contributions | |
Run | -0.040 |
forth | -0.037 |
www | -0.036 |
gust | -0.036 |
boom | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
lor | +0.128 |
ests | +0.128 |
lair | +0.127 |
dentist | +0.126 |
fault | +0.125 |
Neg logit contributions | |
forth | -0.063 |
Run | -0.059 |
www | -0.053 |
ww | -0.048 |
gust | -0.048 |
Token | gave |
Token ID | 2921 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
Run | +0.005 |
www | +0.005 |
forth | +0.005 |
ww | +0.005 |
gust | +0.004 |
Neg logit contributions | |
fault | -0.005 |
lair | -0.005 |
dentist | -0.005 |
lor | -0.005 |
clinic | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | -8.47e+00 |
Pos logit contributions | |
lor | +0.024 |
lair | +0.024 |
clinic | +0.024 |
tr | +0.023 |
fault | +0.023 |
Neg logit contributions | |
forth | -0.018 |
Run | -0.018 |
www | -0.016 |
gust | -0.016 |
ww | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
lor | +0.200 |
lair | +0.199 |
clinic | +0.195 |
fault | +0.190 |
tr | +0.183 |
Neg logit contributions | |
Run | -0.159 |
www | -0.152 |
ww | -0.147 |
forth | -0.144 |
ahead | -0.135 |
Token | treat |
Token ID | 2190 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
lair | +0.105 |
lor | +0.099 |
clinic | +0.098 |
wounds | +0.098 |
fault | +0.097 |
Neg logit contributions | |
Run | -0.115 |
www | -0.114 |
ww | -0.112 |
gust | -0.105 |
boom | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
lair | +0.071 |
lor | +0.069 |
fault | +0.067 |
clinic | +0.067 |
dentist | +0.067 |
Neg logit contributions | |
Run | -0.080 |
www | -0.078 |
ww | -0.072 |
forth | -0.071 |
ahead | -0.067 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
lair | +0.024 |
wounds | +0.024 |
fault | +0.023 |
patients | +0.023 |
lor | +0.023 |
Neg logit contributions | |
Run | -0.027 |
www | -0.025 |
gust | -0.024 |
ww | -0.023 |
forth | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
Run | +0.006 |
www | +0.005 |
forth | +0.005 |
ww | +0.005 |
gust | +0.005 |
Neg logit contributions | |
fault | -0.005 |
lair | -0.005 |
dentist | -0.005 |
ests | -0.005 |
lor | -0.005 |
Token | Max |
Token ID | 5436 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
tr | +0.077 |
lair | +0.076 |
fault | +0.074 |
ests | +0.074 |
lor | +0.072 |
Neg logit contributions | |
Run | -0.058 |
www | -0.055 |
forth | -0.049 |
ww | -0.049 |
gust | -0.048 |
Token | 's |
Token ID | 338 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
lair | +0.146 |
dentist | +0.145 |
lor | +0.141 |
ests | +0.141 |
tr | +0.140 |
Neg logit contributions | |
Run | -0.109 |
www | -0.104 |
forth | -0.101 |
ww | -0.098 |
heart | -0.093 |
Token | friendship |
Token ID | 14738 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
lor | +0.109 |
ests | +0.098 |
lair | +0.094 |
neys | +0.094 |
dentist | +0.093 |
Neg logit contributions | |
Run | -0.115 |
www | -0.109 |
gust | -0.108 |
ww | -0.103 |
forth | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
dentist | +0.054 |
lair | +0.052 |
clinic | +0.051 |
principal | +0.050 |
wounds | +0.049 |
Neg logit contributions | |
www | -0.043 |
Run | -0.043 |
ww | -0.041 |
forth | -0.040 |
ening | -0.036 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Run | +0.010 |
forth | +0.009 |
www | +0.009 |
ww | +0.009 |
gust | +0.008 |
Neg logit contributions | |
lor | -0.009 |
ests | -0.009 |
dentist | -0.009 |
lair | -0.009 |
clinic | -0.009 |
Token | him |
Token ID | 683 |
Feature activation | -8.35e+00 |
Pos logit contributions | |
lair | +0.036 |
lor | +0.035 |
dentist | +0.034 |
clinic | +0.034 |
tr | +0.034 |
Neg logit contributions | |
Run | -0.026 |
forth | -0.026 |
www | -0.025 |
ww | -0.023 |
dd | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
lair | +0.197 |
lor | +0.194 |
dentist | +0.185 |
clinic | +0.184 |
tr | +0.178 |
Neg logit contributions | |
Run | -0.154 |
ww | -0.149 |
www | -0.146 |
forth | -0.137 |
ahead | -0.131 |
Token | big |
Token ID | 1263 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
lair | +0.101 |
neys | +0.096 |
wounds | +0.096 |
dentist | +0.096 |
osc | +0.096 |
Neg logit contributions | |
www | -0.116 |
ww | -0.116 |
Run | -0.112 |
gust | -0.105 |
ha | -0.095 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
dentist | +0.017 |
lair | +0.017 |
fault | +0.017 |
clinic | +0.016 |
lor | +0.016 |
Neg logit contributions | |
Run | -0.037 |
www | -0.035 |
ww | -0.034 |
forth | -0.033 |
gust | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
lair | +0.037 |
fault | +0.035 |
wounds | +0.035 |
dentist | +0.035 |
clinic | +0.034 |
Neg logit contributions | |
Run | -0.034 |
www | -0.033 |
ww | -0.031 |
forth | -0.031 |
heart | -0.029 |
Token | From |
Token ID | 3574 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
lair | +0.022 |
wounds | +0.022 |
fault | +0.021 |
dentist | +0.021 |
ests | +0.020 |
Neg logit contributions | |
Run | -0.033 |
www | -0.032 |
ww | -0.030 |
gust | -0.029 |
forth | -0.028 |
Token | ran |
Token ID | 4966 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
lair | +0.009 |
wounds | +0.009 |
fault | +0.008 |
patients | +0.008 |
dentist | +0.008 |
Neg logit contributions | |
Run | -0.013 |
www | -0.013 |
ww | -0.012 |
gust | -0.012 |
ang | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
Run | +0.079 |
www | +0.079 |
ww | +0.075 |
gust | +0.073 |
forth | +0.070 |
Neg logit contributions | |
fault | -0.032 |
lair | -0.029 |
dentist | -0.029 |
clinic | -0.029 |
wounds | -0.029 |
Token | him |
Token ID | 683 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
lor | +0.062 |
ests | +0.059 |
lair | +0.058 |
fault | +0.058 |
dentist | +0.058 |
Neg logit contributions | |
Run | -0.054 |
www | -0.047 |
gust | -0.045 |
forth | -0.044 |
boom | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
dentist | +0.110 |
ests | +0.109 |
lor | +0.105 |
fault | +0.103 |
lair | +0.101 |
Neg logit contributions | |
forth | -0.088 |
Run | -0.084 |
www | -0.073 |
gust | -0.071 |
ening | -0.071 |
Token | gave |
Token ID | 2921 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
Run | +0.011 |
www | +0.010 |
forth | +0.009 |
ww | +0.009 |
gust | +0.009 |
Neg logit contributions | |
fault | -0.010 |
lair | -0.010 |
ests | -0.010 |
lor | -0.010 |
dentist | -0.010 |
Token | him |
Token ID | 683 |
Feature activation | -8.32e+00 |
Pos logit contributions | |
lair | +0.014 |
clinic | +0.013 |
dentist | +0.013 |
fault | +0.013 |
lor | +0.013 |
Neg logit contributions | |
Run | -0.012 |
www | -0.012 |
forth | -0.011 |
ww | -0.011 |
gust | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
lor | +0.205 |
lair | +0.201 |
clinic | +0.191 |
dentist | +0.185 |
tr | +0.181 |
Neg logit contributions | |
Run | -0.151 |
www | -0.135 |
ww | -0.134 |
forth | -0.130 |
ahead | -0.129 |
Token | big |
Token ID | 1263 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
lair | +0.098 |
neys | +0.093 |
lor | +0.093 |
wounds | +0.092 |
dentist | +0.092 |
Neg logit contributions | |
Run | -0.118 |
www | -0.118 |
ww | -0.116 |
gust | -0.109 |
boom | -0.099 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
dentist | +0.016 |
fault | +0.015 |
lair | +0.015 |
clinic | +0.014 |
aid | +0.014 |
Neg logit contributions | |
Run | -0.040 |
www | -0.039 |
forth | -0.037 |
ww | -0.037 |
izing | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
lair | +0.041 |
wounds | +0.040 |
fault | +0.040 |
dentist | +0.038 |
clinic | +0.038 |
Neg logit contributions | |
Run | -0.037 |
www | -0.035 |
forth | -0.033 |
ww | -0.032 |
ahead | -0.032 |
Token | They |
Token ID | 1119 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
lair | +0.019 |
fault | +0.019 |
wounds | +0.019 |
dentist | +0.018 |
lor | +0.018 |
Neg logit contributions | |
Run | -0.023 |
www | -0.022 |
gust | -0.020 |
ww | -0.020 |
forth | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
lair | +0.014 |
fault | +0.014 |
clinic | +0.013 |
lor | +0.013 |
ests | +0.013 |
Neg logit contributions | |
Run | -0.013 |
www | -0.012 |
forth | -0.011 |
gust | -0.011 |
ww | -0.011 |
Token | mistake |
Token ID | 7457 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
lor | +0.058 |
ests | +0.050 |
clinic | +0.049 |
osc | +0.048 |
neys | +0.048 |
Neg logit contributions | |
Run | -0.066 |
gust | -0.065 |
forth | -0.063 |
www | -0.063 |
ww | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Run | +0.028 |
www | +0.026 |
ww | +0.024 |
forth | +0.024 |
gust | +0.024 |
Neg logit contributions | |
lair | -0.028 |
dentist | -0.028 |
clinic | -0.027 |
lor | -0.027 |
fault | -0.027 |
Token | gave |
Token ID | 2921 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Run | +0.026 |
www | +0.025 |
forth | +0.023 |
ww | +0.023 |
gust | +0.023 |
Neg logit contributions | |
fault | -0.027 |
lair | -0.027 |
dentist | -0.027 |
lor | -0.026 |
clinic | -0.026 |
Token | his |
Token ID | 465 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
lor | +0.011 |
clinic | +0.010 |
lair | +0.010 |
fault | +0.010 |
tr | +0.009 |
Neg logit contributions | |
forth | -0.009 |
Run | -0.007 |
www | -0.007 |
gust | -0.007 |
ening | -0.006 |
Token | sister |
Token ID | 6621 |
Feature activation | -8.29e+00 |
Pos logit contributions | |
lor | +0.143 |
tr | +0.122 |
osc | +0.121 |
ests | +0.120 |
age | +0.120 |
Neg logit contributions | |
gust | -0.107 |
Run | -0.103 |
forth | -0.103 |
www | -0.096 |
boom | -0.094 |
Token | a |
Token ID | 257 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
lor | +0.176 |
lair | +0.175 |
fault | +0.174 |
clinic | +0.168 |
ests | +0.160 |
Neg logit contributions | |
Run | -0.185 |
www | -0.172 |
ww | -0.166 |
gust | -0.160 |
forth | -0.157 |
Token | turn |
Token ID | 1210 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
lor | +0.096 |
lair | +0.093 |
neys | +0.091 |
ests | +0.090 |
girls | +0.090 |
Neg logit contributions | |
Run | -0.086 |
gust | -0.084 |
ww | -0.083 |
www | -0.083 |
boom | -0.073 |
Token | with |
Token ID | 351 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
lor | +0.016 |
lair | +0.016 |
dentist | +0.015 |
clinic | +0.015 |
ests | +0.014 |
Neg logit contributions | |
Run | -0.019 |
www | -0.018 |
forth | -0.018 |
gust | -0.018 |
ww | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
lor | +0.010 |
clinic | +0.009 |
lair | +0.009 |
tr | +0.009 |
ests | +0.009 |
Neg logit contributions | |
gust | -0.009 |
Run | -0.009 |
forth | -0.008 |
www | -0.008 |
boom | -0.007 |
Token | toy |
Token ID | 13373 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
lor | +0.038 |
dentist | +0.037 |
clinic | +0.037 |
lair | +0.037 |
ests | +0.036 |
Neg logit contributions | |
Run | -0.039 |
www | -0.036 |
gust | -0.034 |
ww | -0.034 |
forth | -0.034 |
Token | ran |
Token ID | 4966 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
fault | +0.017 |
lor | +0.016 |
lair | +0.016 |
clinic | +0.016 |
dentist | +0.016 |
Neg logit contributions | |
Run | -0.016 |
www | -0.015 |
ww | -0.014 |
forth | -0.013 |
gust | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
Run | +0.104 |
www | +0.101 |
ww | +0.097 |
gust | +0.095 |
forth | +0.094 |
Neg logit contributions | |
dentist | -0.022 |
lair | -0.021 |
fault | -0.020 |
clinic | -0.019 |
lor | -0.018 |
Token | Sam |
Token ID | 3409 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
fault | +0.068 |
lair | +0.068 |
lor | +0.068 |
dentist | +0.068 |
clinic | +0.066 |
Neg logit contributions | |
Run | -0.077 |
www | -0.070 |
forth | -0.066 |
gust | -0.065 |
ww | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ests | +0.103 |
fault | +0.099 |
dentist | +0.098 |
neys | +0.097 |
lor | +0.095 |
Neg logit contributions | |
forth | -0.055 |
Run | -0.052 |
ening | -0.051 |
ahead | -0.044 |
www | -0.044 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
fault | +0.010 |
lair | +0.009 |
ests | +0.009 |
lor | +0.009 |
dentist | +0.009 |
Neg logit contributions | |
Run | -0.011 |
www | -0.010 |
ww | -0.010 |
forth | -0.010 |
gust | -0.009 |
Token | him |
Token ID | 683 |
Feature activation | -8.25e+00 |
Pos logit contributions | |
dentist | +0.021 |
lair | +0.021 |
clinic | +0.021 |
fault | +0.020 |
lor | +0.020 |
Neg logit contributions | |
Run | -0.026 |
www | -0.024 |
forth | -0.023 |
ww | -0.023 |
gust | -0.022 |
Token | his |
Token ID | 465 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
lor | +0.200 |
lair | +0.196 |
clinic | +0.187 |
dentist | +0.180 |
fault | +0.177 |
Neg logit contributions | |
Run | -0.158 |
www | -0.138 |
forth | -0.136 |
ww | -0.135 |
ahead | -0.131 |
Token | l |
Token ID | 300 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
neys | +0.149 |
lor | +0.143 |
lair | +0.138 |
keeping | +0.138 |
ests | +0.131 |
Neg logit contributions | |
Run | -0.120 |
www | -0.119 |
ww | -0.118 |
forth | -0.112 |
gust | -0.109 |
Token | oll |
Token ID | 692 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
dentist | +0.008 |
lair | +0.007 |
clinic | +0.007 |
fault | +0.007 |
patients | +0.007 |
Neg logit contributions | |
Run | -0.014 |
www | -0.014 |
ww | -0.013 |
ang | -0.013 |
gust | -0.012 |
Token | ipop |
Token ID | 42800 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
lair | +0.013 |
clinic | +0.013 |
dentist | +0.013 |
aid | +0.012 |
fault | +0.012 |
Neg logit contributions | |
www | -0.012 |
ww | -0.012 |
Run | -0.012 |
forth | -0.011 |
dd | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
clinic | +0.097 |
lair | +0.096 |
lor | +0.096 |
dentist | +0.095 |
principal | +0.092 |
Neg logit contributions | |
Run | -0.075 |
forth | -0.072 |
www | -0.071 |
ww | -0.068 |
after | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
fault | +0.061 |
lair | +0.055 |
tr | +0.050 |
osc | +0.049 |
clinic | +0.049 |
Neg logit contributions | |
Run | -0.067 |
www | -0.066 |
ww | -0.063 |
gust | -0.058 |
ang | -0.058 |
Token | Daddy |
Token ID | 48280 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
fault | +0.023 |
lair | +0.022 |
dentist | +0.022 |
clinic | +0.021 |
ests | +0.021 |
Neg logit contributions | |
Run | -0.026 |
www | -0.025 |
ww | -0.023 |
forth | -0.022 |
gust | -0.021 |
Token | gave |
Token ID | 2921 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
dentist | +0.026 |
lair | +0.026 |
fault | +0.026 |
clinic | +0.025 |
lor | +0.025 |
Neg logit contributions | |
Run | -0.036 |
www | -0.034 |
ww | -0.032 |
forth | -0.031 |
gust | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
heart | +0.001 |
forth | +0.001 |
www | +0.001 |
Run | +0.001 |
gust | +0.001 |
Neg logit contributions | |
lair | -0.002 |
clinic | -0.002 |
fault | -0.002 |
tr | -0.002 |
neys | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
lor | +0.126 |
lair | +0.124 |
neys | +0.118 |
tr | +0.118 |
ests | +0.117 |
Neg logit contributions | |
Run | -0.102 |
www | -0.095 |
gust | -0.089 |
forth | -0.087 |
ww | -0.086 |
Token | girl |
Token ID | 2576 |
Feature activation | -8.24e+00 |
Pos logit contributions | |
lor | +0.023 |
lair | +0.023 |
dentist | +0.022 |
ests | +0.022 |
clinic | +0.022 |
Neg logit contributions | |
Run | -0.013 |
www | -0.012 |
forth | -0.011 |
ww | -0.011 |
gust | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
fault | +0.188 |
lair | +0.185 |
lor | +0.180 |
dentist | +0.172 |
clinic | +0.172 |
Neg logit contributions | |
Run | -0.170 |
www | -0.161 |
forth | -0.156 |
ww | -0.151 |
gust | -0.143 |
Token | hug |
Token ID | 16225 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
lair | +0.081 |
lor | +0.078 |
fault | +0.077 |
dentist | +0.076 |
clinic | +0.075 |
Neg logit contributions | |
Run | -0.096 |
www | -0.094 |
ww | -0.089 |
gust | -0.086 |
forth | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
lair | +0.017 |
fault | +0.017 |
wounds | +0.017 |
dentist | +0.017 |
clinic | +0.016 |
Neg logit contributions | |
Run | -0.011 |
forth | -0.010 |
www | -0.010 |
ening | -0.010 |
ging | -0.010 |
Token | then |
Token ID | 788 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Run | +0.007 |
www | +0.007 |
ww | +0.006 |
forth | +0.006 |
gust | +0.006 |
Neg logit contributions | |
fault | -0.007 |
lair | -0.007 |
lor | -0.007 |
clinic | -0.007 |
ests | -0.007 |
Token | went |
Token ID | 1816 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
Run | +0.010 |
www | +0.010 |
ww | +0.009 |
forth | +0.009 |
gust | +0.009 |
Neg logit contributions | |
fault | -0.010 |
lair | -0.010 |
dentist | -0.010 |
clinic | -0.010 |
lor | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ests | +0.018 |
lor | +0.018 |
lair | +0.017 |
fault | +0.017 |
dentist | +0.017 |
Neg logit contributions | |
Run | -0.015 |
www | -0.014 |
gust | -0.014 |
forth | -0.013 |
ww | -0.013 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
Run | +0.011 |
www | +0.010 |
ww | +0.009 |
forth | +0.009 |
gust | +0.009 |
Neg logit contributions | |
dentist | -0.009 |
lair | -0.008 |
fault | -0.008 |
clinic | -0.008 |
lor | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Run | +0.023 |
www | +0.022 |
ww | +0.020 |
forth | +0.020 |
gust | +0.020 |
Neg logit contributions | |
dentist | -0.016 |
lair | -0.016 |
fault | -0.015 |
clinic | -0.015 |
lor | -0.015 |
Token | gave |
Token ID | 2921 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
Run | +0.060 |
www | +0.056 |
ww | +0.053 |
gust | +0.051 |
forth | +0.050 |
Neg logit contributions | |
dentist | -0.039 |
lair | -0.038 |
fault | -0.037 |
clinic | -0.036 |
lor | -0.036 |
Token | her |
Token ID | 607 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
lair | +0.002 |
fault | +0.002 |
clinic | +0.002 |
dentist | +0.002 |
lor | +0.002 |
Neg logit contributions | |
Run | -0.002 |
www | -0.002 |
forth | -0.002 |
ww | -0.002 |
gust | -0.002 |
Token | son |
Token ID | 3367 |
Feature activation | -8.23e+00 |
Pos logit contributions | |
lor | +0.159 |
clinic | +0.150 |
lair | +0.149 |
ests | +0.138 |
osc | +0.137 |
Neg logit contributions | |
www | -0.102 |
forth | -0.101 |
Run | -0.101 |
gust | -0.100 |
ww | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
lair | +0.181 |
lor | +0.180 |
fault | +0.171 |
clinic | +0.171 |
dentist | +0.169 |
Neg logit contributions | |
www | -0.167 |
Run | -0.166 |
ww | -0.161 |
forth | -0.155 |
ahead | -0.147 |
Token | big |
Token ID | 1263 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
lair | +0.070 |
dentist | +0.067 |
fault | +0.067 |
lor | +0.066 |
clinic | +0.066 |
Neg logit contributions | |
Run | -0.095 |
www | -0.093 |
ww | -0.089 |
gust | -0.086 |
forth | -0.081 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
dentist | +0.006 |
fault | +0.005 |
aid | +0.005 |
clinic | +0.005 |
lair | +0.005 |
Neg logit contributions | |
Run | -0.023 |
www | -0.021 |
forth | -0.021 |
izing | -0.021 |
dd | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
wounds | +0.029 |
lair | +0.029 |
dentist | +0.027 |
fault | +0.027 |
clinic | +0.027 |
Neg logit contributions | |
Run | -0.032 |
www | -0.032 |
forth | -0.030 |
ww | -0.030 |
gust | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
lair | +0.021 |
wounds | +0.020 |
fault | +0.020 |
dentist | +0.020 |
clinic | +0.018 |
Neg logit contributions | |
Run | -0.043 |
www | -0.041 |
ww | -0.038 |
gust | -0.037 |
forth | -0.036 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
lair | +0.035 |
fault | +0.034 |
wounds | +0.034 |
dentist | +0.033 |
lor | +0.032 |
Neg logit contributions | |
Run | -0.044 |
www | -0.041 |
gust | -0.038 |
ww | -0.038 |
forth | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
fault | +0.034 |
lair | +0.033 |
lor | +0.032 |
clinic | +0.031 |
ests | +0.031 |
Neg logit contributions | |
Run | -0.032 |
www | -0.031 |
forth | -0.029 |
ww | -0.027 |
gust | -0.027 |
Token | yes |
Token ID | 3763 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
lair | +0.050 |
dentist | +0.048 |
fault | +0.048 |
ests | +0.048 |
clinic | +0.047 |
Neg logit contributions | |
Run | -0.046 |
www | -0.042 |
gust | -0.040 |
ww | -0.038 |
forth | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
Run | +0.003 |
www | +0.003 |
ww | +0.003 |
forth | +0.003 |
gust | +0.002 |
Neg logit contributions | |
lair | -0.003 |
dentist | -0.003 |
fault | -0.003 |
ests | -0.003 |
clinic | -0.003 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
Run | +0.015 |
www | +0.015 |
ww | +0.014 |
forth | +0.013 |
gust | +0.013 |
Neg logit contributions | |
dentist | -0.015 |
lair | -0.015 |
fault | -0.015 |
clinic | -0.015 |
lor | -0.015 |
Token | him |
Token ID | 683 |
Feature activation | -8.22e+00 |
Pos logit contributions | |
lair | +0.007 |
clinic | +0.007 |
fault | +0.006 |
lor | +0.006 |
dentist | +0.006 |
Neg logit contributions | |
Run | -0.007 |
www | -0.006 |
forth | -0.006 |
ww | -0.006 |
gust | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
lair | +0.201 |
lor | +0.198 |
clinic | +0.191 |
dentist | +0.185 |
fault | +0.184 |
Neg logit contributions | |
Run | -0.151 |
www | -0.145 |
ww | -0.137 |
ahead | -0.135 |
forth | -0.131 |
Token | small |
Token ID | 1402 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
lor | +0.089 |
ests | +0.081 |
lair | +0.080 |
osc | +0.079 |
isk | +0.078 |
Neg logit contributions | |
Run | -0.102 |
www | -0.094 |
gust | -0.092 |
ww | -0.088 |
forth | -0.087 |
Token | shovel |
Token ID | 33677 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
dentist | +0.024 |
lair | +0.024 |
fault | +0.024 |
clinic | +0.023 |
lor | +0.023 |
Neg logit contributions | |
Run | -0.032 |
www | -0.031 |
ww | -0.029 |
forth | -0.028 |
gust | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
dentist | +0.042 |
clinic | +0.041 |
lair | +0.040 |
lor | +0.039 |
fault | +0.037 |
Neg logit contributions | |
Run | -0.054 |
www | -0.051 |
forth | -0.051 |
ww | -0.048 |
gust | -0.048 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
lair | +0.016 |
fault | +0.015 |
wounds | +0.015 |
dentist | +0.015 |
lor | +0.014 |
Neg logit contributions | |
Run | -0.023 |
www | -0.022 |
ww | -0.020 |
gust | -0.020 |
forth | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Run | +0.004 |
www | +0.004 |
forth | +0.003 |
gust | +0.003 |
ww | +0.003 |
Neg logit contributions | |
lor | -0.006 |
ests | -0.006 |
dentist | -0.006 |
lair | -0.006 |
wounds | -0.005 |
Token | but |
Token ID | 475 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Run | +0.003 |
www | +0.003 |
ww | +0.003 |
forth | +0.003 |
gust | +0.003 |
Neg logit contributions | |
dentist | -0.003 |
lair | -0.003 |
fault | -0.003 |
clinic | -0.003 |
wounds | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
Run | +0.036 |
www | +0.034 |
ww | +0.031 |
forth | +0.030 |
gust | +0.030 |
Neg logit contributions | |
dentist | -0.045 |
lair | -0.045 |
fault | -0.045 |
clinic | -0.044 |
lor | -0.043 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
lor | +0.061 |
ests | +0.053 |
handed | +0.048 |
neys | +0.048 |
osc | +0.048 |
Neg logit contributions | |
gust | -0.081 |
Run | -0.079 |
forth | -0.079 |
www | -0.078 |
ww | -0.073 |
Token | gave |
Token ID | 2921 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
lair | +0.031 |
fault | +0.031 |
lor | +0.030 |
ests | +0.030 |
clinic | +0.030 |
Neg logit contributions | |
Run | -0.033 |
www | -0.031 |
forth | -0.029 |
gust | -0.028 |
ww | -0.028 |
Token | him |
Token ID | 683 |
Feature activation | -8.21e+00 |
Pos logit contributions | |
forth | +0.013 |
Run | +0.012 |
www | +0.012 |
ening | +0.011 |
ging | +0.011 |
Neg logit contributions | |
lair | -0.019 |
clinic | -0.019 |
tr | -0.019 |
lor | -0.019 |
neys | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
lair | +0.181 |
lor | +0.176 |
clinic | +0.169 |
dentist | +0.163 |
fault | +0.163 |
Neg logit contributions | |
Run | -0.181 |
www | -0.173 |
ww | -0.163 |
forth | -0.155 |
ahead | -0.150 |
Token | big |
Token ID | 1263 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
lair | +0.080 |
lor | +0.076 |
dentist | +0.076 |
fault | +0.076 |
ests | +0.075 |
Neg logit contributions | |
Run | -0.101 |
www | -0.099 |
ww | -0.094 |
gust | -0.091 |
forth | -0.082 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
dentist | +0.006 |
fault | +0.006 |
aid | +0.006 |
clinic | +0.005 |
lair | +0.005 |
Neg logit contributions | |
Run | -0.019 |
www | -0.018 |
forth | -0.017 |
ww | -0.017 |
izing | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
lair | +0.028 |
wounds | +0.027 |
fault | +0.027 |
dentist | +0.027 |
lor | +0.026 |
Neg logit contributions | |
Run | -0.023 |
www | -0.021 |
forth | -0.020 |
ening | -0.020 |
ww | -0.020 |
Token | encouraged |
Token ID | 10085 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
lair | +0.002 |
fault | +0.002 |
lor | +0.002 |
ests | +0.002 |
clinic | +0.002 |
Neg logit contributions | |
Run | -0.002 |
www | -0.002 |
ww | -0.002 |
forth | -0.002 |
gust | -0.002 |
Token | thanked |
Token ID | 26280 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Run | +0.018 |
www | +0.018 |
forth | +0.017 |
ww | +0.017 |
gust | +0.016 |
Neg logit contributions | |
fault | -0.012 |
dentist | -0.012 |
lair | -0.012 |
clinic | -0.012 |
lor | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
lair | +0.052 |
lor | +0.052 |
ests | +0.051 |
fault | +0.051 |
neys | +0.050 |
Neg logit contributions | |
Run | -0.048 |
forth | -0.046 |
gust | -0.045 |
www | -0.044 |
boom | -0.041 |
Token | dad |
Token ID | 9955 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
lor | +0.074 |
ests | +0.063 |
lair | +0.062 |
clinic | +0.059 |
fault | +0.059 |
Neg logit contributions | |
Run | -0.118 |
forth | -0.117 |
gust | -0.114 |
www | -0.111 |
boom | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
dentist | +0.118 |
lair | +0.117 |
fault | +0.117 |
ests | +0.114 |
lor | +0.114 |
Neg logit contributions | |
Run | -0.102 |
www | -0.097 |
forth | -0.092 |
ww | -0.090 |
gust | -0.087 |
Token | gave |
Token ID | 2921 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
Run | +0.010 |
www | +0.010 |
forth | +0.009 |
ww | +0.009 |
gust | +0.009 |
Neg logit contributions | |
fault | -0.009 |
lair | -0.009 |
dentist | -0.009 |
clinic | -0.009 |
lor | -0.009 |
Token | him |
Token ID | 683 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
lair | +0.020 |
lor | +0.019 |
tr | +0.019 |
clinic | +0.019 |
neys | +0.019 |
Neg logit contributions | |
forth | -0.016 |
Run | -0.016 |
www | -0.015 |
gust | -0.014 |
ww | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
lair | +0.186 |
lor | +0.181 |
clinic | +0.178 |
fault | +0.174 |
dentist | +0.167 |
Neg logit contributions | |
Run | -0.165 |
www | -0.163 |
ww | -0.158 |
forth | -0.155 |
ahead | -0.144 |
Token | big |
Token ID | 1263 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
lair | +0.092 |
fault | +0.088 |
lor | +0.087 |
wounds | +0.086 |
dentist | +0.086 |
Neg logit contributions | |
Run | -0.119 |
www | -0.117 |
ww | -0.114 |
gust | -0.109 |
boom | -0.101 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
dentist | +0.009 |
fault | +0.008 |
kit | +0.007 |
clinic | +0.007 |
aid | +0.007 |
Neg logit contributions | |
Run | -0.032 |
www | -0.030 |
forth | -0.029 |
ww | -0.029 |
izing | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
lair | +0.034 |
wounds | +0.034 |
fault | +0.033 |
aj | +0.032 |
dentist | +0.032 |
Neg logit contributions | |
Run | -0.032 |
www | -0.030 |
forth | -0.030 |
gust | -0.028 |
ww | -0.028 |
Token | From |
Token ID | 3574 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
lair | +0.026 |
wounds | +0.026 |
dentist | +0.024 |
patients | +0.024 |
fault | +0.024 |
Neg logit contributions | |
Run | -0.040 |
www | -0.039 |
ww | -0.037 |
gust | -0.037 |
forth | -0.034 |
Token | comfort |
Token ID | 4467 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
fault | +0.003 |
lair | +0.003 |
dentist | +0.003 |
ests | +0.003 |
lor | +0.003 |
Neg logit contributions | |
Run | -0.004 |
www | -0.003 |
forth | -0.003 |
gust | -0.003 |
ww | -0.003 |
Token | ed |
Token ID | 276 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Run | +0.056 |
www | +0.052 |
ww | +0.049 |
forth | +0.049 |
gust | +0.047 |
Neg logit contributions | |
dentist | -0.052 |
lair | -0.052 |
fault | -0.051 |
clinic | -0.050 |
lor | -0.049 |
Token | him |
Token ID | 683 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
Run | +0.005 |
www | +0.004 |
forth | +0.004 |
ww | +0.004 |
gust | +0.004 |
Neg logit contributions | |
lair | -0.004 |
dentist | -0.004 |
fault | -0.004 |
lor | -0.004 |
ests | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
dentist | +0.109 |
ests | +0.106 |
lair | +0.105 |
lor | +0.104 |
fault | +0.102 |
Neg logit contributions | |
Run | -0.081 |
forth | -0.075 |
www | -0.072 |
ening | -0.068 |
gust | -0.068 |
Token | gave |
Token ID | 2921 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
Run | +0.021 |
forth | +0.019 |
www | +0.019 |
gust | +0.018 |
ww | +0.017 |
Neg logit contributions | |
fault | -0.019 |
ests | -0.019 |
lor | -0.019 |
lair | -0.018 |
dentist | -0.018 |
Token | him |
Token ID | 683 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
lair | +0.001 |
lor | +0.001 |
clinic | +0.001 |
dentist | +0.001 |
fault | +0.001 |
Neg logit contributions | |
Run | -0.001 |
www | -0.001 |
forth | -0.001 |
ww | -0.001 |
gust | -0.001 |
Token | something |
Token ID | 1223 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
lair | +0.196 |
lor | +0.196 |
clinic | +0.183 |
dentist | +0.182 |
tr | +0.174 |
Neg logit contributions | |
Run | -0.163 |
www | -0.148 |
ww | -0.145 |
ahead | -0.135 |
forth | -0.134 |
Token | to |
Token ID | 284 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
lor | +0.062 |
lair | +0.060 |
ests | +0.059 |
dentist | +0.059 |
clinic | +0.058 |
Neg logit contributions | |
Run | -0.071 |
www | -0.067 |
ww | -0.064 |
gust | -0.063 |
forth | -0.061 |
Token | eat |
Token ID | 4483 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
lor | +0.027 |
lair | +0.027 |
ests | +0.027 |
fault | +0.027 |
aj | +0.025 |
Neg logit contributions | |
Run | -0.026 |
www | -0.024 |
forth | -0.022 |
gust | -0.022 |
boom | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
lair | +0.014 |
dentist | +0.014 |
lor | +0.014 |
fault | +0.014 |
clinic | +0.014 |
Neg logit contributions | |
Run | -0.019 |
www | -0.018 |
forth | -0.017 |
ww | -0.017 |
gust | -0.017 |
Token | After |
Token ID | 2293 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
lair | +0.013 |
fault | +0.013 |
dentist | +0.013 |
wounds | +0.013 |
ests | +0.012 |
Neg logit contributions | |
Run | -0.018 |
www | -0.016 |
gust | -0.015 |
ww | -0.015 |
forth | -0.014 |
Token | forg |
Token ID | 5784 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
lair | +0.041 |
fault | +0.041 |
lor | +0.040 |
clinic | +0.039 |
ests | +0.038 |
Neg logit contributions | |
Run | -0.043 |
www | -0.040 |
forth | -0.038 |
gust | -0.037 |
ww | -0.036 |
Token | ave |
Token ID | 1015 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Run | +0.066 |
www | +0.063 |
ww | +0.061 |
gust | +0.060 |
forth | +0.058 |
Neg logit contributions | |
lair | -0.040 |
dentist | -0.040 |
clinic | -0.038 |
lor | -0.038 |
fault | -0.037 |
Token | him |
Token ID | 683 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
lair | +0.026 |
fault | +0.025 |
dentist | +0.025 |
lor | +0.024 |
neys | +0.024 |
Neg logit contributions | |
Run | -0.028 |
www | -0.025 |
ww | -0.024 |
forth | -0.024 |
gust | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
lor | +0.144 |
ests | +0.139 |
lair | +0.138 |
dentist | +0.135 |
fault | +0.135 |
Neg logit contributions | |
Run | -0.078 |
forth | -0.078 |
gust | -0.069 |
www | -0.069 |
ening | -0.067 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
lair | +0.003 |
fault | +0.003 |
lor | +0.003 |
ests | +0.003 |
dentist | +0.003 |
Neg logit contributions | |
Run | -0.003 |
www | -0.003 |
forth | -0.002 |
ww | -0.002 |
gust | -0.002 |
Token | him |
Token ID | 683 |
Feature activation | -8.19e+00 |
Pos logit contributions | |
lair | +0.005 |
neys | +0.005 |
fault | +0.005 |
aj | +0.005 |
dentist | +0.005 |
Neg logit contributions | |
Run | -0.004 |
forth | -0.003 |
www | -0.003 |
ww | -0.003 |
dd | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
lor | +0.201 |
lair | +0.195 |
clinic | +0.185 |
fault | +0.178 |
aj | +0.170 |
Neg logit contributions | |
Run | -0.157 |
www | -0.146 |
ww | -0.143 |
forth | -0.137 |
gust | -0.132 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
lor | +0.102 |
lair | +0.102 |
ests | +0.100 |
keeping | +0.100 |
neys | +0.100 |
Neg logit contributions | |
www | -0.097 |
ww | -0.096 |
Run | -0.095 |
gust | -0.093 |
boom | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
lair | +0.035 |
wounds | +0.034 |
aj | +0.033 |
lor | +0.033 |
clinic | +0.032 |
Neg logit contributions | |
Run | -0.021 |
after | -0.020 |
forth | -0.020 |
www | -0.020 |
ahead | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
lair | +0.009 |
dentist | +0.008 |
fault | +0.008 |
neys | +0.008 |
wounds | +0.008 |
Neg logit contributions | |
Run | -0.013 |
www | -0.012 |
ww | -0.012 |
gust | -0.012 |
forth | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
lair | +0.027 |
fault | +0.026 |
dentist | +0.025 |
wounds | +0.024 |
patients | +0.023 |
Neg logit contributions | |
Run | -0.041 |
www | -0.040 |
ww | -0.038 |
gust | -0.035 |
ang | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Run | +0.051 |
www | +0.048 |
ww | +0.046 |
gust | +0.044 |
forth | +0.043 |
Neg logit contributions | |
dentist | -0.024 |
clinic | -0.023 |
lair | -0.023 |
fault | -0.023 |
truth | -0.022 |
Token | thanked |
Token ID | 26280 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
fault | +0.039 |
ests | +0.039 |
lor | +0.038 |
lair | +0.038 |
dentist | +0.037 |
Neg logit contributions | |
Run | -0.038 |
www | -0.034 |
forth | -0.032 |
gust | -0.031 |
ww | -0.031 |
Token | him |
Token ID | 683 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
lair | +0.063 |
tr | +0.061 |
fault | +0.061 |
ests | +0.061 |
lor | +0.060 |
Neg logit contributions | |
Run | -0.049 |
forth | -0.045 |
gust | -0.044 |
www | -0.044 |
boom | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ests | +0.172 |
fault | +0.169 |
neys | +0.168 |
lor | +0.167 |
lair | +0.163 |
Neg logit contributions | |
forth | -0.084 |
Run | -0.078 |
ening | -0.073 |
ging | -0.072 |
ahead | -0.071 |
Token | gave |
Token ID | 2921 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
Run | +0.014 |
forth | +0.013 |
www | +0.013 |
gust | +0.012 |
ww | +0.012 |
Neg logit contributions | |
fault | -0.015 |
lair | -0.014 |
dentist | -0.014 |
ests | -0.014 |
lor | -0.014 |
Token | him |
Token ID | 683 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
lair | +0.021 |
clinic | +0.020 |
lor | +0.020 |
tr | +0.020 |
fault | +0.020 |
Neg logit contributions | |
Run | -0.015 |
forth | -0.015 |
www | -0.014 |
ww | -0.013 |
dd | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
lor | +0.216 |
lair | +0.216 |
clinic | +0.201 |
tr | +0.197 |
fault | +0.195 |
Neg logit contributions | |
Run | -0.128 |
www | -0.117 |
ww | -0.115 |
ahead | -0.113 |
forth | -0.111 |
Token | big |
Token ID | 1263 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
lair | +0.104 |
fault | +0.098 |
wounds | +0.097 |
neys | +0.097 |
dentist | +0.096 |
Neg logit contributions | |
www | -0.126 |
Run | -0.125 |
ww | -0.124 |
gust | -0.115 |
boom | -0.105 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
dentist | +0.013 |
lair | +0.013 |
fault | +0.012 |
clinic | +0.012 |
aid | +0.012 |
Neg logit contributions | |
Run | -0.035 |
www | -0.033 |
ww | -0.032 |
forth | -0.032 |
gust | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
lair | +0.036 |
fault | +0.035 |
wounds | +0.034 |
dentist | +0.033 |
aj | +0.032 |
Neg logit contributions | |
Run | -0.030 |
www | -0.028 |
forth | -0.026 |
ahead | -0.026 |
ww | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
lair | +0.023 |
wounds | +0.023 |
fault | +0.022 |
dentist | +0.022 |
ests | +0.022 |
Neg logit contributions | |
Run | -0.032 |
www | -0.030 |
ww | -0.028 |
gust | -0.028 |
forth | -0.026 |
Token | her |
Token ID | 607 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
Run | +0.047 |
www | +0.045 |
gust | +0.043 |
ww | +0.042 |
forth | +0.042 |
Neg logit contributions | |
lair | -0.034 |
fault | -0.033 |
dentist | -0.032 |
lor | -0.032 |
clinic | -0.032 |
Token | face |
Token ID | 1986 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
lair | +0.055 |
fault | +0.053 |
dentist | +0.053 |
lor | +0.052 |
ests | +0.051 |
Neg logit contributions | |
Run | -0.078 |
gust | -0.076 |
www | -0.075 |
forth | -0.075 |
ging | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
lair | +0.020 |
fault | +0.019 |
dentist | +0.019 |
ests | +0.019 |
wounds | +0.019 |
Neg logit contributions | |
Run | -0.017 |
www | -0.016 |
forth | -0.015 |
gust | -0.015 |
ww | -0.015 |
Token | asked |
Token ID | 1965 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
Run | +0.019 |
www | +0.018 |
forth | +0.017 |
ww | +0.017 |
gust | +0.016 |
Neg logit contributions | |
fault | -0.018 |
lair | -0.018 |
dentist | -0.018 |
lor | -0.017 |
ests | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
lair | +0.084 |
lor | +0.082 |
fault | +0.081 |
clinic | +0.079 |
ests | +0.078 |
Neg logit contributions | |
Run | -0.082 |
www | -0.080 |
forth | -0.076 |
gust | -0.075 |
ww | -0.072 |
Token | daughter |
Token ID | 4957 |
Feature activation | -8.16e+00 |
Pos logit contributions | |
lor | +0.124 |
age | +0.113 |
lair | +0.111 |
ests | +0.109 |
fault | +0.108 |
Neg logit contributions | |
www | -0.141 |
forth | -0.141 |
Run | -0.136 |
gust | -0.131 |
ww | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
lair | +0.188 |
wounds | +0.187 |
lor | +0.186 |
ests | +0.185 |
dentist | +0.179 |
Neg logit contributions | |
www | -0.144 |
forth | -0.143 |
Run | -0.141 |
ahead | -0.137 |
after | -0.134 |
Token | " |
Token ID | 366 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
lair | +0.058 |
fault | +0.057 |
dentist | +0.056 |
ests | +0.055 |
lor | +0.055 |
Neg logit contributions | |
Run | -0.079 |
www | -0.074 |
ww | -0.069 |
forth | -0.069 |
gust | -0.068 |
Token | Do |
Token ID | 5211 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
Run | +0.001 |
www | +0.001 |
ww | +0.001 |
gust | +0.001 |
forth | +0.001 |
Neg logit contributions | |
dentist | -0.001 |
lair | -0.001 |
lor | -0.001 |
fault | -0.001 |
clinic | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
www | +0.001 |
Run | +0.001 |
ww | +0.001 |
gust | +0.000 |
forth | +0.000 |
Neg logit contributions | |
lair | -0.001 |
dentist | -0.001 |
fault | -0.001 |
clinic | -0.001 |
aid | -0.001 |
Token | want |
Token ID | 765 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
dentist | +0.024 |
fault | +0.023 |
aid | +0.023 |
truth | +0.023 |
lair | +0.022 |
Neg logit contributions | |
Run | -0.029 |
www | -0.027 |
ww | -0.026 |
izing | -0.025 |
forth | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
Run | +0.016 |
www | +0.015 |
ww | +0.014 |
forth | +0.014 |
gust | +0.014 |
Neg logit contributions | |
dentist | -0.015 |
lair | -0.015 |
fault | -0.015 |
clinic | -0.015 |
lor | -0.015 |
Token | circles |
Token ID | 13332 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Run | +0.001 |
www | +0.001 |
ww | +0.001 |
forth | +0.001 |
gust | +0.001 |
Neg logit contributions | |
dentist | -0.001 |
lair | -0.001 |
fault | -0.001 |
lor | -0.001 |
clinic | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
Run | +0.032 |
www | +0.030 |
ww | +0.028 |
forth | +0.027 |
gust | +0.027 |
Neg logit contributions | |
dentist | -0.033 |
lair | -0.033 |
fault | -0.033 |
clinic | -0.032 |
lor | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Run | +0.018 |
www | +0.017 |
ww | +0.016 |
forth | +0.016 |
gust | +0.016 |
Neg logit contributions | |
dentist | -0.015 |
lair | -0.014 |
fault | -0.014 |
clinic | -0.014 |
lor | -0.014 |
Token | squ |
Token ID | 2809 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
Run | +0.047 |
www | +0.044 |
ww | +0.041 |
forth | +0.039 |
gust | +0.039 |
Neg logit contributions | |
dentist | -0.046 |
lair | -0.046 |
fault | -0.045 |
clinic | -0.044 |
lor | -0.044 |
Token | igg |
Token ID | 6950 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
Run | +0.169 |
www | +0.157 |
ww | +0.141 |
gust | +0.128 |
Uh | +0.127 |
Neg logit contributions | |
wounds | -0.131 |
fault | -0.131 |
aj | -0.129 |
ests | -0.127 |
osc | -0.126 |
Token | les |
Token ID | 829 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
Run | +0.134 |
www | +0.118 |
gust | +0.110 |
Uh | +0.105 |
ww | +0.105 |
Neg logit contributions | |
fault | -0.161 |
wounds | -0.152 |
feelings | -0.150 |
osc | -0.149 |
ests | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
dentist | +0.001 |
lair | +0.001 |
fault | +0.001 |
lor | +0.001 |
clinic | +0.001 |
Neg logit contributions | |
Run | -0.002 |
www | -0.002 |
ww | -0.002 |
forth | -0.002 |
gust | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
lair | +0.007 |
dentist | +0.007 |
lor | +0.007 |
wounds | +0.007 |
clinic | +0.006 |
Neg logit contributions | |
Run | -0.009 |
www | -0.008 |
gust | -0.008 |
ww | -0.008 |
boom | -0.008 |
Token | all |
Token ID | 477 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Run | +0.022 |
www | +0.021 |
ww | +0.020 |
gust | +0.019 |
forth | +0.019 |
Neg logit contributions | |
dentist | -0.016 |
lair | -0.015 |
fault | -0.015 |
clinic | -0.015 |
ests | -0.014 |
Token | laughed |
Token ID | 13818 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Run | +0.049 |
www | +0.046 |
ww | +0.044 |
gust | +0.042 |
forth | +0.041 |
Neg logit contributions | |
fault | -0.028 |
dentist | -0.028 |
lair | -0.027 |
ests | -0.026 |
osc | -0.026 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
Run | +0.002 |
www | +0.002 |
gust | +0.002 |
ww | +0.002 |
boom | +0.002 |
Neg logit contributions | |
fault | -0.002 |
dentist | -0.002 |
wounds | -0.002 |
lor | -0.002 |
lair | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Run | +0.104 |
www | +0.103 |
ww | +0.095 |
forth | +0.091 |
ang | +0.089 |
Neg logit contributions | |
dentist | -0.086 |
lair | -0.081 |
clinic | -0.078 |
fault | -0.077 |
parents | -0.076 |
Token | he |
Token ID | 339 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
www | +0.073 |
Run | +0.072 |
ww | +0.068 |
forth | +0.064 |
gust | +0.063 |
Neg logit contributions | |
dentist | -0.052 |
lair | -0.049 |
clinic | -0.046 |
fault | -0.046 |
wounds | -0.045 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Run | +0.031 |
www | +0.029 |
ww | +0.028 |
forth | +0.027 |
gust | +0.027 |
Neg logit contributions | |
dentist | -0.021 |
fault | -0.021 |
lair | -0.021 |
clinic | -0.020 |
lor | -0.020 |
Token | something |
Token ID | 1223 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Run | +0.071 |
www | +0.065 |
gust | +0.064 |
forth | +0.061 |
ww | +0.061 |
Neg logit contributions | |
lor | -0.049 |
dentist | -0.049 |
ests | -0.048 |
fault | -0.048 |
lair | -0.048 |
Token | tick |
Token ID | 4378 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Run | +0.034 |
www | +0.033 |
ww | +0.031 |
forth | +0.029 |
gust | +0.029 |
Neg logit contributions | |
dentist | -0.032 |
lair | -0.031 |
fault | -0.031 |
clinic | -0.030 |
wounds | -0.030 |
Token | ling |
Token ID | 1359 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Run | +0.100 |
www | +0.096 |
ww | +0.088 |
gust | +0.086 |
Uh | +0.078 |
Neg logit contributions | |
lor | -0.131 |
wounds | -0.129 |
ests | -0.129 |
osc | -0.129 |
dentist | -0.129 |
Token | his |
Token ID | 465 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Run | +0.057 |
www | +0.055 |
ww | +0.052 |
gust | +0.051 |
forth | +0.050 |
Neg logit contributions | |
dentist | -0.033 |
lair | -0.033 |
fault | -0.032 |
clinic | -0.031 |
lor | -0.031 |
Token | head |
Token ID | 1182 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
dentist | +0.038 |
clinic | +0.037 |
lor | +0.037 |
ests | +0.037 |
lair | +0.035 |
Neg logit contributions | |
Run | -0.038 |
gust | -0.037 |
forth | -0.037 |
www | -0.037 |
ww | -0.035 |
Token | ! |
Token ID | 0 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Run | +0.015 |
www | +0.015 |
ww | +0.014 |
gust | +0.014 |
forth | +0.014 |
Neg logit contributions | |
dentist | -0.008 |
lair | -0.007 |
fault | -0.007 |
clinic | -0.007 |
lor | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
fault | +0.000 |
lair | +0.000 |
dentist | +0.000 |
wounds | +0.000 |
clinic | +0.000 |
Neg logit contributions | |
Run | -0.000 |
www | -0.000 |
gust | -0.000 |
ww | -0.000 |
boom | -0.000 |
Token | wherever |
Token ID | 14530 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
Run | +0.027 |
www | +0.026 |
forth | +0.024 |
ww | +0.023 |
gust | +0.023 |
Neg logit contributions | |
dentist | -0.047 |
lair | -0.047 |
clinic | -0.046 |
fault | -0.045 |
wounds | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Run | +0.009 |
www | +0.009 |
gust | +0.008 |
ww | +0.008 |
forth | +0.008 |
Neg logit contributions | |
lair | -0.011 |
fault | -0.011 |
dentist | -0.011 |
lor | -0.011 |
ests | -0.011 |
Token | went |
Token ID | 1816 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Run | +0.046 |
www | +0.042 |
ww | +0.039 |
forth | +0.039 |
gust | +0.039 |
Neg logit contributions | |
fault | -0.050 |
dentist | -0.049 |
lair | -0.049 |
clinic | -0.047 |
lor | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Run | +0.075 |
www | +0.072 |
ww | +0.068 |
gust | +0.066 |
forth | +0.066 |
Neg logit contributions | |
dentist | -0.035 |
lair | -0.034 |
fault | -0.034 |
clinic | -0.034 |
lor | -0.033 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
lair | +0.004 |
wounds | +0.004 |
dentist | +0.004 |
fault | +0.004 |
lor | +0.004 |
Neg logit contributions | |
Run | -0.006 |
www | -0.006 |
gust | -0.005 |
ww | -0.005 |
forth | -0.005 |
Token | ad |
Token ID | 512 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
Run | +0.026 |
www | +0.025 |
ww | +0.024 |
gust | +0.024 |
forth | +0.023 |
Neg logit contributions | |
dentist | -0.015 |
lair | -0.014 |
fault | -0.014 |
clinic | -0.014 |
lor | -0.014 |
Token | ored |
Token ID | 1850 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
Run | +0.127 |
www | +0.120 |
ww | +0.113 |
forth | +0.111 |
gust | +0.110 |
Neg logit contributions | |
dentist | -0.097 |
lor | -0.095 |
clinic | -0.094 |
fault | -0.091 |
ests | -0.091 |
Token | her |
Token ID | 607 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
Run | +0.062 |
www | +0.058 |
ww | +0.055 |
forth | +0.054 |
gust | +0.054 |
Neg logit contributions | |
dentist | -0.060 |
lair | -0.059 |
fault | -0.058 |
lor | -0.057 |
clinic | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
lor | +0.072 |
lair | +0.071 |
ests | +0.069 |
dentist | +0.069 |
clinic | +0.065 |
Neg logit contributions | |
Run | -0.063 |
www | -0.062 |
gust | -0.062 |
ww | -0.059 |
forth | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Run | +0.007 |
www | +0.007 |
ww | +0.006 |
gust | +0.006 |
forth | +0.006 |
Neg logit contributions | |
dentist | -0.007 |
lair | -0.007 |
fault | -0.007 |
lor | -0.007 |
clinic | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Run | +0.060 |
www | +0.056 |
forth | +0.053 |
ww | +0.052 |
gust | +0.052 |
Neg logit contributions | |
lair | -0.064 |
dentist | -0.064 |
fault | -0.064 |
lor | -0.063 |
ests | -0.062 |
Token | them |
Token ID | 606 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
lair | +0.012 |
dentist | +0.012 |
lor | +0.012 |
ests | +0.012 |
clinic | +0.012 |
Neg logit contributions | |
Run | -0.011 |
www | -0.011 |
ww | -0.010 |
forth | -0.010 |
gust | -0.010 |
Token | food |
Token ID | 2057 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
dentist | +0.114 |
lair | +0.110 |
lor | +0.108 |
ests | +0.106 |
clinic | +0.106 |
Neg logit contributions | |
Run | -0.110 |
www | -0.107 |
ww | -0.103 |
forth | -0.103 |
boom | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
dentist | +0.047 |
lair | +0.046 |
lor | +0.045 |
ests | +0.045 |
fault | +0.044 |
Neg logit contributions | |
Run | -0.045 |
www | -0.044 |
ww | -0.042 |
forth | -0.041 |
boom | -0.038 |
Token | But |
Token ID | 887 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Run | +0.004 |
www | +0.004 |
ww | +0.003 |
gust | +0.003 |
forth | +0.003 |
Neg logit contributions | |
lair | -0.003 |
dentist | -0.003 |
fault | -0.003 |
lor | -0.003 |
ests | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Run | +0.045 |
www | +0.043 |
ww | +0.040 |
gust | +0.038 |
forth | +0.036 |
Neg logit contributions | |
dentist | -0.050 |
lair | -0.048 |
fault | -0.048 |
clinic | -0.047 |
wounds | -0.046 |
Token | sw |
Token ID | 1509 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
Run | +0.009 |
www | +0.009 |
ww | +0.008 |
gust | +0.008 |
forth | +0.008 |
Neg logit contributions | |
dentist | -0.011 |
fault | -0.011 |
lair | -0.011 |
clinic | -0.011 |
wounds | -0.011 |
Token | an |
Token ID | 272 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Run | +0.123 |
www | +0.114 |
ww | +0.108 |
gust | +0.107 |
forth | +0.104 |
Neg logit contributions | |
fault | -0.099 |
lair | -0.098 |
dentist | -0.095 |
clinic | -0.094 |
lor | -0.094 |
Token | is |
Token ID | 318 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
dentist | +0.006 |
lair | +0.006 |
ests | +0.006 |
fault | +0.006 |
lor | +0.006 |
Neg logit contributions | |
Run | -0.008 |
www | -0.008 |
ww | -0.007 |
forth | -0.007 |
gust | -0.007 |
Token | very |
Token ID | 845 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
dentist | +0.001 |
ests | +0.001 |
lair | +0.001 |
lor | +0.001 |
fault | +0.001 |
Neg logit contributions | |
Run | -0.002 |
www | -0.002 |
ww | -0.002 |
forth | -0.002 |
gust | -0.002 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Run | +0.037 |
www | +0.034 |
forth | +0.033 |
gust | +0.032 |
ww | +0.032 |
Neg logit contributions | |
dentist | -0.025 |
lair | -0.025 |
fault | -0.024 |
clinic | -0.024 |
wounds | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
dentist | +0.003 |
lair | +0.003 |
lor | +0.003 |
clinic | +0.003 |
wounds | +0.003 |
Neg logit contributions | |
Run | -0.003 |
www | -0.003 |
ww | -0.003 |
forth | -0.003 |
gust | -0.003 |
Token | don |
Token ID | 836 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Run | +0.017 |
www | +0.016 |
ww | +0.015 |
forth | +0.014 |
gust | +0.014 |
Neg logit contributions | |
dentist | -0.019 |
lair | -0.019 |
fault | -0.018 |
lor | -0.018 |
clinic | -0.018 |
Token | 't |
Token ID | 470 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Run | +0.037 |
www | +0.034 |
forth | +0.033 |
ww | +0.033 |
gust | +0.033 |
Neg logit contributions | |
lor | -0.015 |
truth | -0.015 |
dentist | -0.015 |
clinic | -0.013 |
Her | -0.013 |
Token | want |
Token ID | 765 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Run | +0.029 |
www | +0.027 |
ww | +0.026 |
gust | +0.025 |
forth | +0.025 |
Neg logit contributions | |
dentist | -0.022 |
fault | -0.022 |
clinic | -0.021 |
lair | -0.021 |
truth | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
dentist | +0.011 |
lair | +0.011 |
fault | +0.010 |
clinic | +0.010 |
lor | +0.010 |
Neg logit contributions | |
Run | -0.015 |
www | -0.015 |
ww | -0.014 |
gust | -0.014 |
forth | -0.013 |
Token | ! |
Token ID | 0 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
dentist | +0.033 |
lair | +0.032 |
fault | +0.032 |
clinic | +0.031 |
lor | +0.031 |
Neg logit contributions | |
Run | -0.039 |
www | -0.037 |
ww | -0.035 |
forth | -0.034 |
gust | -0.034 |
Token | â |
Token ID | 22940 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
Run | +0.005 |
www | +0.005 |
ww | +0.005 |
gust | +0.004 |
forth | +0.004 |
Neg logit contributions | |
lair | -0.006 |
dentist | -0.006 |
fault | -0.006 |
wounds | -0.005 |
clinic | -0.005 |
Token | € |
Token ID | 26391 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Run | +0.174 |
www | +0.156 |
gust | +0.155 |
ww | +0.150 |
forth | +0.149 |
Neg logit contributions | |
lor | -0.130 |
dentist | -0.129 |
clinic | -0.126 |
osc | -0.126 |
age | -0.125 |
Token | Play |
Token ID | 3811 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Run | +0.033 |
www | +0.032 |
ww | +0.030 |
forth | +0.028 |
gust | +0.028 |
Neg logit contributions | |
dentist | -0.028 |
lair | -0.028 |
fault | -0.027 |
wounds | -0.026 |
clinic | -0.026 |
Token | shook |
Token ID | 14682 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Run | +0.034 |
www | +0.032 |
ww | +0.030 |
gust | +0.029 |
forth | +0.029 |
Neg logit contributions | |
dentist | -0.031 |
lair | -0.030 |
fault | -0.030 |
clinic | -0.030 |
lor | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
Run | +0.054 |
www | +0.050 |
ww | +0.047 |
gust | +0.046 |
forth | +0.044 |
Neg logit contributions | |
dentist | -0.053 |
fault | -0.052 |
lair | -0.052 |
clinic | -0.050 |
wounds | -0.050 |
Token | head |
Token ID | 1182 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
dentist | +0.058 |
lair | +0.056 |
ests | +0.055 |
clinic | +0.054 |
fault | +0.054 |
Neg logit contributions | |
Run | -0.068 |
www | -0.065 |
forth | -0.063 |
ww | -0.062 |
gust | -0.060 |
Token | pretty |
Token ID | 2495 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
Run | +0.035 |
www | +0.033 |
ww | +0.031 |
forth | +0.031 |
gust | +0.029 |
Neg logit contributions | |
fault | -0.020 |
dentist | -0.020 |
Her | -0.020 |
truth | -0.020 |
lair | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Run | +0.081 |
www | +0.078 |
ww | +0.074 |
gust | +0.072 |
forth | +0.070 |
Neg logit contributions | |
dentist | -0.045 |
lair | -0.044 |
fault | -0.044 |
lor | -0.042 |
clinic | -0.041 |
Token | The |
Token ID | 383 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Run | +0.009 |
www | +0.008 |
gust | +0.008 |
ww | +0.007 |
forth | +0.007 |
Neg logit contributions | |
lair | -0.008 |
fault | -0.008 |
lor | -0.008 |
wounds | -0.008 |
dentist | -0.007 |
Token | doll |
Token ID | 3654 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Run | +0.004 |
www | +0.003 |
gust | +0.003 |
forth | +0.003 |
ww | +0.003 |
Neg logit contributions | |
lair | -0.003 |
fault | -0.003 |
lor | -0.003 |
ests | -0.003 |
dentist | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
dentist | +0.023 |
fault | +0.022 |
lair | +0.022 |
lor | +0.022 |
ests | +0.022 |
Neg logit contributions | |
Run | -0.028 |
www | -0.027 |
forth | -0.025 |
ww | -0.025 |
gust | -0.025 |
Token | so |
Token ID | 523 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ests | +0.009 |
lor | +0.009 |
dentist | +0.009 |
fault | +0.009 |
lair | +0.009 |
Neg logit contributions | |
Run | -0.009 |
www | -0.008 |
gust | -0.008 |
forth | -0.008 |
ww | -0.008 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Run | +0.027 |
www | +0.025 |
forth | +0.024 |
ww | +0.024 |
gust | +0.023 |
Neg logit contributions | |
dentist | -0.018 |
fault | -0.017 |
lair | -0.017 |
Her | -0.016 |
clinic | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
Run | +0.047 |
www | +0.045 |
ww | +0.042 |
forth | +0.041 |
gust | +0.041 |
Neg logit contributions | |
dentist | -0.030 |
lair | -0.030 |
fault | -0.030 |
clinic | -0.029 |
lor | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Run | +0.012 |
www | +0.011 |
gust | +0.011 |
ww | +0.010 |
forth | +0.009 |
Neg logit contributions | |
lair | -0.011 |
fault | -0.011 |
wounds | -0.010 |
dentist | -0.010 |
lor | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
fault | +0.016 |
lair | +0.016 |
dentist | +0.015 |
clinic | +0.014 |
wounds | +0.014 |
Neg logit contributions | |
Run | -0.036 |
www | -0.035 |
ww | -0.032 |
gust | -0.031 |
ang | -0.030 |
Token | The |
Token ID | 464 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Run | +0.032 |
gust | +0.032 |
ening | +0.032 |
forth | +0.031 |
www | +0.031 |
Neg logit contributions | |
dentist | -0.011 |
Her | -0.010 |
lor | -0.010 |
clinic | -0.009 |
aid | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
lair | +0.041 |
fault | +0.040 |
dentist | +0.037 |
wounds | +0.036 |
clinic | +0.034 |
Neg logit contributions | |
Run | -0.072 |
www | -0.068 |
ww | -0.064 |
gust | -0.063 |
dd | -0.060 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Run | +0.004 |
www | +0.003 |
ww | +0.003 |
gust | +0.003 |
forth | +0.003 |
Neg logit contributions | |
fault | -0.003 |
wounds | -0.003 |
lair | -0.003 |
dentist | -0.003 |
patients | -0.003 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Run | +0.003 |
www | +0.003 |
ww | +0.003 |
gust | +0.003 |
forth | +0.003 |
Neg logit contributions | |
dentist | -0.003 |
lair | -0.003 |
clinic | -0.003 |
fault | -0.003 |
lor | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
fault | +0.071 |
lor | +0.069 |
lair | +0.069 |
clinic | +0.068 |
neys | +0.065 |
Neg logit contributions | |
Run | -0.068 |
gust | -0.055 |
www | -0.053 |
ww | -0.051 |
boom | -0.049 |
Token | time |
Token ID | 640 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Run | +0.028 |
www | +0.026 |
ww | +0.024 |
forth | +0.024 |
gust | +0.023 |
Neg logit contributions | |
dentist | -0.028 |
lair | -0.028 |
fault | -0.028 |
clinic | -0.027 |
aid | -0.026 |
Token | there |
Token ID | 612 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Run | +0.044 |
www | +0.042 |
forth | +0.039 |
ww | +0.039 |
gust | +0.037 |
Neg logit contributions | |
fault | -0.037 |
dentist | -0.037 |
lair | -0.036 |
lor | -0.035 |
Her | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Run | +0.027 |
www | +0.025 |
gust | +0.024 |
ww | +0.023 |
forth | +0.023 |
Neg logit contributions | |
lair | -0.019 |
dentist | -0.018 |
fault | -0.018 |
clinic | -0.018 |
wounds | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
Run | +0.010 |
www | +0.009 |
ww | +0.009 |
forth | +0.009 |
gust | +0.009 |
Neg logit contributions | |
dentist | -0.004 |
lair | -0.004 |
fault | -0.004 |
clinic | -0.004 |
lor | -0.004 |
Token | large |
Token ID | 1588 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
Run | +0.024 |
www | +0.022 |
forth | +0.021 |
ening | +0.021 |
ww | +0.021 |
Neg logit contributions | |
dentist | -0.013 |
clinic | -0.012 |
doctor | -0.012 |
granddaughter | -0.011 |
aid | -0.011 |
Token | bear |
Token ID | 6842 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Run | +0.098 |
www | +0.089 |
dd | +0.085 |
ging | +0.084 |
ww | +0.084 |
Neg logit contributions | |
dentist | -0.056 |
office | -0.051 |
clinic | -0.050 |
doctor | -0.049 |
parents | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Run | +0.003 |
www | +0.003 |
ww | +0.003 |
ang | +0.003 |
forth | +0.003 |
Neg logit contributions | |
fault | -0.003 |
wounds | -0.003 |
dentist | -0.003 |
lair | -0.003 |
ests | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
dentist | +0.011 |
lair | +0.010 |
fault | +0.010 |
clinic | +0.010 |
lor | +0.010 |
Neg logit contributions | |
Run | -0.017 |
www | -0.016 |
ww | -0.015 |
forth | -0.015 |
gust | -0.014 |
Token | been |
Token ID | 587 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
ests | +0.008 |
clinic | +0.008 |
lor | +0.007 |
aj | +0.007 |
fault | +0.007 |
Neg logit contributions | |
Run | -0.009 |
www | -0.009 |
gust | -0.008 |
ww | -0.008 |
boom | -0.008 |
Token | stuck |
Token ID | 7819 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
Run | +0.010 |
www | +0.010 |
ww | +0.009 |
forth | +0.009 |
gust | +0.009 |
Neg logit contributions | |
dentist | -0.010 |
fault | -0.010 |
lor | -0.009 |
lair | -0.009 |
ests | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Run | +0.088 |
www | +0.084 |
ww | +0.080 |
gust | +0.076 |
forth | +0.074 |
Neg logit contributions | |
lair | -0.057 |
fault | -0.057 |
dentist | -0.055 |
clinic | -0.052 |
aid | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Run | +0.010 |
www | +0.009 |
gust | +0.008 |
ww | +0.008 |
forth | +0.008 |
Neg logit contributions | |
lor | -0.008 |
dentist | -0.007 |
ests | -0.007 |
fault | -0.007 |
clinic | -0.007 |
Token | same |
Token ID | 976 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Run | +0.039 |
www | +0.037 |
ww | +0.035 |
forth | +0.034 |
gust | +0.034 |
Neg logit contributions | |
dentist | -0.032 |
lair | -0.032 |
fault | -0.031 |
clinic | -0.031 |
lor | -0.030 |
Token | spot |
Token ID | 4136 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
Run | +0.047 |
www | +0.044 |
ww | +0.042 |
forth | +0.040 |
gust | +0.039 |
Neg logit contributions | |
lair | -0.033 |
dentist | -0.033 |
clinic | -0.031 |
fault | -0.031 |
aid | -0.031 |
Token | for |
Token ID | 329 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
dentist | +0.017 |
lair | +0.017 |
lor | +0.017 |
fault | +0.016 |
clinic | +0.016 |
Neg logit contributions | |
Run | -0.023 |
www | -0.022 |
forth | -0.021 |
ww | -0.021 |
gust | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
fault | +0.016 |
lair | +0.016 |
lor | +0.016 |
dentist | +0.016 |
ests | +0.015 |
Neg logit contributions | |
Run | -0.026 |
www | -0.024 |
gust | -0.023 |
ww | -0.023 |
forth | -0.022 |
Token | long |
Token ID | 890 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
dentist | +0.029 |
lair | +0.029 |
clinic | +0.028 |
fault | +0.028 |
aid | +0.028 |
Neg logit contributions | |
Run | -0.029 |
www | -0.027 |
forth | -0.025 |
ww | -0.025 |
gust | -0.023 |
Token | time |
Token ID | 640 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
Run | +0.066 |
www | +0.061 |
ww | +0.057 |
forth | +0.056 |
izing | +0.053 |
Neg logit contributions | |
dentist | -0.054 |
lair | -0.054 |
aid | -0.053 |
clinic | -0.052 |
fault | -0.052 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Run | +0.009 |
www | +0.009 |
ww | +0.008 |
forth | +0.008 |
gust | +0.008 |
Neg logit contributions | |
fault | -0.005 |
dentist | -0.005 |
lair | -0.005 |
ests | -0.005 |
clinic | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
lor | +0.028 |
clinic | +0.023 |
dentist | +0.023 |
lair | +0.022 |
ests | +0.022 |
Neg logit contributions | |
Run | -0.050 |
www | -0.047 |
forth | -0.046 |
boom | -0.045 |
ww | -0.045 |
Token | play |
Token ID | 711 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
lor | +0.025 |
lair | +0.024 |
dentist | +0.024 |
fault | +0.024 |
clinic | +0.022 |
Neg logit contributions | |
Run | -0.024 |
www | -0.023 |
forth | -0.022 |
gust | -0.021 |
ww | -0.021 |
Token | outside |
Token ID | 2354 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
Run | +0.009 |
www | +0.008 |
forth | +0.007 |
ww | +0.007 |
gust | +0.007 |
Neg logit contributions | |
dentist | -0.011 |
fault | -0.011 |
lair | -0.010 |
lor | -0.010 |
clinic | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Run | +0.021 |
www | +0.021 |
ww | +0.020 |
gust | +0.019 |
forth | +0.018 |
Neg logit contributions | |
lair | -0.013 |
dentist | -0.013 |
fault | -0.013 |
clinic | -0.013 |
ests | -0.012 |
Token | One |
Token ID | 1881 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
dentist | +0.002 |
lair | +0.002 |
fault | +0.002 |
lor | +0.002 |
clinic | +0.002 |
Neg logit contributions | |
Run | -0.005 |
www | -0.004 |
ww | -0.004 |
gust | -0.004 |
forth | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
Run | +0.017 |
www | +0.016 |
ging | +0.016 |
izing | +0.015 |
forth | +0.015 |
Neg logit contributions | |
tr | -0.016 |
dentist | -0.016 |
aid | -0.016 |
story | -0.015 |
Her | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Run | +0.100 |
www | +0.095 |
forth | +0.094 |
gust | +0.089 |
ang | +0.089 |
Neg logit contributions | |
fault | -0.045 |
Her | -0.045 |
to | -0.044 |
parents | -0.044 |
names | -0.040 |
Token | John |
Token ID | 1757 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
www | +0.064 |
Run | +0.063 |
ww | +0.062 |
ang | +0.060 |
forth | +0.058 |
Neg logit contributions | |
dentist | -0.039 |
Her | -0.037 |
grandma | -0.037 |
parents | -0.037 |
address | -0.036 |
Token | brought |
Token ID | 3181 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
Run | +0.056 |
www | +0.054 |
ww | +0.051 |
gust | +0.050 |
forth | +0.049 |
Neg logit contributions | |
dentist | -0.039 |
lair | -0.038 |
fault | -0.037 |
clinic | -0.036 |
aid | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Run | +0.002 |
www | +0.002 |
ww | +0.002 |
forth | +0.002 |
gust | +0.002 |
Neg logit contributions | |
dentist | -0.001 |
clinic | -0.001 |
lair | -0.001 |
lor | -0.001 |
fault | -0.001 |
Token | stay |
Token ID | 2652 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
dentist | +0.016 |
lair | +0.016 |
fault | +0.016 |
ests | +0.015 |
lor | +0.015 |
Neg logit contributions | |
Run | -0.025 |
www | -0.024 |
ww | -0.022 |
forth | -0.022 |
gust | -0.022 |
Token | with |
Token ID | 351 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Run | +0.033 |
www | +0.031 |
forth | +0.029 |
ww | +0.029 |
gust | +0.028 |
Neg logit contributions | |
dentist | -0.034 |
fault | -0.033 |
lair | -0.033 |
lor | -0.032 |
ests | -0.032 |
Token | me |
Token ID | 502 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
lair | +0.014 |
dentist | +0.014 |
ests | +0.014 |
fault | +0.014 |
clinic | +0.014 |
Neg logit contributions | |
Run | -0.007 |
www | -0.007 |
ww | -0.007 |
forth | -0.006 |
gust | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
dentist | +0.068 |
lair | +0.066 |
fault | +0.066 |
ests | +0.065 |
lor | +0.064 |
Neg logit contributions | |
www | -0.054 |
Run | -0.053 |
forth | -0.050 |
ww | -0.050 |
boom | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Run | +0.008 |
www | +0.007 |
forth | +0.007 |
ww | +0.007 |
gust | +0.006 |
Neg logit contributions | |
ests | -0.008 |
lor | -0.008 |
fault | -0.008 |
lair | -0.008 |
dentist | -0.008 |
Token | other |
Token ID | 584 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
dentist | +0.023 |
lor | +0.023 |
lair | +0.022 |
fault | +0.022 |
ests | +0.022 |
Neg logit contributions | |
Run | -0.027 |
www | -0.026 |
ww | -0.024 |
gust | -0.023 |
forth | -0.023 |
Token | pengu |
Token ID | 38373 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Run | +0.008 |
www | +0.008 |
ww | +0.007 |
gust | +0.007 |
forth | +0.007 |
Neg logit contributions | |
dentist | -0.005 |
lair | -0.005 |
clinic | -0.005 |
fault | -0.005 |
ests | -0.005 |
Token | ins |
Token ID | 1040 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Run | +0.041 |
www | +0.039 |
ww | +0.037 |
forth | +0.035 |
gust | +0.035 |
Neg logit contributions | |
dentist | -0.040 |
lair | -0.039 |
fault | -0.039 |
clinic | -0.038 |
lor | -0.038 |
Token | ." |
Token ID | 526 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
dentist | +0.009 |
lair | +0.008 |
lor | +0.008 |
aid | +0.008 |
wounds | +0.008 |
Neg logit contributions | |
Run | -0.009 |
www | -0.009 |
ww | -0.008 |
forth | -0.008 |
boom | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
lair | +0.019 |
dentist | +0.018 |
fault | +0.017 |
clinic | +0.017 |
lor | +0.016 |
Neg logit contributions | |
Run | -0.016 |
www | -0.015 |
ww | -0.014 |
gust | -0.014 |
forth | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
lair | +0.024 |
fault | +0.024 |
dentist | +0.023 |
wounds | +0.021 |
clinic | +0.021 |
Neg logit contributions | |
Run | -0.037 |
www | -0.035 |
ww | -0.033 |
ang | -0.031 |
dd | -0.031 |
Token | store |
Token ID | 3650 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
www | +0.035 |
Run | +0.034 |
ww | +0.033 |
forth | +0.032 |
gust | +0.031 |
Neg logit contributions | |
fault | -0.028 |
lor | -0.028 |
ests | -0.027 |
wounds | -0.027 |
lair | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
lor | +0.029 |
lair | +0.029 |
dentist | +0.029 |
wounds | +0.029 |
ests | +0.029 |
Neg logit contributions | |
Run | -0.014 |
forth | -0.013 |
www | -0.013 |
gust | -0.013 |
ww | -0.012 |
Token | they |
Token ID | 484 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
Run | +0.020 |
www | +0.018 |
forth | +0.018 |
gust | +0.017 |
ww | +0.017 |
Neg logit contributions | |
lair | -0.022 |
dentist | -0.021 |
fault | -0.021 |
lor | -0.021 |
ests | -0.020 |
Token | went |
Token ID | 1816 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
Run | +0.022 |
www | +0.021 |
ww | +0.019 |
forth | +0.019 |
gust | +0.019 |
Neg logit contributions | |
dentist | -0.017 |
lair | -0.017 |
fault | -0.017 |
clinic | -0.016 |
lor | -0.016 |
Token | back |
Token ID | 736 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Run | +0.022 |
www | +0.021 |
forth | +0.020 |
ww | +0.020 |
gust | +0.019 |
Neg logit contributions | |
dentist | -0.016 |
fault | -0.016 |
lair | -0.015 |
lor | -0.015 |
ests | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
lor | +0.040 |
dentist | +0.039 |
lair | +0.039 |
fault | +0.037 |
ests | +0.037 |
Neg logit contributions | |
Run | -0.044 |
www | -0.042 |
forth | -0.042 |
ahead | -0.039 |
ww | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
lor | +0.052 |
ests | +0.052 |
lair | +0.050 |
fault | +0.049 |
dentist | +0.049 |
Neg logit contributions | |
Run | -0.042 |
www | -0.038 |
forth | -0.036 |
gust | -0.036 |
ww | -0.033 |
Token | park |
Token ID | 3952 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Run | +0.012 |
www | +0.012 |
forth | +0.011 |
ww | +0.011 |
gust | +0.011 |
Neg logit contributions | |
fault | -0.011 |
ests | -0.010 |
lor | -0.010 |
osc | -0.010 |
lair | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
dentist | +0.029 |
ests | +0.029 |
lor | +0.029 |
fault | +0.029 |
wounds | +0.028 |
Neg logit contributions | |
Run | -0.031 |
www | -0.029 |
forth | -0.029 |
gust | -0.027 |
ahead | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
Run | +0.010 |
www | +0.009 |
gust | +0.009 |
ww | +0.008 |
forth | +0.008 |
Neg logit contributions | |
lair | -0.009 |
dentist | -0.009 |
fault | -0.009 |
wounds | -0.009 |
lor | -0.009 |
Token | sat |
Token ID | 3332 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Run | +0.013 |
www | +0.012 |
ww | +0.011 |
forth | +0.011 |
gust | +0.011 |
Neg logit contributions | |
dentist | -0.010 |
lair | -0.010 |
fault | -0.010 |
lor | -0.009 |
clinic | -0.009 |
Token | went |
Token ID | 1816 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Run | +0.020 |
www | +0.019 |
ww | +0.018 |
forth | +0.018 |
gust | +0.017 |
Neg logit contributions | |
fault | -0.017 |
lair | -0.017 |
dentist | -0.017 |
lor | -0.016 |
ests | -0.016 |
Token | back |
Token ID | 736 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Run | +0.030 |
www | +0.028 |
forth | +0.027 |
ww | +0.026 |
gust | +0.026 |
Neg logit contributions | |
fault | -0.018 |
dentist | -0.018 |
lor | -0.018 |
lair | -0.018 |
ests | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
lor | +0.029 |
dentist | +0.028 |
fault | +0.028 |
lair | +0.028 |
ests | +0.027 |
Neg logit contributions | |
Run | -0.037 |
www | -0.035 |
forth | -0.034 |
ww | -0.032 |
boom | -0.031 |
Token | her |
Token ID | 607 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
ests | +0.043 |
lor | +0.043 |
fault | +0.041 |
lair | +0.041 |
dentist | +0.041 |
Neg logit contributions | |
Run | -0.051 |
www | -0.048 |
forth | -0.047 |
gust | -0.046 |
ww | -0.044 |
Token | garden |
Token ID | 11376 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
lor | +0.055 |
ests | +0.055 |
osc | +0.049 |
iddles | +0.048 |
isk | +0.047 |
Neg logit contributions | |
forth | -0.065 |
Run | -0.058 |
gust | -0.058 |
www | -0.055 |
blur | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e-03 |
Pos logit contributions | |
ests | +0.061 |
fault | +0.061 |
lor | +0.061 |
dentist | +0.059 |
wounds | +0.058 |
Neg logit contributions | |
forth | -0.041 |
Run | -0.039 |
gust | -0.038 |
www | -0.036 |
blur | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
wounds | +0.000 |
lair | +0.000 |
fault | +0.000 |
dentist | +0.000 |
lor | +0.000 |
Neg logit contributions | |
Run | -0.000 |
www | -0.000 |
gust | -0.000 |
ww | -0.000 |
blur | -0.000 |
Token | planted |
Token ID | 18969 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
fault | +0.008 |
lor | +0.008 |
lair | +0.008 |
ests | +0.008 |
dentist | +0.008 |
Neg logit contributions | |
Run | -0.007 |
www | -0.007 |
forth | -0.007 |
gust | -0.006 |
ww | -0.006 |
Token | more |
Token ID | 517 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Run | +0.010 |
www | +0.009 |
gust | +0.009 |
ww | +0.009 |
forth | +0.009 |
Neg logit contributions | |
lair | -0.009 |
fault | -0.009 |
clinic | -0.009 |
dentist | -0.009 |
lor | -0.009 |
Token | seeds |
Token ID | 11904 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Run | +0.005 |
www | +0.005 |
ww | +0.005 |
forth | +0.005 |
gust | +0.005 |
Neg logit contributions | |
dentist | -0.004 |
lair | -0.004 |
fault | -0.004 |
clinic | -0.004 |
lor | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Run | +0.003 |
www | +0.003 |
forth | +0.003 |
ww | +0.003 |
gust | +0.002 |
Neg logit contributions | |
dentist | -0.003 |
lair | -0.003 |
fault | -0.003 |
clinic | -0.003 |
principal | -0.003 |
Token | can |
Token ID | 460 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
lair | +0.002 |
dentist | +0.002 |
fault | +0.002 |
lor | +0.002 |
clinic | +0.001 |
Neg logit contributions | |
Run | -0.002 |
www | -0.002 |
ww | -0.002 |
forth | -0.001 |
gust | -0.001 |
Token | play |
Token ID | 711 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
lair | +0.035 |
fault | +0.034 |
dentist | +0.034 |
lor | +0.033 |
ests | +0.033 |
Neg logit contributions | |
Run | -0.040 |
www | -0.038 |
ww | -0.035 |
forth | -0.035 |
gust | -0.034 |
Token | with |
Token ID | 351 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
fault | +0.004 |
dentist | +0.004 |
lair | +0.004 |
lor | +0.003 |
clinic | +0.003 |
Neg logit contributions | |
Run | -0.005 |
www | -0.004 |
ww | -0.004 |
forth | -0.004 |
gust | -0.004 |
Token | your |
Token ID | 534 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
dentist | +0.009 |
lair | +0.009 |
fault | +0.009 |
clinic | +0.009 |
lor | +0.009 |
Neg logit contributions | |
Run | -0.005 |
www | -0.004 |
ww | -0.004 |
forth | -0.004 |
gust | -0.004 |
Token | own |
Token ID | 898 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
lor | +0.075 |
dentist | +0.068 |
lair | +0.067 |
clinic | +0.064 |
Her | +0.064 |
Neg logit contributions | |
Run | -0.077 |
forth | -0.074 |
www | -0.071 |
gust | -0.070 |
boom | -0.069 |
Token | car |
Token ID | 1097 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
dentist | +0.033 |
lor | +0.032 |
lair | +0.032 |
fault | +0.031 |
clinic | +0.030 |
Neg logit contributions | |
Run | -0.049 |
www | -0.047 |
forth | -0.045 |
ww | -0.044 |
gust | -0.043 |
Token | ." |
Token ID | 526 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
lor | +0.023 |
lair | +0.023 |
fault | +0.023 |
dentist | +0.023 |
wounds | +0.022 |
Neg logit contributions | |
Run | -0.023 |
www | -0.023 |
forth | -0.022 |
ww | -0.021 |
boom | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
lair | +0.034 |
fault | +0.034 |
lor | +0.032 |
tr | +0.032 |
osc | +0.031 |
Neg logit contributions | |
Run | -0.035 |
www | -0.031 |
ww | -0.030 |
gust | -0.030 |
ang | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
fault | +0.026 |
lair | +0.025 |
tr | +0.023 |
osc | +0.023 |
patients | +0.022 |
Neg logit contributions | |
Run | -0.033 |
www | -0.029 |
ang | -0.029 |
ww | -0.028 |
gust | -0.027 |
Token | Sam |
Token ID | 16305 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Run | +0.014 |
www | +0.013 |
ww | +0.012 |
forth | +0.012 |
gust | +0.012 |
Neg logit contributions | |
dentist | -0.014 |
fault | -0.014 |
lair | -0.014 |
clinic | -0.014 |
lor | -0.014 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Run | +0.025 |
www | +0.022 |
forth | +0.021 |
ww | +0.020 |
gust | +0.019 |
Neg logit contributions | |
fault | -0.027 |
lair | -0.026 |
clinic | -0.025 |
lor | -0.025 |
dentist | -0.024 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
lair | +0.015 |
ests | +0.015 |
wounds | +0.014 |
lor | +0.014 |
dentist | +0.014 |
Neg logit contributions | |
Run | -0.014 |
gust | -0.013 |
www | -0.012 |
ww | -0.011 |
Uh | -0.011 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Run | +0.016 |
www | +0.015 |
forth | +0.014 |
gust | +0.013 |
ww | +0.013 |
Neg logit contributions | |
fault | -0.016 |
ests | -0.016 |
lair | -0.015 |
dentist | -0.015 |
neys | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
lair | +0.057 |
ests | +0.055 |
clinic | +0.053 |
aj | +0.053 |
lor | +0.052 |
Neg logit contributions | |
Run | -0.023 |
www | -0.021 |
ww | -0.019 |
izing | -0.017 |
dd | -0.017 |
Token | lesson |
Token ID | 11483 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
dentist | +0.046 |
lair | +0.046 |
ests | +0.044 |
clinic | +0.044 |
fault | +0.044 |
Neg logit contributions | |
Run | -0.064 |
www | -0.062 |
ww | -0.059 |
gust | -0.056 |
forth | -0.055 |
Token | that |
Token ID | 326 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
lair | +0.004 |
dentist | +0.004 |
fault | +0.004 |
clinic | +0.004 |
ests | +0.003 |
Neg logit contributions | |
Run | -0.004 |
www | -0.004 |
ww | -0.004 |
forth | -0.003 |
gust | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Run | +0.000 |
www | +0.000 |
ww | +0.000 |
gust | +0.000 |
forth | +0.000 |
Neg logit contributions | |
dentist | -0.001 |
fault | -0.001 |
lair | -0.001 |
truth | -0.001 |
clinic | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
dentist | +0.005 |
lair | +0.005 |
fault | +0.005 |
ests | +0.005 |
clinic | +0.005 |
Neg logit contributions | |
Run | -0.005 |
www | -0.005 |
ww | -0.005 |
forth | -0.005 |
gust | -0.005 |
Token | be |
Token ID | 307 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
lair | +0.014 |
ests | +0.013 |
fault | +0.013 |
lor | +0.013 |
dentist | +0.013 |
Neg logit contributions | |
Run | -0.016 |
www | -0.015 |
forth | -0.014 |
ww | -0.014 |
boom | -0.013 |
Token | careful |
Token ID | 8161 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
Run | +0.015 |
www | +0.014 |
forth | +0.014 |
ww | +0.013 |
gust | +0.013 |
Neg logit contributions | |
lor | -0.019 |
ests | -0.019 |
dentist | -0.018 |
fault | -0.018 |
lair | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Run | +0.010 |
www | +0.010 |
ww | +0.009 |
forth | +0.009 |
gust | +0.009 |
Neg logit contributions | |
dentist | -0.009 |
lair | -0.009 |
fault | -0.008 |
clinic | -0.008 |
lor | -0.008 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
lor | +0.013 |
lair | +0.013 |
ests | +0.013 |
dentist | +0.013 |
tr | +0.012 |
Neg logit contributions | |
Run | -0.012 |
www | -0.012 |
forth | -0.011 |
ww | -0.011 |
ening | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Run | +0.024 |
www | +0.023 |
ww | +0.022 |
forth | +0.022 |
gust | +0.021 |
Neg logit contributions | |
dentist | -0.012 |
lair | -0.012 |
fault | -0.012 |
clinic | -0.012 |
lor | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
fault | +0.004 |
lair | +0.004 |
dentist | +0.004 |
wounds | +0.004 |
clinic | +0.004 |
Neg logit contributions | |
Run | -0.006 |
www | -0.005 |
gust | -0.005 |
ww | -0.005 |
forth | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
fault | +0.017 |
lair | +0.016 |
dentist | +0.015 |
clinic | +0.014 |
wounds | +0.014 |
Neg logit contributions | |
Run | -0.042 |
www | -0.040 |
ww | -0.038 |
gust | -0.036 |
ang | -0.035 |
Token | Spot |
Token ID | 32565 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
forth | +0.003 |
Run | +0.003 |
gust | +0.003 |
ening | +0.003 |
www | +0.003 |
Neg logit contributions | |
dentist | -0.002 |
aid | -0.002 |
lor | -0.002 |
clinic | -0.002 |
lair | -0.002 |
Token | tried |
Token ID | 3088 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Run | +0.038 |
www | +0.036 |
ww | +0.034 |
gust | +0.033 |
forth | +0.033 |
Neg logit contributions | |
dentist | -0.030 |
lair | -0.029 |
fault | -0.028 |
clinic | -0.028 |
lor | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
lor | +0.003 |
dentist | +0.003 |
lair | +0.003 |
ests | +0.003 |
clinic | +0.003 |
Neg logit contributions | |
Run | -0.010 |
www | -0.009 |
forth | -0.009 |
ww | -0.009 |
gust | -0.009 |
Token | pull |
Token ID | 2834 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
aid | +0.035 |
wounds | +0.035 |
dentist | +0.034 |
lair | +0.033 |
clinic | +0.032 |
Neg logit contributions | |
www | -0.043 |
ww | -0.042 |
Run | -0.042 |
gust | -0.038 |
ang | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
www | +0.081 |
Run | +0.077 |
ww | +0.077 |
gust | +0.072 |
opter | +0.070 |
Neg logit contributions | |
wounds | -0.036 |
stitches | -0.035 |
fault | -0.033 |
to | -0.033 |
kit | -0.033 |
Token | bone |
Token ID | 9970 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
dentist | +0.016 |
lair | +0.015 |
fault | +0.015 |
clinic | +0.014 |
wounds | +0.014 |
Neg logit contributions | |
Run | -0.044 |
www | -0.043 |
ww | -0.041 |
forth | -0.040 |
gust | -0.040 |
Token | out |
Token ID | 503 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
fault | +0.032 |
lair | +0.031 |
dentist | +0.030 |
aid | +0.030 |
tr | +0.029 |
Neg logit contributions | |
Run | -0.049 |
www | -0.048 |
ww | -0.046 |
dd | -0.042 |
gust | -0.042 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Run | +0.003 |
www | +0.003 |
ww | +0.003 |
gust | +0.003 |
forth | +0.003 |
Neg logit contributions | |
lair | -0.002 |
fault | -0.002 |
aid | -0.002 |
dentist | -0.002 |
wounds | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
lor | +0.043 |
aj | +0.040 |
ests | +0.039 |
robe | +0.036 |
lair | +0.036 |
Neg logit contributions | |
www | -0.033 |
it | -0.033 |
after | -0.033 |
boom | -0.033 |
ahead | -0.032 |
Token | mail |
Token ID | 6920 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
fault | +0.066 |
ests | +0.066 |
lair | +0.065 |
lor | +0.063 |
aj | +0.063 |
Neg logit contributions | |
Run | -0.077 |
www | -0.075 |
forth | -0.068 |
ww | -0.068 |
gust | -0.066 |
Token | a |
Token ID | 257 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
lair | +0.051 |
fault | +0.051 |
lor | +0.050 |
clinic | +0.049 |
aj | +0.048 |
Neg logit contributions | |
Run | -0.039 |
www | -0.038 |
forth | -0.037 |
gust | -0.035 |
ww | -0.034 |
Token | letter |
Token ID | 3850 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
lair | +0.040 |
fault | +0.039 |
ests | +0.039 |
dentist | +0.039 |
lor | +0.038 |
Neg logit contributions | |
Run | -0.078 |
www | -0.076 |
ww | -0.072 |
gust | -0.071 |
forth | -0.070 |
Token | to |
Token ID | 284 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
wounds | +0.060 |
ests | +0.059 |
fault | +0.059 |
lor | +0.058 |
lair | +0.058 |
Neg logit contributions | |
Run | -0.074 |
www | -0.073 |
forth | -0.070 |
ww | -0.068 |
gust | -0.067 |
Token | her |
Token ID | 607 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
fault | +0.063 |
lair | +0.062 |
lor | +0.060 |
ests | +0.060 |
aj | +0.057 |
Neg logit contributions | |
Run | -0.062 |
www | -0.061 |
gust | -0.058 |
forth | -0.057 |
ww | -0.055 |
Token | grandma |
Token ID | 49890 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
lor | +0.097 |
ests | +0.092 |
osc | +0.089 |
lair | +0.082 |
seek | +0.079 |
Neg logit contributions | |
forth | -0.108 |
www | -0.100 |
gust | -0.100 |
Run | -0.098 |
ww | -0.092 |
Token | who |
Token ID | 508 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
ests | +0.104 |
fault | +0.101 |
lair | +0.100 |
lor | +0.100 |
wounds | +0.097 |
Neg logit contributions | |
forth | -0.085 |
Run | -0.074 |
www | -0.070 |
ahead | -0.068 |
ening | -0.067 |
Token | lived |
Token ID | 5615 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
lair | +0.013 |
fault | +0.013 |
wounds | +0.013 |
lor | +0.013 |
dentist | +0.012 |
Neg logit contributions | |
Run | -0.017 |
www | -0.017 |
ww | -0.015 |
forth | -0.015 |
gust | -0.015 |
Token | far |
Token ID | 1290 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
fault | +0.034 |
ests | +0.032 |
dentist | +0.032 |
lor | +0.032 |
wounds | +0.031 |
Neg logit contributions | |
Run | -0.026 |
www | -0.024 |
forth | -0.023 |
gust | -0.022 |
ww | -0.021 |
Token | away |
Token ID | 1497 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Run | +0.103 |
www | +0.099 |
ww | +0.092 |
gust | +0.090 |
forth | +0.086 |
Neg logit contributions | |
dentist | -0.086 |
lair | -0.084 |
clinic | -0.084 |
fault | -0.083 |
aid | -0.081 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
Run | +0.046 |
www | +0.046 |
ww | +0.042 |
gust | +0.039 |
forth | +0.038 |
Neg logit contributions | |
dentist | -0.047 |
fault | -0.043 |
lair | -0.043 |
clinic | -0.042 |
wounds | -0.042 |
Token | my |
Token ID | 1820 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
forth | +0.016 |
www | +0.014 |
Run | +0.013 |
ww | +0.013 |
heart | +0.012 |
Neg logit contributions | |
lor | -0.022 |
clinic | -0.022 |
lair | -0.021 |
wounds | -0.021 |
ests | -0.021 |
Token | 's |
Token ID | 338 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Run | +0.022 |
www | +0.021 |
forth | +0.020 |
ww | +0.020 |
gust | +0.020 |
Neg logit contributions | |
fault | -0.017 |
ests | -0.017 |
lor | -0.017 |
lair | -0.017 |
clinic | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
lor | +0.064 |
osc | +0.056 |
neys | +0.054 |
ests | +0.052 |
clinic | +0.052 |
Neg logit contributions | |
gust | -0.063 |
forth | -0.059 |
wind | -0.055 |
Run | -0.052 |
ww | -0.049 |
Token | gave |
Token ID | 2921 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
fault | +0.016 |
lair | +0.016 |
lor | +0.015 |
ests | +0.015 |
clinic | +0.015 |
Neg logit contributions | |
Run | -0.017 |
www | -0.016 |
forth | -0.016 |
ww | -0.015 |
gust | -0.015 |
Token | him |
Token ID | 683 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
lor | +0.002 |
lair | +0.002 |
clinic | +0.002 |
aj | +0.002 |
aid | +0.002 |
Neg logit contributions | |
Run | -0.001 |
forth | -0.001 |
www | -0.001 |
gust | -0.001 |
ww | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
lor | +0.172 |
lair | +0.166 |
clinic | +0.157 |
fault | +0.153 |
tr | +0.149 |
Neg logit contributions | |
Run | -0.130 |
www | -0.120 |
forth | -0.116 |
ww | -0.116 |
after | -0.110 |
Token | piece |
Token ID | 3704 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
lair | +0.074 |
lor | +0.073 |
neys | +0.072 |
osc | +0.071 |
ests | +0.071 |
Neg logit contributions | |
www | -0.080 |
Run | -0.079 |
ww | -0.079 |
gust | -0.076 |
boom | -0.066 |
Token | of |
Token ID | 286 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
fault | +0.039 |
lair | +0.039 |
dentist | +0.039 |
lor | +0.039 |
clinic | +0.039 |
Neg logit contributions | |
Run | -0.027 |
www | -0.026 |
ww | -0.024 |
gust | -0.023 |
forth | -0.022 |
Token | paper |
Token ID | 3348 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
lair | +0.022 |
lor | +0.022 |
fault | +0.021 |
ests | +0.021 |
clinic | +0.020 |
Neg logit contributions | |
Run | -0.027 |
www | -0.026 |
ww | -0.025 |
gust | -0.024 |
forth | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
clinic | +0.059 |
lor | +0.059 |
fault | +0.059 |
dentist | +0.059 |
lair | +0.059 |
Neg logit contributions | |
Run | -0.057 |
forth | -0.054 |
www | -0.053 |
ww | -0.050 |
boom | -0.049 |
Token | The |
Token ID | 383 |
Feature activation | +5.16e-03 |
Pos logit contributions | |
lair | +0.027 |
dentist | +0.024 |
fault | +0.023 |
wounds | +0.022 |
ests | +0.022 |
Neg logit contributions | |
Run | -0.032 |
www | -0.029 |
gust | -0.028 |
forth | -0.028 |
ww | -0.027 |
Token | daughter |
Token ID | 4957 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Run | +0.000 |
www | +0.000 |
ww | +0.000 |
forth | +0.000 |
gust | +0.000 |
Neg logit contributions | |
dentist | -0.000 |
lair | -0.000 |
fault | -0.000 |
clinic | -0.000 |
lor | -0.000 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
fault | +0.025 |
lair | +0.024 |
dentist | +0.024 |
clinic | +0.023 |
lor | +0.023 |
Neg logit contributions | |
Run | -0.026 |
www | -0.025 |
forth | -0.024 |
ww | -0.023 |
gust | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Run | +0.023 |
gust | +0.021 |
forth | +0.021 |
www | +0.021 |
ww | +0.020 |
Neg logit contributions | |
dentist | -0.028 |
ests | -0.027 |
lor | -0.027 |
clinic | -0.027 |
lair | -0.027 |
Token | hugged |
Token ID | 41130 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Run | +0.045 |
www | +0.043 |
ww | +0.040 |
gust | +0.039 |
forth | +0.038 |
Neg logit contributions | |
dentist | -0.027 |
fault | -0.026 |
lair | -0.026 |
clinic | -0.025 |
lor | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
lair | +0.003 |
lor | +0.003 |
dentist | +0.002 |
ests | +0.002 |
fault | +0.002 |
Neg logit contributions | |
Run | -0.002 |
forth | -0.002 |
gust | -0.002 |
www | -0.002 |
boom | -0.002 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
lor | +0.087 |
lair | +0.079 |
ests | +0.078 |
clinic | +0.075 |
dentist | +0.075 |
Neg logit contributions | |
forth | -0.133 |
Run | -0.129 |
gust | -0.128 |
www | -0.124 |
boom | -0.118 |
Token | my |
Token ID | 1820 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
lair | +0.087 |
dentist | +0.084 |
lor | +0.083 |
fault | +0.083 |
clinic | +0.083 |
Neg logit contributions | |
forth | -0.086 |
Run | -0.083 |
www | -0.081 |
ww | -0.076 |
gust | -0.075 |
Token | back |
Token ID | 736 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
dentist | +0.078 |
lair | +0.077 |
ests | +0.074 |
fault | +0.073 |
clinic | +0.072 |
Neg logit contributions | |
Run | -0.094 |
forth | -0.092 |
www | -0.092 |
ww | -0.087 |
gust | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
dentist | +0.036 |
ests | +0.036 |
lair | +0.035 |
lor | +0.035 |
fault | +0.034 |
Neg logit contributions | |
Run | -0.047 |
www | -0.045 |
forth | -0.044 |
ww | -0.042 |
gust | -0.042 |
Token | They |
Token ID | 1119 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
lair | +0.020 |
dentist | +0.019 |
wounds | +0.019 |
ests | +0.018 |
clinic | +0.018 |
Neg logit contributions | |
Run | -0.027 |
www | -0.026 |
ww | -0.025 |
gust | -0.025 |
forth | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
dentist | +0.050 |
lor | +0.050 |
lair | +0.048 |
ests | +0.048 |
fault | +0.046 |
Neg logit contributions | |
Run | -0.061 |
forth | -0.056 |
www | -0.053 |
gust | -0.052 |
ging | -0.051 |
Token | cars |
Token ID | 5006 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
lor | +0.093 |
dentist | +0.077 |
ests | +0.075 |
lair | +0.073 |
handed | +0.071 |
Neg logit contributions | |
gust | -0.085 |
Run | -0.084 |
boom | -0.082 |
ging | -0.080 |
crashing | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
lor | +0.004 |
dentist | +0.004 |
lair | +0.004 |
clinic | +0.004 |
ests | +0.004 |
Neg logit contributions | |
Run | -0.004 |
forth | -0.004 |
gust | -0.004 |
www | -0.004 |
boom | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Run | +0.021 |
www | +0.019 |
gust | +0.018 |
ww | +0.018 |
forth | +0.017 |
Neg logit contributions | |
lor | -0.015 |
lair | -0.015 |
fault | -0.014 |
clinic | -0.014 |
dentist | -0.014 |
Token | asked |
Token ID | 1965 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
fault | +0.044 |
lair | +0.042 |
lor | +0.041 |
clinic | +0.040 |
ests | +0.039 |
Neg logit contributions | |
Run | -0.046 |
www | -0.042 |
gust | -0.039 |
forth | -0.039 |
ww | -0.039 |
Token | them |
Token ID | 606 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
lor | +0.069 |
lair | +0.068 |
fault | +0.066 |
dentist | +0.066 |
clinic | +0.065 |
Neg logit contributions | |
Run | -0.069 |
www | -0.064 |
forth | -0.061 |
gust | -0.060 |
ww | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
lor | +0.160 |
lair | +0.150 |
ests | +0.147 |
dentist | +0.140 |
clinic | +0.140 |
Neg logit contributions | |
Run | -0.124 |
forth | -0.113 |
boom | -0.110 |
www | -0.108 |
gust | -0.101 |
Token | " |
Token ID | 366 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
lor | +0.057 |
lair | +0.057 |
ests | +0.056 |
fault | +0.055 |
dentist | +0.052 |
Neg logit contributions | |
Run | -0.062 |
gust | -0.053 |
forth | -0.053 |
www | -0.053 |
boom | -0.052 |
Token | What |
Token ID | 2061 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
www | +0.024 |
Run | +0.024 |
ww | +0.023 |
gust | +0.022 |
forth | +0.021 |
Neg logit contributions | |
dentist | -0.020 |
lair | -0.019 |
wounds | -0.018 |
clinic | -0.018 |
lor | -0.018 |
Token | 's |
Token ID | 338 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
lair | +0.014 |
lor | +0.014 |
clinic | +0.014 |
wounds | +0.014 |
dentist | +0.013 |
Neg logit contributions | |
Run | -0.015 |
www | -0.014 |
ww | -0.013 |
gust | -0.012 |
forth | -0.012 |
Token | wrong |
Token ID | 2642 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Run | +0.024 |
www | +0.022 |
ww | +0.021 |
gust | +0.021 |
forth | +0.021 |
Neg logit contributions | |
dentist | -0.009 |
fault | -0.008 |
lair | -0.008 |
clinic | -0.008 |
wounds | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
dentist | +0.016 |
lair | +0.015 |
fault | +0.015 |
clinic | +0.015 |
lor | +0.014 |
Neg logit contributions | |
Run | -0.026 |
www | -0.025 |
ww | -0.024 |
gust | -0.023 |
forth | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
lair | +0.009 |
dentist | +0.009 |
lor | +0.009 |
fault | +0.009 |
clinic | +0.008 |
Neg logit contributions | |
Run | -0.015 |
www | -0.014 |
gust | -0.013 |
ww | -0.013 |
forth | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
lair | +0.015 |
fault | +0.015 |
dentist | +0.015 |
wounds | +0.013 |
clinic | +0.013 |
Neg logit contributions | |
Run | -0.040 |
www | -0.038 |
ww | -0.037 |
gust | -0.035 |
ang | -0.034 |
Token | They |
Token ID | 2990 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
gust | +0.019 |
ening | +0.018 |
forth | +0.018 |
Run | +0.018 |
www | +0.017 |
Neg logit contributions | |
aid | -0.006 |
tr | -0.006 |
clinic | -0.006 |
Her | -0.006 |
| -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Run | +0.020 |
www | +0.020 |
ww | +0.019 |
gust | +0.017 |
izing | +0.017 |
Neg logit contributions | |
dentist | -0.014 |
lair | -0.013 |
clinic | -0.013 |
aid | -0.013 |
ests | -0.013 |
Token | their |
Token ID | 511 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
lor | +0.067 |
lair | +0.065 |
dentist | +0.064 |
fault | +0.062 |
clinic | +0.061 |
Neg logit contributions | |
Run | -0.066 |
www | -0.060 |
gust | -0.057 |
forth | -0.056 |
ww | -0.055 |
Token | mom |
Token ID | 1995 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
lor | +0.122 |
ests | +0.103 |
handed | +0.098 |
osc | +0.098 |
age | +0.096 |
Neg logit contributions | |
Run | -0.127 |
forth | -0.121 |
gust | -0.118 |
www | -0.117 |
boom | -0.114 |
Token | if |
Token ID | 611 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
lor | +0.170 |
lair | +0.165 |
ests | +0.163 |
wounds | +0.159 |
fault | +0.158 |
Neg logit contributions | |
Run | -0.063 |
forth | -0.062 |
www | -0.058 |
boom | -0.051 |
ww | -0.050 |
Token | they |
Token ID | 484 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
lair | +0.035 |
lor | +0.034 |
fault | +0.034 |
ests | +0.034 |
clinic | +0.033 |
Neg logit contributions | |
Run | -0.018 |
www | -0.015 |
ww | -0.014 |
forth | -0.014 |
gust | -0.013 |
Token | could |
Token ID | 714 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
lor | +0.007 |
lair | +0.007 |
clinic | +0.007 |
fault | +0.007 |
dentist | +0.007 |
Neg logit contributions | |
Run | -0.008 |
www | -0.007 |
gust | -0.007 |
forth | -0.007 |
ww | -0.007 |
Token | climb |
Token ID | 12080 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
lor | +0.057 |
lair | +0.057 |
ests | +0.056 |
dentist | +0.056 |
fault | +0.055 |
Neg logit contributions | |
Run | -0.040 |
www | -0.037 |
forth | -0.035 |
gust | -0.034 |
ww | -0.033 |