Token | Farmer |
Token ID | 37755 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
hy | +0.025 |
coat | +0.022 |
blond | +0.021 |
house | +0.021 |
Sue | +0.021 |
Neg logit contributions | |
dolphins | -0.030 |
ya | -0.029 |
mber | -0.029 |
dolphin | -0.029 |
va | -0.027 |
Token | Joe |
Token ID | 5689 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
ya | +0.033 |
mber | +0.032 |
dolphins | +0.031 |
maid | +0.031 |
va | +0.031 |
Neg logit contributions | |
Sue | -0.020 |
hy | -0.018 |
Kitty | -0.017 |
blond | -0.017 |
house | -0.016 |
Token | says |
Token ID | 1139 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
ya | +0.012 |
dolphins | +0.011 |
mber | +0.011 |
dolphin | +0.011 |
asper | +0.011 |
Neg logit contributions | |
Sue | -0.026 |
hy | -0.026 |
Kitty | -0.025 |
Kim | -0.025 |
blond | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
blond | +0.002 |
Kim | +0.002 |
Wh | +0.002 |
Neg logit contributions | |
maid | -0.002 |
ub | -0.002 |
us | -0.002 |
fish | -0.002 |
utes | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
mber | +0.020 |
ya | +0.020 |
utes | +0.020 |
dolphins | +0.020 |
dolphin | +0.020 |
Neg logit contributions | |
Sue | -0.011 |
hy | -0.011 |
Kitty | -0.009 |
blond | -0.009 |
house | -0.009 |
Token | Ste |
Token ID | 7447 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
utes | +0.009 |
ya | +0.009 |
maid | +0.009 |
mber | +0.009 |
dolphins | +0.009 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.006 |
hy | -0.005 |
Tim | -0.005 |
Kim | -0.005 |
Token | aling |
Token ID | 4272 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
utes | +0.182 |
ya | +0.173 |
maid | +0.173 |
dolphins | +0.171 |
mber | +0.169 |
Neg logit contributions | |
Sue | -0.173 |
Kitty | -0.148 |
hy | -0.143 |
Kim | -0.142 |
Tim | -0.141 |
Token | is |
Token ID | 318 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
utes | +0.020 |
ya | +0.019 |
maid | +0.019 |
mber | +0.019 |
dolphins | +0.019 |
Neg logit contributions | |
Sue | -0.016 |
Kitty | -0.014 |
hy | -0.013 |
Kim | -0.013 |
Tim | -0.013 |
Token | bad |
Token ID | 2089 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Sue | +0.017 |
Kitty | +0.014 |
hy | +0.013 |
Kim | +0.013 |
Tim | +0.013 |
Neg logit contributions | |
utes | -0.030 |
ya | -0.029 |
dolphins | -0.029 |
maid | -0.029 |
mber | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Sue | +0.007 |
Kitty | +0.006 |
hy | +0.005 |
Kim | +0.005 |
Tim | +0.005 |
Neg logit contributions | |
utes | -0.017 |
ya | -0.016 |
dolphins | -0.016 |
maid | -0.016 |
mber | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
utes | +0.012 |
ya | +0.012 |
mber | +0.012 |
ub | +0.011 |
dolphins | +0.011 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.007 |
hy | -0.007 |
hetically | -0.006 |
house | -0.006 |
Token | Her |
Token ID | 9360 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
utes | +0.006 |
ya | +0.006 |
mber | +0.006 |
va | +0.005 |
dolphins | +0.005 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.006 |
hy | -0.006 |
Kim | -0.006 |
Tim | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Sue | +0.043 |
hy | +0.039 |
Kitty | +0.039 |
Kim | +0.037 |
She | +0.036 |
Neg logit contributions | |
utes | -0.044 |
maid | -0.043 |
ya | -0.041 |
crew | -0.040 |
dolphin | -0.040 |
Token | said |
Token ID | 531 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Sue | +0.051 |
hy | +0.048 |
blond | +0.046 |
� | +0.046 |
Kitty | +0.046 |
Neg logit contributions | |
ya | -0.044 |
mber | -0.041 |
va | -0.040 |
asper | -0.040 |
maid | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
ya | +0.043 |
mber | +0.043 |
dolphins | +0.042 |
utes | +0.042 |
va | +0.042 |
Neg logit contributions | |
Sue | -0.026 |
hy | -0.022 |
Kitty | -0.022 |
Kim | -0.022 |
Kim | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
utes | +0.011 |
ya | +0.011 |
mber | +0.011 |
dolphins | +0.011 |
va | +0.010 |
Neg logit contributions | |
Sue | -0.012 |
hy | -0.010 |
Kitty | -0.010 |
Kim | -0.010 |
house | -0.009 |
Token | Ste |
Token ID | 7447 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.003 |
hy | +0.003 |
Kim | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
utes | -0.006 |
maid | -0.006 |
ya | -0.006 |
dolphins | -0.006 |
submarine | -0.006 |
Token | ak |
Token ID | 461 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
maid | +0.184 |
utes | +0.182 |
dolphins | +0.181 |
dolphin | +0.175 |
crew | +0.172 |
Neg logit contributions | |
Sue | -0.170 |
Kitty | -0.141 |
house | -0.139 |
Kim | -0.139 |
hy | -0.138 |
Token | is |
Token ID | 318 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
utes | +0.029 |
ya | +0.029 |
mber | +0.028 |
maid | +0.028 |
dolphins | +0.028 |
Neg logit contributions | |
Sue | -0.024 |
Kitty | -0.021 |
hy | -0.020 |
Kim | -0.019 |
Tim | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Sue | +0.017 |
Kitty | +0.013 |
Tim | +0.012 |
Kim | +0.012 |
hy | +0.012 |
Neg logit contributions | |
utes | -0.034 |
maid | -0.033 |
ya | -0.033 |
ub | -0.032 |
mber | -0.032 |
Token | type |
Token ID | 2099 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
utes | +0.012 |
ub | +0.011 |
maid | +0.011 |
eds | +0.011 |
asper | +0.011 |
Neg logit contributions | |
Sue | -0.005 |
Kitty | -0.004 |
Tim | -0.004 |
chocolate | -0.004 |
hy | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
utes | +0.037 |
maid | +0.035 |
ya | +0.035 |
dolphins | +0.034 |
ub | +0.034 |
Neg logit contributions | |
Sue | -0.016 |
Kitty | -0.011 |
Tim | -0.011 |
hy | -0.011 |
She | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
Sue | +0.026 |
hy | +0.023 |
Kitty | +0.021 |
Kim | +0.019 |
� | +0.019 |
Neg logit contributions | |
dolphins | -0.066 |
utes | -0.064 |
ya | -0.063 |
dolphin | -0.063 |
coral | -0.062 |
Token | sign |
Token ID | 1051 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
utes | +0.046 |
ya | +0.043 |
asper | +0.043 |
ub | +0.043 |
maid | +0.042 |
Neg logit contributions | |
Sue | -0.022 |
Kitty | -0.017 |
hy | -0.016 |
Tim | -0.016 |
shake | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.012 |
Kim | +0.011 |
Tim | +0.011 |
blond | +0.010 |
Neg logit contributions | |
utes | -0.015 |
dolphins | -0.015 |
ya | -0.015 |
fish | -0.015 |
dolphin | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Sue | +0.005 |
Kitty | +0.005 |
hy | +0.004 |
Kim | +0.004 |
Tim | +0.004 |
Neg logit contributions | |
utes | -0.006 |
ya | -0.006 |
dolphins | -0.006 |
mber | -0.006 |
maid | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
maid | +0.056 |
utes | +0.056 |
dolphins | +0.055 |
fish | +0.055 |
mber | +0.055 |
Neg logit contributions | |
Sue | -0.047 |
Kitty | -0.042 |
Kim | -0.040 |
hetically | -0.040 |
hy | -0.040 |
Token | Ste |
Token ID | 7447 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.003 |
hy | +0.003 |
Kim | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
utes | -0.004 |
ya | -0.004 |
mber | -0.004 |
dolphins | -0.004 |
maid | -0.004 |
Token | ak |
Token ID | 461 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
maid | +0.180 |
utes | +0.178 |
dolphins | +0.173 |
dolphin | +0.167 |
ya | +0.166 |
Neg logit contributions | |
Sue | -0.176 |
Kitty | -0.147 |
hy | -0.145 |
Kim | -0.143 |
house | -0.143 |
Token | house |
Token ID | 4803 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
utes | +0.033 |
ya | +0.031 |
maid | +0.031 |
dolphins | +0.031 |
mber | +0.031 |
Neg logit contributions | |
Sue | -0.032 |
Kitty | -0.028 |
hy | -0.027 |
Tim | -0.026 |
Kim | -0.026 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Sue | +0.042 |
Kitty | +0.037 |
hy | +0.035 |
Kim | +0.035 |
Tim | +0.034 |
Neg logit contributions | |
utes | -0.045 |
ya | -0.044 |
maid | -0.043 |
mber | -0.043 |
dolphins | -0.043 |
Token | Leo |
Token ID | 19632 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
utes | +0.008 |
ya | +0.008 |
mber | +0.008 |
dolphins | +0.008 |
maid | +0.008 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.003 |
hy | -0.003 |
Kim | -0.003 |
Tim | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
utes | +0.018 |
dolphins | +0.017 |
ya | +0.017 |
mber | +0.017 |
targets | +0.017 |
Neg logit contributions | |
Sue | -0.010 |
Kitty | -0.009 |
Tim | -0.008 |
hy | -0.008 |
She | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
hy | +0.034 |
Sue | +0.031 |
house | +0.030 |
blond | +0.028 |
coat | +0.028 |
Neg logit contributions | |
ya | -0.064 |
dolphins | -0.059 |
mber | -0.058 |
la | -0.056 |
targets | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Sue | +0.016 |
Kitty | +0.013 |
Kim | +0.012 |
hy | +0.012 |
Kim | +0.012 |
Neg logit contributions | |
ya | -0.024 |
maid | -0.024 |
utes | -0.024 |
dolphins | -0.024 |
mber | -0.023 |
Token | said |
Token ID | 531 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Sue | +0.017 |
� | +0.016 |
hy | +0.015 |
Kim | +0.015 |
Kitty | +0.015 |
Neg logit contributions | |
ya | -0.017 |
mber | -0.016 |
dolphins | -0.016 |
maid | -0.015 |
dolphin | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
maid | +0.041 |
ya | +0.041 |
mber | +0.041 |
ub | +0.041 |
utes | +0.040 |
Neg logit contributions | |
Sue | -0.028 |
Kitty | -0.024 |
Kim | -0.024 |
hy | -0.024 |
lick | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
utes | +0.019 |
ya | +0.019 |
mber | +0.018 |
dolphins | +0.018 |
maid | +0.018 |
Neg logit contributions | |
Sue | -0.021 |
Kitty | -0.018 |
hy | -0.018 |
Kim | -0.017 |
Tim | -0.017 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
utes | +0.011 |
ya | +0.011 |
mber | +0.011 |
dolphins | +0.010 |
asper | +0.010 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.008 |
hy | -0.008 |
Kim | -0.007 |
Tim | -0.007 |
Token | aling |
Token ID | 4272 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
maid | +0.174 |
utes | +0.173 |
dolphins | +0.169 |
dolphin | +0.166 |
submarine | +0.161 |
Neg logit contributions | |
Sue | -0.175 |
hy | -0.146 |
Kitty | -0.145 |
Kim | -0.144 |
house | -0.142 |
Token | is |
Token ID | 318 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
utes | +0.012 |
ya | +0.011 |
maid | +0.011 |
dolphins | +0.011 |
mber | +0.011 |
Neg logit contributions | |
Sue | -0.010 |
Kitty | -0.008 |
hy | -0.008 |
Kim | -0.008 |
Tim | -0.008 |
Token | wrong |
Token ID | 2642 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
Sue | +0.014 |
Kitty | +0.012 |
hy | +0.012 |
Kim | +0.011 |
Tim | +0.011 |
Neg logit contributions | |
utes | -0.021 |
ya | -0.021 |
dolphins | -0.020 |
mber | -0.020 |
maid | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
utes | +0.043 |
ya | +0.041 |
maid | +0.041 |
mber | +0.041 |
dolphins | +0.040 |
Neg logit contributions | |
Sue | -0.021 |
Kitty | -0.016 |
Tim | -0.015 |
Kim | -0.015 |
hy | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
ya | +0.010 |
mber | +0.010 |
dolphins | +0.010 |
utes | +0.009 |
maid | +0.009 |
Neg logit contributions | |
Sue | -0.008 |
hy | -0.007 |
Kitty | -0.007 |
Kim | -0.007 |
Tim | -0.006 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
utes | +0.015 |
maid | +0.014 |
ya | +0.014 |
mber | +0.014 |
submarine | +0.014 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.007 |
Tim | -0.007 |
house | -0.007 |
She | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
Sue | +0.024 |
hy | +0.022 |
hetically | +0.019 |
Kitty | +0.019 |
� | +0.018 |
Neg logit contributions | |
dolphins | -0.059 |
utes | -0.059 |
ya | -0.058 |
dolphin | -0.057 |
mber | -0.057 |
Token | cat |
Token ID | 3797 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
utes | +0.043 |
asper | +0.042 |
ub | +0.041 |
ya | +0.041 |
ico | +0.040 |
Neg logit contributions | |
Sue | -0.020 |
Kitty | -0.017 |
Tim | -0.015 |
hy | -0.015 |
shake | -0.015 |
Token | named |
Token ID | 3706 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Sue | +0.026 |
Kim | +0.022 |
blond | +0.022 |
Kitty | +0.021 |
hy | +0.021 |
Neg logit contributions | |
utes | -0.031 |
fish | -0.030 |
dolphin | -0.030 |
dolphins | -0.030 |
eds | -0.029 |
Token | Sy |
Token ID | 1632 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ya | +0.023 |
utes | +0.023 |
dolphins | +0.022 |
dolphin | +0.022 |
mber | +0.022 |
Neg logit contributions | |
Sue | -0.009 |
hetically | -0.009 |
hy | -0.008 |
house | -0.008 |
lick | -0.007 |
Token | lves |
Token ID | 31018 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
utes | +0.048 |
mber | +0.045 |
maid | +0.042 |
ya | +0.042 |
dolphins | +0.042 |
Neg logit contributions | |
Sue | -0.112 |
Kitty | -0.103 |
hy | -0.100 |
Tim | -0.099 |
Kim | -0.097 |
Token | ter |
Token ID | 353 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
utes | +0.171 |
mber | +0.167 |
ya | +0.163 |
asper | +0.158 |
va | +0.157 |
Neg logit contributions | |
Sue | -0.171 |
Kitty | -0.147 |
Tim | -0.141 |
hy | -0.139 |
Kim | -0.139 |
Token | trying |
Token ID | 2111 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
utes | +0.078 |
maid | +0.075 |
dolphins | +0.074 |
ub | +0.074 |
fish | +0.074 |
Neg logit contributions | |
Sue | -0.049 |
Kitty | -0.040 |
hy | -0.039 |
Kim | -0.039 |
blond | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
utes | +0.085 |
maid | +0.084 |
mber | +0.083 |
ya | +0.082 |
ub | +0.082 |
Neg logit contributions | |
Sue | -0.046 |
Kitty | -0.036 |
Tim | -0.033 |
Kim | -0.032 |
She | -0.031 |
Token | catch |
Token ID | 4929 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
utes | +0.016 |
dolphins | +0.015 |
ya | +0.015 |
maid | +0.015 |
dolphin | +0.015 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.010 |
hy | -0.010 |
Kim | -0.010 |
Tim | -0.010 |
Token | him |
Token ID | 683 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
utes | +0.048 |
targets | +0.048 |
dolphins | +0.047 |
ya | +0.047 |
ub | +0.047 |
Neg logit contributions | |
Sue | -0.025 |
hy | -0.021 |
hetically | -0.020 |
Kim | -0.020 |
Kitty | -0.019 |
Token | said |
Token ID | 531 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
utes | +0.010 |
ya | +0.010 |
mber | +0.010 |
maid | +0.010 |
dolphins | +0.010 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.008 |
hy | -0.008 |
Kim | -0.008 |
Tim | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
maid | +0.014 |
va | +0.013 |
ya | +0.013 |
fish | +0.013 |
crew | +0.013 |
Neg logit contributions | |
Kim | -0.014 |
Kitty | -0.013 |
Sue | -0.013 |
hy | -0.012 |
Wh | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Sue | +0.004 |
hy | +0.004 |
Kitty | +0.004 |
Kim | +0.003 |
hetically | +0.003 |
Neg logit contributions | |
utes | -0.007 |
mber | -0.006 |
ya | -0.006 |
dolphins | -0.006 |
maid | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
utes | +0.009 |
ya | +0.009 |
maid | +0.009 |
dolphins | +0.009 |
mber | +0.009 |
Neg logit contributions | |
Sue | -0.005 |
Kitty | -0.004 |
Kim | -0.004 |
Tim | -0.004 |
hy | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
utes | +0.013 |
ya | +0.013 |
maid | +0.012 |
dolphins | +0.012 |
mber | +0.012 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.011 |
hy | -0.010 |
Kim | -0.010 |
Tim | -0.010 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
hy | +0.010 |
Tim | +0.010 |
Kim | +0.010 |
Neg logit contributions | |
utes | -0.020 |
ya | -0.020 |
maid | -0.020 |
dolphins | -0.019 |
mber | -0.019 |
Token | ak |
Token ID | 461 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
utes | +0.177 |
maid | +0.176 |
dolphins | +0.171 |
dolphin | +0.165 |
crew | +0.165 |
Neg logit contributions | |
Sue | -0.155 |
Kitty | -0.127 |
hy | -0.125 |
Kim | -0.124 |
Tim | -0.124 |
Token | is |
Token ID | 318 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
utes | +0.018 |
ya | +0.018 |
maid | +0.017 |
mber | +0.017 |
fish | +0.017 |
Neg logit contributions | |
Sue | -0.016 |
Kitty | -0.014 |
hy | -0.013 |
Kim | -0.013 |
Tim | -0.013 |
Token | too |
Token ID | 1165 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Sue | +0.027 |
Kitty | +0.023 |
hy | +0.022 |
Kim | +0.021 |
Tim | +0.021 |
Neg logit contributions | |
utes | -0.045 |
ya | -0.044 |
dolphins | -0.043 |
maid | -0.043 |
mber | -0.043 |
Token | hard |
Token ID | 1327 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Sue | +0.030 |
Kitty | +0.024 |
Tim | +0.022 |
hy | +0.022 |
Kim | +0.022 |
Neg logit contributions | |
utes | -0.050 |
ya | -0.048 |
maid | -0.048 |
dolphins | -0.047 |
mber | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Sue | +0.062 |
Kitty | +0.051 |
hy | +0.049 |
Tim | +0.048 |
Kim | +0.048 |
Neg logit contributions | |
utes | -0.099 |
ya | -0.095 |
maid | -0.095 |
mber | -0.094 |
dolphins | -0.094 |
Token | most |
Token ID | 749 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Sue | +0.022 |
Kitty | +0.019 |
hy | +0.018 |
Tim | +0.018 |
Kim | +0.018 |
Neg logit contributions | |
utes | -0.028 |
ya | -0.027 |
mber | -0.027 |
maid | -0.027 |
dolphins | -0.027 |
Token | perfect |
Token ID | 2818 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
utes | +0.015 |
ya | +0.014 |
maid | +0.014 |
mber | +0.014 |
dolphins | +0.014 |
Neg logit contributions | |
Sue | -0.013 |
Kitty | -0.011 |
hy | -0.011 |
Tim | -0.010 |
Kim | -0.010 |
Token | present |
Token ID | 1944 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
utes | +0.061 |
ya | +0.058 |
maid | +0.057 |
mber | +0.057 |
dolphins | +0.057 |
Neg logit contributions | |
Sue | -0.058 |
Kitty | -0.050 |
hy | -0.048 |
Kim | -0.047 |
Tim | -0.047 |
Token | ! |
Token ID | 0 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
utes | +0.014 |
ya | +0.014 |
maid | +0.013 |
dolphins | +0.013 |
mber | +0.013 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.007 |
hy | -0.007 |
Kim | -0.007 |
Tim | -0.007 |
Token | Sy |
Token ID | 1632 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
utes | +0.018 |
ya | +0.017 |
maid | +0.017 |
dolphins | +0.017 |
mber | +0.017 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.008 |
hy | -0.007 |
Kim | -0.007 |
Tim | -0.007 |
Token | lves |
Token ID | 31018 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
utes | +0.043 |
dolphins | +0.038 |
maid | +0.037 |
mber | +0.037 |
ya | +0.036 |
Neg logit contributions | |
Sue | -0.109 |
Kitty | -0.099 |
hy | -0.098 |
Tim | -0.096 |
Kim | -0.096 |
Token | ter |
Token ID | 353 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
utes | +0.171 |
mber | +0.164 |
dolphins | +0.156 |
asper | +0.155 |
ya | +0.155 |
Neg logit contributions | |
Sue | -0.159 |
Kitty | -0.135 |
Tim | -0.132 |
hy | -0.129 |
Kim | -0.128 |
Token | was |
Token ID | 373 |
Feature activation | +3.20e-03 |
Pos logit contributions | |
utes | +0.087 |
ya | +0.086 |
maid | +0.084 |
mber | +0.084 |
dolphins | +0.083 |
Neg logit contributions | |
Sue | -0.064 |
Kitty | -0.054 |
hy | -0.051 |
Kim | -0.051 |
Tim | -0.050 |
Token | so |
Token ID | 523 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
utes | +0.000 |
ya | +0.000 |
dolphins | +0.000 |
maid | +0.000 |
mber | +0.000 |
Neg logit contributions | |
Sue | -0.000 |
Kitty | -0.000 |
hy | -0.000 |
Kim | -0.000 |
Tim | -0.000 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
utes | +0.016 |
ya | +0.016 |
mber | +0.015 |
dolphins | +0.015 |
va | +0.015 |
Neg logit contributions | |
Sue | -0.016 |
Kitty | -0.015 |
Kim | -0.014 |
hy | -0.014 |
hetically | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
Sue | +0.010 |
Kitty | +0.008 |
hy | +0.008 |
Kim | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
utes | -0.016 |
ya | -0.016 |
maid | -0.016 |
mber | -0.016 |
dolphins | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.005 |
mber | +0.005 |
dolphins | +0.005 |
maid | +0.005 |
Neg logit contributions | |
Sue | -0.002 |
Kitty | -0.002 |
hy | -0.002 |
Kim | -0.002 |
Tim | -0.001 |
Token | Welcome |
Token ID | 14618 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
utes | +0.034 |
ya | +0.033 |
mber | +0.032 |
dolphins | +0.032 |
maid | +0.032 |
Neg logit contributions | |
Sue | -0.028 |
Kitty | -0.024 |
hy | -0.023 |
Kim | -0.023 |
Tim | -0.023 |
Token | home |
Token ID | 1363 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
utes | +0.037 |
ya | +0.034 |
dolphins | +0.034 |
maid | +0.034 |
mber | +0.034 |
Neg logit contributions | |
Sue | -0.029 |
Kitty | -0.024 |
Tim | -0.023 |
hy | -0.022 |
Kim | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
utes | +0.040 |
ya | +0.038 |
maid | +0.038 |
dolphins | +0.037 |
mber | +0.037 |
Neg logit contributions | |
Sue | -0.032 |
Kitty | -0.027 |
hy | -0.025 |
Tim | -0.025 |
Kim | -0.025 |
Token | B |
Token ID | 347 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
utes | +0.046 |
ya | +0.044 |
maid | +0.044 |
mber | +0.044 |
dolphins | +0.044 |
Neg logit contributions | |
Sue | -0.027 |
Kitty | -0.022 |
hy | -0.021 |
Kim | -0.021 |
Tim | -0.021 |
Token | oun |
Token ID | 977 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
utes | +0.043 |
ya | +0.040 |
maid | +0.039 |
mber | +0.039 |
ub | +0.038 |
Neg logit contributions | |
Sue | -0.068 |
Kitty | -0.061 |
hy | -0.058 |
Kim | -0.058 |
Tim | -0.058 |
Token | cy |
Token ID | 948 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
utes | +0.159 |
mber | +0.151 |
ya | +0.150 |
dolphins | +0.146 |
ub | +0.141 |
Neg logit contributions | |
Sue | -0.140 |
Tim | -0.121 |
Kitty | -0.121 |
hy | -0.120 |
house | -0.114 |
Token | !", |
Token ID | 40754 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
utes | +0.105 |
ya | +0.097 |
mber | +0.096 |
maid | +0.096 |
dolphins | +0.095 |
Neg logit contributions | |
Sue | -0.084 |
Kitty | -0.071 |
hy | -0.069 |
Tim | -0.068 |
Kim | -0.066 |
Token | they |
Token ID | 484 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
utes | +0.031 |
ya | +0.030 |
dolphins | +0.030 |
maid | +0.029 |
mber | +0.029 |
Neg logit contributions | |
Sue | -0.019 |
Kitty | -0.016 |
hy | -0.015 |
Kim | -0.015 |
Tim | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
utes | +0.039 |
ya | +0.038 |
mber | +0.037 |
maid | +0.037 |
dolphins | +0.037 |
Neg logit contributions | |
Sue | -0.024 |
Kitty | -0.019 |
hy | -0.018 |
Tim | -0.018 |
Kim | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
utes | +0.031 |
maid | +0.031 |
ya | +0.030 |
dolphins | +0.030 |
crew | +0.029 |
Neg logit contributions | |
Sue | -0.019 |
Kitty | -0.016 |
hy | -0.016 |
Kim | -0.015 |
Kim | -0.015 |
Token | behind |
Token ID | 2157 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
utes | +0.067 |
ya | +0.064 |
dolphins | +0.064 |
maid | +0.064 |
mber | +0.062 |
Neg logit contributions | |
Sue | -0.035 |
Kitty | -0.029 |
Kim | -0.027 |
hy | -0.026 |
Tim | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
dolphins | +0.012 |
ya | +0.012 |
utes | +0.011 |
targets | +0.011 |
maid | +0.011 |
Neg logit contributions | |
Sue | -0.007 |
hy | -0.006 |
hetically | -0.006 |
Kitty | -0.006 |
Kim | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
utes | +0.028 |
ya | +0.027 |
maid | +0.026 |
dolphins | +0.026 |
mber | +0.026 |
Neg logit contributions | |
Sue | -0.013 |
Kitty | -0.010 |
hy | -0.010 |
Kim | -0.009 |
Tim | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Sue | +0.008 |
Kim | +0.007 |
hy | +0.007 |
hetically | +0.007 |
Kim | +0.007 |
Neg logit contributions | |
mber | -0.012 |
ya | -0.012 |
utes | -0.011 |
va | -0.011 |
dolphins | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Sue | +0.008 |
Kitty | +0.007 |
hy | +0.006 |
Kim | +0.006 |
Tim | +0.006 |
Neg logit contributions | |
utes | -0.014 |
ya | -0.013 |
maid | -0.013 |
dolphins | -0.013 |
mber | -0.013 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
Sue | +0.005 |
Kim | +0.004 |
Kitty | +0.004 |
hy | +0.004 |
Tim | +0.004 |
Neg logit contributions | |
ya | -0.005 |
utes | -0.005 |
mber | -0.005 |
va | -0.005 |
dolphins | -0.005 |
Token | lla |
Token ID | 8466 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
utes | +0.166 |
maid | +0.165 |
dolphins | +0.163 |
submarine | +0.157 |
dolphin | +0.157 |
Neg logit contributions | |
Sue | -0.144 |
hy | -0.130 |
Kitty | -0.123 |
She | -0.119 |
Tim | -0.114 |
Token | couldn |
Token ID | 3521 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
utes | +0.126 |
dolphins | +0.118 |
maid | +0.116 |
mber | +0.116 |
ya | +0.116 |
Neg logit contributions | |
Sue | -0.060 |
Kitty | -0.048 |
Tim | -0.046 |
She | -0.045 |
hy | -0.044 |
Token | 't |
Token ID | 470 |
Feature activation | +7.87e-04 |
Pos logit contributions | |
utes | +0.006 |
ub | +0.006 |
mber | +0.006 |
va | +0.006 |
ya | +0.006 |
Neg logit contributions | |
Sue | -0.007 |
blond | -0.006 |
hy | -0.006 |
Kitty | -0.006 |
Kim | -0.006 |
Token | resist |
Token ID | 4180 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
ya | +0.000 |
maid | +0.000 |
utes | +0.000 |
ub | +0.000 |
fish | +0.000 |
Neg logit contributions | |
Sue | -0.000 |
Kitty | -0.000 |
Kim | -0.000 |
hy | -0.000 |
Tim | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
utes | +0.038 |
ya | +0.037 |
dolphins | +0.037 |
maid | +0.036 |
dolphin | +0.035 |
Neg logit contributions | |
Sue | -0.026 |
Kitty | -0.022 |
hy | -0.021 |
Kim | -0.021 |
Tim | -0.020 |
Token | reach |
Token ID | 3151 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
hetically | +0.001 |
Sue | +0.001 |
hy | +0.001 |
blond | +0.001 |
chocolate | +0.001 |
Neg logit contributions | |
fish | -0.001 |
crew | -0.001 |
maid | -0.001 |
dolphin | -0.001 |
utes | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.003 |
hy | +0.003 |
Kim | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
utes | -0.007 |
ya | -0.007 |
dolphins | -0.007 |
maid | -0.007 |
mber | -0.007 |
Token | ! |
Token ID | 0 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Sue | +0.005 |
hy | +0.004 |
Kitty | +0.004 |
Kim | +0.004 |
blond | +0.004 |
Neg logit contributions | |
utes | -0.005 |
ub | -0.005 |
ya | -0.005 |
maid | -0.005 |
fish | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
Sue | +0.003 |
Kim | +0.003 |
hy | +0.003 |
hetically | +0.003 |
Kim | +0.003 |
Neg logit contributions | |
mber | -0.007 |
ya | -0.006 |
utes | -0.006 |
va | -0.006 |
dolphins | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
utes | +0.001 |
maid | +0.001 |
ya | +0.001 |
dolphins | +0.001 |
mber | +0.001 |
Neg logit contributions | |
Sue | -0.000 |
Kitty | -0.000 |
Tim | -0.000 |
hy | -0.000 |
Kim | -0.000 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.005 |
mber | +0.005 |
va | +0.005 |
dolphins | +0.005 |
Neg logit contributions | |
Sue | -0.005 |
Kim | -0.004 |
Kitty | -0.004 |
hy | -0.004 |
Tim | -0.004 |
Token | lla |
Token ID | 8466 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
utes | +0.167 |
maid | +0.164 |
dolphins | +0.164 |
submarine | +0.159 |
dolphin | +0.159 |
Neg logit contributions | |
Sue | -0.139 |
hy | -0.126 |
Kitty | -0.119 |
She | -0.114 |
house | -0.112 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
utes | +0.136 |
ya | +0.127 |
dolphins | +0.126 |
mber | +0.126 |
maid | +0.125 |
Neg logit contributions | |
Sue | -0.068 |
Kitty | -0.053 |
Tim | -0.052 |
hy | -0.051 |
She | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Sue | +0.005 |
hy | +0.004 |
Kim | +0.004 |
house | +0.004 |
Kitty | +0.004 |
Neg logit contributions | |
ya | -0.008 |
utes | -0.007 |
dolphins | -0.007 |
targets | -0.007 |
maid | -0.007 |
Token | stand |
Token ID | 1302 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Sue | +0.009 |
Kitty | +0.008 |
Kim | +0.007 |
hy | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
utes | -0.010 |
ya | -0.009 |
maid | -0.009 |
mber | -0.009 |
dolphins | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ya | +0.009 |
fish | +0.009 |
utes | +0.009 |
ub | +0.009 |
mber | +0.008 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.008 |
blond | -0.007 |
Tim | -0.007 |
Wh | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
utes | +0.047 |
mber | +0.045 |
maid | +0.045 |
ya | +0.045 |
ub | +0.044 |
Neg logit contributions | |
Sue | -0.024 |
Kitty | -0.019 |
Tim | -0.018 |
Kim | -0.017 |
hy | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
utes | +0.022 |
ya | +0.022 |
maid | +0.022 |
fish | +0.022 |
ub | +0.021 |
Neg logit contributions | |
Sue | -0.016 |
hy | -0.015 |
Kim | -0.014 |
blond | -0.014 |
hetically | -0.014 |
Token | |
Token ID | 220 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Sue | +0.007 |
hy | +0.006 |
Kitty | +0.006 |
Kim | +0.006 |
hetically | +0.005 |
Neg logit contributions | |
utes | -0.010 |
ya | -0.010 |
mber | -0.010 |
dolphins | -0.009 |
ub | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
utes | +0.045 |
ya | +0.043 |
mber | +0.043 |
maid | +0.042 |
dolphins | +0.042 |
Neg logit contributions | |
Sue | -0.029 |
Kitty | -0.024 |
hy | -0.024 |
Kim | -0.022 |
Tim | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
Tim | +0.002 |
She | +0.002 |
Kim | +0.002 |
Neg logit contributions | |
utes | -0.004 |
maid | -0.004 |
ya | -0.004 |
dolphins | -0.004 |
submarine | -0.004 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
ya | +0.001 |
utes | +0.001 |
mber | +0.001 |
dolphins | +0.001 |
va | +0.001 |
Neg logit contributions | |
Sue | -0.001 |
Kim | -0.001 |
Kitty | -0.001 |
hy | -0.001 |
Tim | -0.001 |
Token | lla |
Token ID | 8466 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
maid | +0.165 |
utes | +0.163 |
dolphins | +0.161 |
submarine | +0.158 |
dolphin | +0.157 |
Neg logit contributions | |
Sue | -0.147 |
hy | -0.127 |
Kitty | -0.122 |
She | -0.120 |
house | -0.114 |
Token | carefully |
Token ID | 7773 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
utes | +0.118 |
ya | +0.112 |
maid | +0.112 |
dolphins | +0.111 |
mber | +0.111 |
Neg logit contributions | |
Sue | -0.068 |
Kitty | -0.055 |
Tim | -0.052 |
hy | -0.051 |
Kim | -0.051 |
Token | walked |
Token ID | 6807 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ya | +0.002 |
dolphins | +0.002 |
dolphin | +0.001 |
asper | +0.001 |
utes | +0.001 |
Neg logit contributions | |
Sue | -0.001 |
Kitty | -0.001 |
hy | -0.001 |
Kim | -0.001 |
Kim | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
Sue | +0.044 |
Kitty | +0.038 |
hy | +0.037 |
Kim | +0.036 |
Tim | +0.035 |
Neg logit contributions | |
utes | -0.053 |
ya | -0.052 |
dolphins | -0.050 |
mber | -0.050 |
maid | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
ya | +0.003 |
dolphins | +0.003 |
utes | +0.003 |
mber | +0.002 |
dolphin | +0.002 |
Neg logit contributions | |
Sue | -0.003 |
hy | -0.003 |
Kitty | -0.003 |
Kim | -0.003 |
hetically | -0.003 |
Token | white |
Token ID | 2330 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
utes | +0.003 |
mber | +0.003 |
ya | +0.003 |
dolphins | +0.003 |
maid | +0.003 |
Neg logit contributions | |
Sue | -0.003 |
Kitty | -0.003 |
hy | -0.003 |
Tim | -0.002 |
Kim | -0.002 |
Token | stones |
Token ID | 14966 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
utes | +0.003 |
ya | +0.003 |
maid | +0.003 |
dolphins | +0.003 |
mber | +0.002 |
Neg logit contributions | |
Sue | -0.003 |
Kitty | -0.002 |
hy | -0.002 |
Kim | -0.002 |
Tim | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
utes | +0.011 |
ya | +0.010 |
dolphins | +0.010 |
maid | +0.010 |
fish | +0.010 |
Neg logit contributions | |
Sue | -0.005 |
Kitty | -0.004 |
Kim | -0.004 |
hy | -0.004 |
Tim | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Sue | +0.010 |
hy | +0.009 |
Kim | +0.009 |
Kitty | +0.008 |
hetically | +0.008 |
Neg logit contributions | |
utes | -0.014 |
ya | -0.014 |
mber | -0.014 |
va | -0.013 |
dolphins | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +4.84e-03 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.003 |
Tim | +0.003 |
She | +0.003 |
hy | +0.003 |
Neg logit contributions | |
utes | -0.007 |
maid | -0.007 |
ya | -0.007 |
dolphins | -0.007 |
submarine | -0.007 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
utes | +0.000 |
ya | +0.000 |
mber | +0.000 |
dolphins | +0.000 |
maid | +0.000 |
Neg logit contributions | |
Sue | -0.000 |
Kitty | -0.000 |
Kim | -0.000 |
hy | -0.000 |
Tim | -0.000 |
Token | lla |
Token ID | 8466 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
maid | +0.164 |
utes | +0.163 |
dolphins | +0.160 |
dolphin | +0.157 |
submarine | +0.157 |
Neg logit contributions | |
Sue | -0.142 |
hy | -0.125 |
Kitty | -0.121 |
She | -0.116 |
house | -0.113 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
utes | +0.121 |
dolphins | +0.113 |
maid | +0.113 |
targets | +0.113 |
submarine | +0.113 |
Neg logit contributions | |
Sue | -0.061 |
Tim | -0.048 |
She | -0.048 |
Kitty | -0.047 |
house | -0.046 |
Token | her |
Token ID | 607 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ya | +0.017 |
utes | +0.017 |
dolphins | +0.017 |
mber | +0.016 |
maid | +0.016 |
Neg logit contributions | |
Sue | -0.006 |
hy | -0.006 |
Kitty | -0.005 |
house | -0.005 |
hetically | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
Sue | +0.006 |
Kitty | +0.005 |
Tim | +0.004 |
Kim | +0.004 |
hy | +0.004 |
Neg logit contributions | |
utes | -0.010 |
ya | -0.009 |
mber | -0.009 |
maid | -0.009 |
dolphins | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
Sue | +0.027 |
Kitty | +0.024 |
hy | +0.024 |
Kim | +0.022 |
Kim | +0.021 |
Neg logit contributions | |
utes | -0.037 |
ya | -0.037 |
dolphins | -0.036 |
maid | -0.035 |
mber | -0.035 |
Token | she |
Token ID | 673 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
dolphins | +0.024 |
dolphin | +0.023 |
coral | +0.021 |
pearl | +0.020 |
mber | +0.020 |
Neg logit contributions | |
hy | -0.023 |
hetically | -0.022 |
� | -0.021 |
osc | -0.021 |
sill | -0.021 |
Token | said |
Token ID | 531 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
utes | +0.059 |
ya | +0.055 |
perspective | +0.054 |
ub | +0.054 |
dolphins | +0.053 |
Neg logit contributions | |
Sue | -0.030 |
Kitty | -0.023 |
Tim | -0.022 |
Kim | -0.021 |
Tom | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
dolphins | +0.048 |
maid | +0.047 |
mber | +0.047 |
va | +0.047 |
fish | +0.046 |
Neg logit contributions | |
Sue | -0.028 |
Kim | -0.026 |
Kitty | -0.025 |
hy | -0.025 |
hetically | -0.025 |
Token | " |
Token ID | 366 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
utes | +0.037 |
ya | +0.036 |
mber | +0.035 |
dolphins | +0.035 |
maid | +0.034 |
Neg logit contributions | |
Sue | -0.033 |
Kitty | -0.029 |
hy | -0.028 |
Kim | -0.027 |
Tim | -0.026 |
Token | Re |
Token ID | 3041 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
mber | +0.011 |
ya | +0.011 |
utes | +0.011 |
asper | +0.011 |
dolphins | +0.011 |
Neg logit contributions | |
Sue | -0.010 |
Kitty | -0.008 |
hy | -0.008 |
Kim | -0.008 |
blond | -0.008 |
Token | ve |
Token ID | 303 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
utes | +0.061 |
ya | +0.058 |
mber | +0.056 |
maid | +0.056 |
dolphins | +0.055 |
Neg logit contributions | |
Sue | -0.055 |
Kitty | -0.048 |
Kim | -0.045 |
hy | -0.045 |
Tim | -0.045 |
Token | al |
Token ID | 282 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
utes | +0.195 |
maid | +0.180 |
ub | +0.178 |
dolphins | +0.175 |
ya | +0.175 |
Neg logit contributions | |
Sue | -0.122 |
Kitty | -0.097 |
Tim | -0.095 |
Kim | -0.090 |
hy | -0.089 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
maid | +0.039 |
utes | +0.039 |
ya | +0.038 |
fish | +0.038 |
ub | +0.038 |
Neg logit contributions | |
Sue | -0.023 |
Kitty | -0.020 |
hy | -0.018 |
Kim | -0.018 |
Kim | -0.018 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
hy | +0.001 |
hetically | +0.001 |
Sue | +0.001 |
blond | +0.001 |
Kim | +0.001 |
Neg logit contributions | |
utes | -0.003 |
mber | -0.002 |
ya | -0.002 |
ub | -0.002 |
va | -0.002 |
Token | jumped |
Token ID | 11687 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.005 |
maid | +0.005 |
mber | +0.005 |
dolphins | +0.005 |
Neg logit contributions | |
Sue | -0.003 |
Kitty | -0.003 |
hy | -0.003 |
Kim | -0.003 |
Tim | -0.003 |
Token | out |
Token ID | 503 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Sue | +0.016 |
Kitty | +0.014 |
hy | +0.014 |
Kim | +0.014 |
blond | +0.013 |
Neg logit contributions | |
utes | -0.021 |
ya | -0.020 |
dolphins | -0.020 |
maid | -0.020 |
ub | -0.020 |
Token | pretty |
Token ID | 2495 |
Feature activation | -9.69e-03 |
Pos logit contributions | |
utes | +0.016 |
ya | +0.015 |
mber | +0.015 |
dolphins | +0.015 |
maid | +0.015 |
Neg logit contributions | |
Sue | -0.015 |
Kitty | -0.013 |
hy | -0.013 |
Kim | -0.013 |
hetically | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Sue | +0.000 |
Kitty | +0.000 |
Kim | +0.000 |
hy | +0.000 |
Kim | +0.000 |
Neg logit contributions | |
ya | -0.000 |
dolphins | -0.000 |
maid | -0.000 |
fish | -0.000 |
utes | -0.000 |
Token | she |
Token ID | 673 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Sue | +0.018 |
hy | +0.016 |
Kitty | +0.015 |
Kim | +0.015 |
� | +0.015 |
Neg logit contributions | |
ya | -0.024 |
mber | -0.023 |
dolphins | -0.023 |
utes | -0.022 |
va | -0.022 |
Token | asked |
Token ID | 1965 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
utes | +0.049 |
dolphins | +0.044 |
maid | +0.044 |
ya | +0.044 |
submarine | +0.044 |
Neg logit contributions | |
Sue | -0.031 |
Kitty | -0.026 |
Tim | -0.025 |
hy | -0.024 |
She | -0.023 |
Token | O |
Token ID | 440 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
ya | +0.039 |
dolphins | +0.037 |
utes | +0.036 |
maid | +0.036 |
mber | +0.036 |
Neg logit contributions | |
Sue | -0.021 |
hy | -0.019 |
house | -0.017 |
Kitty | -0.017 |
Kim | -0.017 |
Token | ll |
Token ID | 297 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
utes | +0.027 |
ya | +0.026 |
mber | +0.025 |
ub | +0.025 |
maid | +0.025 |
Neg logit contributions | |
Sue | -0.041 |
hy | -0.035 |
Kim | -0.035 |
Kitty | -0.035 |
Tim | -0.035 |
Token | ie |
Token ID | 494 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
utes | +0.149 |
ya | +0.143 |
maid | +0.141 |
dolphins | +0.140 |
mber | +0.139 |
Neg logit contributions | |
Sue | -0.144 |
Kitty | -0.125 |
hy | -0.121 |
Kim | -0.119 |
Tim | -0.118 |
Token | a |
Token ID | 257 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
utes | +0.059 |
ya | +0.057 |
maid | +0.056 |
dolphins | +0.056 |
mber | +0.056 |
Neg logit contributions | |
Sue | -0.037 |
Kitty | -0.031 |
hy | -0.030 |
Kim | -0.029 |
Tim | -0.029 |
Token | question |
Token ID | 1808 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
utes | +0.064 |
ya | +0.061 |
maid | +0.060 |
dolphins | +0.060 |
mber | +0.059 |
Neg logit contributions | |
Sue | -0.052 |
Kitty | -0.045 |
hy | -0.043 |
Kim | -0.042 |
Tim | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
ya | +0.033 |
utes | +0.033 |
dolphins | +0.033 |
maid | +0.033 |
fish | +0.032 |
Neg logit contributions | |
Sue | -0.019 |
Kitty | -0.017 |
hy | -0.016 |
Kim | -0.015 |
Tim | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Sue | +0.000 |
hy | +0.000 |
Kitty | +0.000 |
hetically | +0.000 |
Kim | +0.000 |
Neg logit contributions | |
utes | -0.001 |
ub | -0.001 |
ya | -0.001 |
mber | -0.001 |
dolphins | -0.001 |
Token | blue |
Token ID | 4171 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
utes | +0.009 |
isha | +0.008 |
ub | +0.008 |
eds | +0.008 |
mber | +0.008 |
Neg logit contributions | |
Sue | -0.008 |
blond | -0.006 |
Tim | -0.006 |
hy | -0.006 |
shake | -0.006 |
Token | shells |
Token ID | 19679 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
isha | +0.020 |
utes | +0.020 |
mber | +0.020 |
ya | +0.019 |
chen | +0.019 |
Neg logit contributions | |
Sue | -0.025 |
Tim | -0.022 |
She | -0.022 |
hy | -0.020 |
shake | -0.020 |
Token | which |
Token ID | 543 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
utes | +0.008 |
ya | +0.008 |
dolphins | +0.008 |
maid | +0.008 |
mber | +0.007 |
Neg logit contributions | |
Sue | -0.005 |
Kitty | -0.004 |
hy | -0.004 |
Kim | -0.004 |
Tim | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.013 |
hy | +0.012 |
Kim | +0.012 |
Tim | +0.011 |
Neg logit contributions | |
utes | -0.026 |
ya | -0.025 |
dolphins | -0.025 |
maid | -0.025 |
mber | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
utes | +0.015 |
eds | +0.014 |
ub | +0.013 |
isha | +0.013 |
asper | +0.013 |
Neg logit contributions | |
Sue | -0.016 |
Tim | -0.013 |
Tom | -0.012 |
blond | -0.012 |
hy | -0.012 |
Token | mit |
Token ID | 2781 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
Sue | +0.010 |
Tim | +0.008 |
Kitty | +0.008 |
hy | +0.008 |
She | +0.008 |
Neg logit contributions | |
utes | -0.009 |
mber | -0.009 |
ub | -0.009 |
ya | -0.009 |
asper | -0.009 |
Token | crab |
Token ID | 32202 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
utes | +0.121 |
ya | +0.111 |
ub | +0.110 |
asper | +0.108 |
eds | +0.107 |
Neg logit contributions | |
Sue | -0.172 |
She | -0.144 |
Tim | -0.142 |
hy | -0.142 |
Kitty | -0.141 |
Token | proudly |
Token ID | 23017 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
utes | +0.047 |
ya | +0.046 |
maid | +0.045 |
dolphins | +0.045 |
mber | +0.045 |
Neg logit contributions | |
Sue | -0.034 |
Kitty | -0.029 |
hy | -0.028 |
Kim | -0.027 |
Tim | -0.027 |
Token | put |
Token ID | 1234 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
utes | +0.089 |
ya | +0.086 |
mber | +0.085 |
dolphins | +0.083 |
maid | +0.083 |
Neg logit contributions | |
Sue | -0.059 |
Kitty | -0.048 |
hy | -0.047 |
Tim | -0.046 |
Kim | -0.045 |
Token | in |
Token ID | 287 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Sue | +0.007 |
Kitty | +0.006 |
hy | +0.005 |
Kim | +0.005 |
Tim | +0.005 |
Neg logit contributions | |
utes | -0.010 |
ya | -0.010 |
dolphins | -0.010 |
maid | -0.010 |
mber | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
utes | +0.017 |
ya | +0.016 |
dolphins | +0.016 |
maid | +0.016 |
mber | +0.016 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.007 |
hy | -0.007 |
Kim | -0.006 |
Tim | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Sue | +0.026 |
hy | +0.024 |
Kitty | +0.023 |
blond | +0.022 |
Kim | +0.022 |
Neg logit contributions | |
utes | -0.030 |
ya | -0.029 |
dolphins | -0.028 |
maid | -0.028 |
targets | -0.028 |
Token | open |
Token ID | 1280 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
Sue | +0.010 |
hy | +0.010 |
blond | +0.010 |
Kim | +0.009 |
Kitty | +0.009 |
Neg logit contributions | |
ub | -0.009 |
utes | -0.009 |
targets | -0.009 |
maid | -0.009 |
fish | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Sue | +0.006 |
Kitty | +0.006 |
hy | +0.005 |
Kim | +0.005 |
Kim | +0.005 |
Neg logit contributions | |
utes | -0.010 |
maid | -0.010 |
ya | -0.010 |
dolphins | -0.010 |
targets | -0.010 |
Token | found |
Token ID | 1043 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
utes | +0.012 |
ya | +0.012 |
dolphins | +0.012 |
maid | +0.011 |
crew | +0.011 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.008 |
hy | -0.008 |
She | -0.008 |
Kim | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
utes | +0.033 |
dolphins | +0.032 |
maid | +0.031 |
ya | +0.031 |
targets | +0.031 |
Neg logit contributions | |
Sue | -0.020 |
hy | -0.018 |
Kitty | -0.017 |
Kim | -0.016 |
blond | -0.016 |
Token | lucky |
Token ID | 9670 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
utes | +0.030 |
maid | +0.030 |
crew | +0.029 |
ya | +0.029 |
dolphins | +0.029 |
Neg logit contributions | |
Sue | -0.018 |
hy | -0.017 |
Kitty | -0.017 |
Kim | -0.016 |
hetically | -0.015 |
Token | pie |
Token ID | 2508 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
maid | +0.167 |
ya | +0.162 |
utes | +0.161 |
pearl | +0.160 |
mber | +0.159 |
Neg logit contributions | |
hy | -0.101 |
Sue | -0.096 |
hetically | -0.093 |
Kitty | -0.093 |
Kim | -0.090 |
Token | inside |
Token ID | 2641 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
fish | +0.000 |
maid | +0.000 |
dolphins | +0.000 |
utes | +0.000 |
ya | +0.000 |
Neg logit contributions | |
Sue | -0.000 |
blond | -0.000 |
hy | -0.000 |
Kitty | -0.000 |
Kim | -0.000 |
Token | ! |
Token ID | 0 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
utes | +0.067 |
ya | +0.066 |
dolphins | +0.066 |
maid | +0.066 |
mber | +0.064 |
Neg logit contributions | |
Sue | -0.034 |
Kitty | -0.029 |
hy | -0.029 |
Kim | -0.026 |
blond | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Sue | +0.001 |
Kitty | +0.001 |
Tim | +0.001 |
Kim | +0.001 |
hy | +0.001 |
Neg logit contributions | |
utes | -0.003 |
ya | -0.003 |
maid | -0.003 |
dolphins | -0.003 |
mber | -0.003 |
Token | all |
Token ID | 477 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
utes | +0.009 |
ya | +0.008 |
mber | +0.008 |
dolphins | +0.008 |
maid | +0.008 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.003 |
Tim | -0.003 |
hy | -0.003 |
Kim | -0.003 |
Token | ak |
Token ID | 461 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ya | +0.016 |
utes | +0.015 |
mber | +0.015 |
dolphins | +0.015 |
maid | +0.014 |
Neg logit contributions | |
Sue | -0.015 |
Kim | -0.012 |
Kitty | -0.012 |
hy | -0.012 |
She | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Sue | +0.011 |
Kitty | +0.010 |
Kim | +0.009 |
Kim | +0.009 |
hy | +0.008 |
Neg logit contributions | |
utes | -0.017 |
ub | -0.017 |
dolphins | -0.016 |
maid | -0.016 |
fish | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Sue | +0.006 |
hy | +0.005 |
hetically | +0.005 |
Kitty | +0.005 |
house | +0.004 |
Neg logit contributions | |
utes | -0.019 |
ub | -0.018 |
dolphins | -0.017 |
maid | -0.017 |
mber | -0.017 |
Token | hoped |
Token ID | 10719 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Sue | +0.007 |
Kitty | +0.006 |
hy | +0.005 |
Kim | +0.005 |
Tim | +0.005 |
Neg logit contributions | |
utes | -0.010 |
ya | -0.010 |
maid | -0.009 |
dolphins | -0.009 |
mber | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
Sue | +0.014 |
hy | +0.013 |
hetically | +0.012 |
house | +0.012 |
Kitty | +0.012 |
Neg logit contributions | |
dolphins | -0.019 |
utes | -0.019 |
ya | -0.018 |
dolphin | -0.018 |
maid | -0.018 |
Token | fle |
Token ID | 5104 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
utes | +0.028 |
ya | +0.026 |
mber | +0.026 |
maid | +0.025 |
asper | +0.025 |
Neg logit contributions | |
Sue | -0.029 |
Kitty | -0.026 |
hy | -0.025 |
Tim | -0.024 |
Kim | -0.024 |
Token | a |
Token ID | 64 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ya | +0.090 |
utes | +0.082 |
mber | +0.080 |
dolphins | +0.077 |
submarine | +0.074 |
Neg logit contributions | |
Sue | -0.202 |
Kitty | -0.182 |
hy | -0.178 |
Tim | -0.174 |
She | -0.173 |
Token | would |
Token ID | 561 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
fish | +0.071 |
maid | +0.070 |
utes | +0.069 |
dolphins | +0.069 |
ya | +0.068 |
Neg logit contributions | |
Sue | -0.083 |
Kitty | -0.073 |
Kim | -0.072 |
hy | -0.071 |
Tim | -0.069 |
Token | hear |
Token ID | 3285 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
utes | +0.033 |
maid | +0.033 |
dolphins | +0.032 |
fish | +0.032 |
ub | +0.032 |
Neg logit contributions | |
Sue | -0.021 |
Kitty | -0.018 |
Kim | -0.017 |
hy | -0.017 |
hetically | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
Sue | +0.020 |
Kitty | +0.016 |
hy | +0.015 |
Kim | +0.014 |
Tim | +0.013 |
Neg logit contributions | |
utes | -0.053 |
dolphins | -0.052 |
ya | -0.052 |
maid | -0.051 |
ub | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
maid | +0.003 |
fish | +0.003 |
ub | +0.003 |
utes | +0.003 |
dolphins | +0.003 |
Neg logit contributions | |
Sue | -0.002 |
blond | -0.002 |
Kitty | -0.002 |
Kim | -0.002 |
hy | -0.002 |
Token | go |
Token ID | 467 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
utes | +0.039 |
dolphins | +0.038 |
ya | +0.038 |
maid | +0.038 |
dolphin | +0.037 |
Neg logit contributions | |
Sue | -0.022 |
hy | -0.019 |
Kitty | -0.018 |
Kim | -0.017 |
hetically | -0.017 |
Token | dancing |
Token ID | 15360 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.012 |
hy | +0.012 |
Kim | +0.012 |
Tim | +0.012 |
Neg logit contributions | |
utes | -0.019 |
ya | -0.019 |
maid | -0.018 |
dolphins | -0.018 |
mber | -0.018 |
Token | !" |
Token ID | 2474 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
utes | +0.033 |
ya | +0.032 |
mber | +0.032 |
maid | +0.031 |
asper | +0.031 |
Neg logit contributions | |
Sue | -0.020 |
Kitty | -0.016 |
Tim | -0.015 |
She | -0.014 |
Kim | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Sue | +0.002 |
hy | +0.002 |
Kitty | +0.001 |
hetically | +0.001 |
Kim | +0.001 |
Neg logit contributions | |
utes | -0.004 |
mber | -0.004 |
ya | -0.004 |
va | -0.004 |
ub | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
utes | +0.009 |
ya | +0.009 |
maid | +0.009 |
dolphins | +0.009 |
mber | +0.008 |
Neg logit contributions | |
Sue | -0.005 |
Kitty | -0.004 |
hy | -0.004 |
Kim | -0.004 |
Tim | -0.004 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
utes | +0.013 |
ya | +0.012 |
maid | +0.012 |
mber | +0.012 |
dolphins | +0.012 |
Neg logit contributions | |
Sue | -0.010 |
Kitty | -0.008 |
hy | -0.008 |
Kim | -0.008 |
Tim | -0.008 |
Token | lla |
Token ID | 8466 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
utes | +0.154 |
maid | +0.152 |
dolphins | +0.151 |
dolphin | +0.144 |
submarine | +0.143 |
Neg logit contributions | |
Sue | -0.140 |
hy | -0.119 |
Kitty | -0.118 |
house | -0.113 |
Tim | -0.111 |
Token | gul |
Token ID | 47161 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
utes | +0.122 |
targets | +0.117 |
submarine | +0.116 |
dolphins | +0.115 |
maid | +0.115 |
Neg logit contributions | |
Sue | -0.060 |
Kitty | -0.047 |
Tim | -0.044 |
hy | -0.043 |
She | -0.043 |
Token | ped |
Token ID | 9124 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
utes | +0.004 |
ya | +0.004 |
maid | +0.004 |
dolphins | +0.004 |
mber | +0.004 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.003 |
hy | -0.003 |
Kim | -0.003 |
Tim | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
Sue | +0.012 |
hy | +0.011 |
Kim | +0.010 |
Kitty | +0.010 |
Kim | +0.010 |
Neg logit contributions | |
utes | -0.013 |
dolphins | -0.013 |
ya | -0.013 |
dolphin | -0.013 |
maid | -0.013 |
Token | but |
Token ID | 475 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
Sue | +0.001 |
hy | +0.001 |
Kitty | +0.001 |
house | +0.001 |
Kim | +0.001 |
Neg logit contributions | |
ya | -0.001 |
mber | -0.001 |
utes | -0.001 |
dolphins | -0.001 |
dolphin | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
utes | +0.027 |
dolphins | +0.027 |
ub | +0.026 |
ya | +0.026 |
dolphin | +0.026 |
Neg logit contributions | |
Sue | -0.033 |
hy | -0.029 |
Kitty | -0.028 |
Kim | -0.028 |
Kim | -0.027 |
Token | think |
Token ID | 892 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Sue | +0.030 |
hy | +0.029 |
Kim | +0.027 |
Kim | +0.026 |
blond | +0.025 |
Neg logit contributions | |
dolphin | -0.032 |
ub | -0.032 |
fish | -0.032 |
perspective | -0.032 |
maid | -0.031 |
Token | that |
Token ID | 326 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
Sue | +0.010 |
hy | +0.008 |
Kitty | +0.008 |
Kim | +0.008 |
hetically | +0.007 |
Neg logit contributions | |
utes | -0.012 |
ya | -0.012 |
dolphins | -0.012 |
mber | -0.012 |
fish | -0.012 |
Token | maybe |
Token ID | 3863 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
dolphins | +0.004 |
utes | +0.004 |
ya | +0.004 |
dolphin | +0.004 |
mber | +0.004 |
Neg logit contributions | |
Sue | -0.002 |
hy | -0.002 |
Kitty | -0.002 |
Kim | -0.002 |
blond | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
Sue | +0.033 |
Kitty | +0.027 |
hy | +0.027 |
Kim | +0.025 |
Tim | +0.025 |
Neg logit contributions | |
utes | -0.055 |
ya | -0.054 |
dolphins | -0.054 |
maid | -0.053 |
mber | -0.053 |
Token | fle |
Token ID | 5104 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
utes | +0.002 |
ya | +0.002 |
maid | +0.002 |
mber | +0.002 |
dolphins | +0.002 |
Neg logit contributions | |
Sue | -0.002 |
Kitty | -0.002 |
hy | -0.002 |
Kim | -0.002 |
Tim | -0.002 |
Token | a |
Token ID | 64 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ya | +0.089 |
utes | +0.082 |
mber | +0.081 |
dolphins | +0.079 |
submarine | +0.078 |
Neg logit contributions | |
Sue | -0.203 |
Kitty | -0.181 |
hy | -0.179 |
house | -0.174 |
Kim | -0.173 |
Token | was |
Token ID | 373 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
utes | +0.077 |
ya | +0.075 |
dolphins | +0.074 |
maid | +0.074 |
mber | +0.073 |
Neg logit contributions | |
Sue | -0.070 |
Kitty | -0.060 |
hy | -0.058 |
Kim | -0.058 |
Tim | -0.057 |
Token | more |
Token ID | 517 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
dolphins | +0.003 |
utes | +0.003 |
ya | +0.003 |
maid | +0.003 |
dolphin | +0.003 |
Neg logit contributions | |
Sue | -0.002 |
hy | -0.002 |
Kitty | -0.002 |
Kim | -0.002 |
hetically | -0.002 |
Token | important |
Token ID | 1593 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Sue | +0.017 |
Kitty | +0.015 |
hy | +0.014 |
Kim | +0.014 |
Tim | +0.014 |
Neg logit contributions | |
utes | -0.020 |
ya | -0.019 |
maid | -0.019 |
mber | -0.019 |
dolphins | -0.019 |
Token | than |
Token ID | 621 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
Sue | +0.007 |
Kitty | +0.006 |
Tim | +0.005 |
Kim | +0.005 |
hy | +0.005 |
Neg logit contributions | |
utes | -0.011 |
maid | -0.011 |
mber | -0.011 |
ya | -0.011 |
dolphins | -0.011 |
Token | Cr |
Token ID | 3864 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
utes | +0.013 |
ya | +0.013 |
maid | +0.013 |
dolphins | +0.013 |
mber | +0.013 |
Neg logit contributions | |
Sue | -0.003 |
Kitty | -0.002 |
hy | -0.002 |
Kim | -0.002 |
Tim | -0.002 |
Token | ust |
Token ID | 436 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
submarine | +0.067 |
dolphins | +0.066 |
pearl | +0.065 |
ya | +0.065 |
crew | +0.064 |
Neg logit contributions | |
Sue | -0.072 |
She | -0.062 |
house | -0.061 |
hy | -0.061 |
Tim | -0.058 |
Token | y |
Token ID | 88 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
utes | +0.149 |
mber | +0.149 |
isha | +0.147 |
ya | +0.142 |
Simon | +0.142 |
Neg logit contributions | |
Sue | -0.134 |
Tim | -0.107 |
hy | -0.105 |
house | -0.100 |
Kitty | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
utes | +0.084 |
mber | +0.084 |
asper | +0.084 |
ya | +0.081 |
targets | +0.080 |
Neg logit contributions | |
Sue | -0.016 |
Tim | -0.009 |
Kitty | -0.007 |
She | -0.007 |
hy | -0.007 |
Token | Cr |
Token ID | 3864 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Sue | +0.001 |
Kitty | +0.001 |
Kim | +0.001 |
hy | +0.001 |
Tim | +0.001 |
Neg logit contributions | |
utes | -0.001 |
ya | -0.001 |
maid | -0.001 |
ub | -0.001 |
dolphins | -0.001 |
Token | ust |
Token ID | 436 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
dolphins | +0.079 |
submarine | +0.076 |
dolphin | +0.075 |
ya | +0.075 |
pearl | +0.074 |
Neg logit contributions | |
Sue | -0.077 |
house | -0.067 |
She | -0.067 |
hy | -0.064 |
Tim | -0.063 |
Token | y |
Token ID | 88 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
utes | +0.150 |
isha | +0.147 |
mber | +0.146 |
dolphins | +0.143 |
ya | +0.141 |
Neg logit contributions | |
Sue | -0.142 |
Tim | -0.117 |
Kitty | -0.113 |
hy | -0.112 |
house | -0.111 |
Token | lived |
Token ID | 5615 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
utes | +0.080 |
dolphins | +0.076 |
maid | +0.076 |
ya | +0.076 |
mber | +0.075 |
Neg logit contributions | |
Sue | -0.044 |
Tim | -0.035 |
Kitty | -0.035 |
hy | -0.035 |
She | -0.034 |
Token | in |
Token ID | 287 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
ya | +0.047 |
utes | +0.047 |
mber | +0.046 |
asper | +0.045 |
maid | +0.045 |
Neg logit contributions | |
Sue | -0.019 |
Kitty | -0.013 |
Tim | -0.013 |
She | -0.012 |
hy | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
dolphins | +0.020 |
coral | +0.020 |
utes | +0.020 |
submarine | +0.020 |
dolphin | +0.020 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.008 |
hetically | -0.008 |
hy | -0.007 |
Kim | -0.007 |
Token | big |
Token ID | 1263 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
utes | +0.021 |
asper | +0.020 |
maid | +0.020 |
ya | +0.019 |
la | +0.019 |
Neg logit contributions | |
Sue | -0.005 |
She | -0.004 |
Tim | -0.003 |
Kitty | -0.003 |
warm | -0.003 |
Token | like |
Token ID | 588 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
utes | +0.049 |
ya | +0.048 |
dolphins | +0.047 |
maid | +0.047 |
mber | +0.047 |
Neg logit contributions | |
Sue | -0.034 |
Kitty | -0.029 |
hy | -0.028 |
Kim | -0.027 |
Tim | -0.026 |
Token | he |
Token ID | 339 |
Feature activation | -9.68e-03 |
Pos logit contributions | |
Sue | +0.021 |
Kitty | +0.017 |
hy | +0.017 |
Kim | +0.016 |
She | +0.016 |
Neg logit contributions | |
utes | -0.028 |
dolphins | -0.028 |
ya | -0.028 |
mber | -0.027 |
maid | -0.027 |
Token | wasn |
Token ID | 2492 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Sue | +0.000 |
Kitty | +0.000 |
hy | +0.000 |
Kim | +0.000 |
Tim | +0.000 |
Neg logit contributions | |
utes | -0.000 |
ya | -0.000 |
maid | -0.000 |
mber | -0.000 |
dolphins | -0.000 |
Token | â |
Token ID | 22940 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
Sue | +0.012 |
Kitty | +0.010 |
blond | +0.010 |
Kim | +0.010 |
hy | +0.010 |
Neg logit contributions | |
utes | -0.013 |
ub | -0.012 |
ya | -0.012 |
dolphins | -0.012 |
mber | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Sue | +0.027 |
Kitty | +0.025 |
Kim | +0.023 |
blond | +0.022 |
Tim | +0.022 |
Neg logit contributions | |
ya | -0.022 |
mber | -0.022 |
va | -0.021 |
ub | -0.020 |
asper | -0.020 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
utes | +0.012 |
mber | +0.011 |
ub | +0.011 |
ya | +0.011 |
asper | +0.011 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.010 |
hy | -0.010 |
Kim | -0.010 |
hetically | -0.010 |
Token | t |
Token ID | 83 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Sue | +0.201 |
Kitty | +0.180 |
blond | +0.171 |
Kim | +0.171 |
Tim | +0.167 |
Neg logit contributions | |
utes | -0.143 |
ub | -0.138 |
mber | -0.132 |
us | -0.132 |
va | -0.131 |
Token | successful |
Token ID | 4388 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Sue | +0.016 |
Kitty | +0.014 |
hy | +0.013 |
Kim | +0.013 |
Tim | +0.013 |
Neg logit contributions | |
utes | -0.020 |
ya | -0.019 |
maid | -0.019 |
mber | -0.019 |
dolphins | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Sue | +0.003 |
Kitty | +0.002 |
hy | +0.002 |
Kim | +0.002 |
Tim | +0.002 |
Neg logit contributions | |
utes | -0.005 |
ya | -0.005 |
maid | -0.005 |
dolphins | -0.005 |
mber | -0.005 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.003 |
hy | +0.003 |
Kim | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
utes | -0.007 |
ya | -0.007 |
mber | -0.007 |
maid | -0.007 |
dolphins | -0.007 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
utes | +0.061 |
dolphins | +0.058 |
mber | +0.058 |
ya | +0.057 |
maid | +0.055 |
Neg logit contributions | |
Sue | -0.080 |
Kitty | -0.071 |
hy | -0.071 |
Kim | -0.069 |
Tim | -0.066 |
Token | But |
Token ID | 887 |
Feature activation | -8.86e-03 |
Pos logit contributions | |
Sue | +0.010 |
Kitty | +0.008 |
hy | +0.008 |
Kim | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
utes | -0.025 |
ya | -0.025 |
mber | -0.024 |
maid | -0.024 |
dolphins | -0.024 |
Token | Emma |
Token ID | 18966 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Sue | +0.000 |
hy | +0.000 |
Kitty | +0.000 |
Kim | +0.000 |
hetically | +0.000 |
Neg logit contributions | |
ya | -0.000 |
utes | -0.000 |
mber | -0.000 |
va | -0.000 |
maid | -0.000 |
Token | wasn |
Token ID | 2492 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
ya | +0.042 |
utes | +0.041 |
mber | +0.041 |
maid | +0.040 |
dolphins | +0.039 |
Neg logit contributions | |
Sue | -0.038 |
Kitty | -0.032 |
hy | -0.031 |
Kim | -0.031 |
Tim | -0.030 |
Token | â |
Token ID | 22940 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Sue | +0.011 |
Kitty | +0.009 |
hy | +0.009 |
Kim | +0.009 |
Tim | +0.009 |
Neg logit contributions | |
utes | -0.014 |
ya | -0.014 |
mber | -0.014 |
dolphins | -0.013 |
ub | -0.013 |
Token | € |
Token ID | 26391 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
Sue | +0.018 |
Kitty | +0.017 |
Kim | +0.015 |
Tim | +0.015 |
blond | +0.015 |
Neg logit contributions | |
ya | -0.014 |
mber | -0.014 |
va | -0.013 |
utes | -0.013 |
asper | -0.013 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
utes | +0.021 |
mber | +0.019 |
ub | +0.019 |
isha | +0.019 |
ya | +0.019 |
Neg logit contributions | |
Sue | -0.022 |
Kitty | -0.019 |
lick | -0.018 |
Tim | -0.018 |
hy | -0.018 |
Token | t |
Token ID | 83 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
Sue | +0.191 |
Kitty | +0.171 |
blond | +0.164 |
Kim | +0.162 |
Tim | +0.160 |
Neg logit contributions | |
utes | -0.149 |
ub | -0.142 |
mber | -0.139 |
ya | -0.137 |
va | -0.137 |
Token | very |
Token ID | 845 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
Sue | +0.027 |
Kitty | +0.023 |
hy | +0.022 |
Kim | +0.022 |
Tim | +0.022 |
Neg logit contributions | |
utes | -0.027 |
ya | -0.026 |
maid | -0.025 |
dolphins | -0.025 |
mber | -0.025 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ya | +0.023 |
mber | +0.023 |
utes | +0.022 |
va | +0.022 |
dolphins | +0.022 |
Neg logit contributions | |
Sue | -0.021 |
Kitty | -0.019 |
hy | -0.018 |
Kim | -0.018 |
Tim | -0.018 |
Token | about |
Token ID | 546 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
Sue | +0.034 |
Kitty | +0.031 |
hy | +0.030 |
Kim | +0.028 |
Kim | +0.027 |
Neg logit contributions | |
ya | -0.051 |
mber | -0.049 |
utes | -0.049 |
dolphins | -0.048 |
maid | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ya | +0.019 |
dolphins | +0.018 |
utes | +0.018 |
mber | +0.018 |
maid | +0.018 |
Neg logit contributions | |
Sue | -0.014 |
hy | -0.013 |
Kitty | -0.012 |
Kim | -0.012 |
Kim | -0.011 |
Token | But |
Token ID | 1537 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
maid | +0.006 |
utes | +0.006 |
ya | +0.006 |
dolphins | +0.006 |
fish | +0.006 |
Neg logit contributions | |
Sue | -0.005 |
Kitty | -0.005 |
Tim | -0.004 |
She | -0.004 |
Kim | -0.004 |
Token | Peter |
Token ID | 5613 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
utes | +0.009 |
ya | +0.009 |
maid | +0.008 |
dolphins | +0.008 |
mber | +0.008 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.006 |
hy | -0.006 |
Kim | -0.005 |
Tim | -0.005 |
Token | wasn |
Token ID | 2492 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ya | +0.001 |
utes | +0.001 |
mber | +0.001 |
maid | +0.001 |
dolphins | +0.001 |
Neg logit contributions | |
Sue | -0.001 |
Kitty | -0.001 |
hy | -0.001 |
Kim | -0.001 |
Tim | -0.001 |
Token | â |
Token ID | 22940 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Sue | +0.011 |
Kitty | +0.009 |
hy | +0.009 |
Kim | +0.008 |
Tim | +0.008 |
Neg logit contributions | |
utes | -0.014 |
ya | -0.013 |
dolphins | -0.013 |
mber | -0.013 |
ub | -0.013 |
Token | € |
Token ID | 26391 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
Sue | +0.016 |
Kitty | +0.015 |
Kim | +0.013 |
blond | +0.013 |
Tim | +0.013 |
Neg logit contributions | |
ya | -0.013 |
mber | -0.013 |
utes | -0.012 |
va | -0.012 |
asper | -0.012 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
utes | +0.022 |
ub | +0.021 |
mber | +0.020 |
asper | +0.020 |
ya | +0.020 |
Neg logit contributions | |
Sue | -0.020 |
Kitty | -0.018 |
hetically | -0.017 |
hy | -0.016 |
lick | -0.016 |
Token | t |
Token ID | 83 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
Sue | +0.186 |
Kitty | +0.166 |
Kim | +0.157 |
blond | +0.157 |
hy | +0.155 |
Neg logit contributions | |
utes | -0.153 |
ub | -0.145 |
mber | -0.143 |
ya | -0.143 |
va | -0.140 |
Token | embarrassed |
Token ID | 21100 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Sue | +0.023 |
Kitty | +0.020 |
hy | +0.019 |
Kim | +0.019 |
Tim | +0.019 |
Neg logit contributions | |
utes | -0.024 |
ya | -0.023 |
maid | -0.023 |
dolphins | -0.022 |
mber | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
ya | +0.008 |
utes | +0.008 |
dolphins | +0.008 |
ub | +0.008 |
maid | +0.008 |
Neg logit contributions | |
Sue | -0.005 |
Kitty | -0.004 |
hy | -0.004 |
Kim | -0.004 |
house | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Sue | +0.008 |
Kitty | +0.006 |
hy | +0.006 |
Kim | +0.005 |
Tim | +0.004 |
Neg logit contributions | |
utes | -0.025 |
ya | -0.025 |
mber | -0.025 |
dolphins | -0.024 |
maid | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
Sue | +0.007 |
Kitty | +0.006 |
hy | +0.005 |
Kim | +0.005 |
Tim | +0.005 |
Neg logit contributions | |
utes | -0.009 |
ya | -0.008 |
maid | -0.008 |
mber | -0.008 |
dolphins | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
hetically | +0.007 |
bleed | +0.006 |
Kitty | +0.006 |
Sue | +0.005 |
bruises | +0.005 |
Neg logit contributions | |
coral | -0.010 |
submarine | -0.010 |
utes | -0.010 |
asper | -0.010 |
ya | -0.010 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Sue | +0.012 |
Kitty | +0.010 |
Kim | +0.010 |
hy | +0.010 |
Tim | +0.009 |
Neg logit contributions | |
utes | -0.014 |
ya | -0.014 |
dolphins | -0.014 |
mber | -0.014 |
maid | -0.013 |
Token | writing |
Token ID | 3597 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Sue | +0.011 |
hy | +0.009 |
Kitty | +0.009 |
Kim | +0.009 |
She | +0.008 |
Neg logit contributions | |
utes | -0.013 |
dolphins | -0.012 |
ya | -0.012 |
mber | -0.012 |
submarine | -0.012 |
Token | z |
Token ID | 1976 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.012 |
hy | +0.012 |
Tim | +0.012 |
Kim | +0.011 |
Neg logit contributions | |
utes | -0.025 |
ya | -0.024 |
maid | -0.024 |
mber | -0.024 |
dolphins | -0.024 |
Token | ig |
Token ID | 328 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Sue | +0.066 |
hy | +0.057 |
Kitty | +0.056 |
Kim | +0.055 |
Tim | +0.054 |
Neg logit contributions | |
utes | -0.072 |
ya | -0.071 |
mber | -0.071 |
maid | -0.070 |
dolphins | -0.069 |
Token | z |
Token ID | 89 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
Sue | +0.056 |
Kitty | +0.049 |
hy | +0.047 |
Kim | +0.047 |
Tim | +0.046 |
Neg logit contributions | |
utes | -0.049 |
ya | -0.046 |
maid | -0.044 |
dolphins | -0.044 |
mber | -0.044 |
Token | ags |
Token ID | 3775 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Sue | +0.168 |
Kitty | +0.146 |
hy | +0.140 |
Kim | +0.138 |
Tim | +0.137 |
Neg logit contributions | |
utes | -0.180 |
ya | -0.173 |
maid | -0.169 |
dolphins | -0.169 |
mber | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
Sue | +0.008 |
Kitty | +0.006 |
Tim | +0.006 |
Kim | +0.006 |
hy | +0.006 |
Neg logit contributions | |
utes | -0.018 |
maid | -0.018 |
mber | -0.018 |
ya | -0.018 |
dolphins | -0.017 |
Token | He |
Token ID | 679 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Sue | +0.009 |
hetically | +0.009 |
Kitty | +0.009 |
bleed | +0.008 |
hy | +0.007 |
Neg logit contributions | |
utes | -0.020 |
ya | -0.020 |
asper | -0.019 |
mber | -0.019 |
dolphins | -0.019 |
Token | wrote |
Token ID | 2630 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Sue | +0.007 |
hy | +0.006 |
Tim | +0.006 |
Kitty | +0.005 |
Kim | +0.005 |
Neg logit contributions | |
utes | -0.013 |
mber | -0.012 |
maid | -0.012 |
ya | -0.012 |
dolphins | -0.012 |
Token | z |
Token ID | 1976 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
utes | +0.018 |
maid | +0.017 |
ya | +0.017 |
ub | +0.017 |
mber | +0.017 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.007 |
Tim | -0.006 |
hy | -0.006 |
Kim | -0.006 |
Token | But |
Token ID | 887 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Sue | +0.006 |
Kitty | +0.005 |
Tim | +0.004 |
Kim | +0.004 |
She | +0.004 |
Neg logit contributions | |
utes | -0.013 |
ya | -0.013 |
maid | -0.013 |
dolphins | -0.012 |
mber | -0.012 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.005 |
dolphins | +0.005 |
mber | +0.005 |
maid | +0.005 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.003 |
hy | -0.003 |
Kim | -0.003 |
Tim | -0.003 |
Token | wasn |
Token ID | 2492 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
utes | +0.038 |
ya | +0.038 |
mber | +0.037 |
maid | +0.037 |
dolphins | +0.037 |
Neg logit contributions | |
Sue | -0.032 |
Kitty | -0.027 |
hy | -0.026 |
Kim | -0.026 |
Tim | -0.025 |
Token | â |
Token ID | 22940 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Sue | +0.012 |
Kitty | +0.010 |
hy | +0.009 |
Kim | +0.009 |
Tim | +0.009 |
Neg logit contributions | |
utes | -0.016 |
ya | -0.015 |
dolphins | -0.015 |
mber | -0.015 |
ub | -0.015 |
Token | € |
Token ID | 26391 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.004 |
Kim | +0.004 |
blond | +0.004 |
Tim | +0.003 |
Neg logit contributions | |
ya | -0.003 |
mber | -0.003 |
va | -0.003 |
asper | -0.003 |
utes | -0.003 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
utes | +0.023 |
ub | +0.022 |
mber | +0.022 |
asper | +0.021 |
ya | +0.021 |
Neg logit contributions | |
Sue | -0.023 |
Kitty | -0.020 |
hy | -0.018 |
Kim | -0.018 |
hetically | -0.018 |
Token | t |
Token ID | 83 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
Sue | +0.184 |
Kitty | +0.165 |
blond | +0.157 |
Kim | +0.156 |
hy | +0.154 |
Neg logit contributions | |
utes | -0.151 |
ub | -0.143 |
mber | -0.140 |
ya | -0.138 |
va | -0.136 |
Token | scared |
Token ID | 12008 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
Sue | +0.025 |
Kitty | +0.021 |
Kim | +0.020 |
hy | +0.020 |
Tim | +0.020 |
Neg logit contributions | |
utes | -0.030 |
maid | -0.028 |
ya | -0.028 |
mber | -0.027 |
dolphins | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Sue | +0.016 |
Kitty | +0.014 |
hy | +0.014 |
house | +0.013 |
Kim | +0.013 |
Neg logit contributions | |
ya | -0.027 |
dolphins | -0.027 |
utes | -0.026 |
ub | -0.026 |
maid | -0.026 |
Token | strangers |
Token ID | 18981 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Sue | +0.043 |
hy | +0.037 |
Kitty | +0.036 |
house | +0.036 |
She | +0.034 |
Neg logit contributions | |
dolphins | -0.065 |
ya | -0.064 |
utes | -0.062 |
dolphin | -0.061 |
mber | -0.060 |
Token | anymore |
Token ID | 7471 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ya | +0.015 |
utes | +0.015 |
dolphins | +0.015 |
maid | +0.015 |
mber | +0.015 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.007 |
Kim | -0.007 |
hy | -0.006 |
Tim | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
ya | +0.003 |
utes | +0.003 |
dolphins | +0.003 |
mber | +0.003 |
maid | +0.003 |
Neg logit contributions | |
Sue | -0.002 |
Kitty | -0.001 |
hy | -0.001 |
Kim | -0.001 |
Tim | -0.001 |
Token | still |
Token ID | 991 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
utes | +0.003 |
ya | +0.003 |
maid | +0.003 |
dolphins | +0.003 |
mber | +0.003 |
Neg logit contributions | |
Sue | -0.003 |
Kitty | -0.002 |
hy | -0.002 |
Tim | -0.002 |
Kim | -0.002 |
Token | hadn |
Token ID | 8020 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
utes | +0.052 |
ya | +0.050 |
maid | +0.049 |
dolphins | +0.049 |
mber | +0.049 |
Neg logit contributions | |
Sue | -0.048 |
Kitty | -0.042 |
hy | -0.040 |
Kim | -0.040 |
Tim | -0.040 |
Token | â |
Token ID | 22940 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
utes | +0.029 |
ya | +0.028 |
maid | +0.027 |
dolphins | +0.027 |
mber | +0.027 |
Neg logit contributions | |
Sue | -0.017 |
Kitty | -0.014 |
hy | -0.013 |
Kim | -0.013 |
Tim | -0.013 |
Token | € |
Token ID | 26391 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Sue | +0.014 |
Kitty | +0.013 |
Kim | +0.012 |
Tim | +0.012 |
hetically | +0.011 |
Neg logit contributions | |
ya | -0.013 |
mber | -0.012 |
utes | -0.012 |
va | -0.012 |
asper | -0.011 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
utes | +0.014 |
ub | +0.012 |
mber | +0.012 |
ya | +0.012 |
asper | +0.012 |
Neg logit contributions | |
Sue | -0.016 |
Kitty | -0.014 |
hetically | -0.014 |
shake | -0.014 |
Tim | -0.014 |
Token | t |
Token ID | 83 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Sue | +0.183 |
Kitty | +0.165 |
Kim | +0.157 |
blond | +0.157 |
shake | +0.156 |
Neg logit contributions | |
utes | -0.142 |
ub | -0.138 |
mber | -0.136 |
ya | -0.135 |
va | -0.134 |
Token | seen |
Token ID | 1775 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Sue | +0.008 |
Kitty | +0.007 |
hy | +0.007 |
Tim | +0.007 |
Kim | +0.007 |
Neg logit contributions | |
ya | -0.009 |
utes | -0.009 |
mber | -0.009 |
dolphins | -0.009 |
maid | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
Sue | +0.041 |
Kitty | +0.035 |
hy | +0.033 |
Kim | +0.033 |
Tim | +0.032 |
Neg logit contributions | |
utes | -0.052 |
ya | -0.052 |
dolphins | -0.051 |
maid | -0.050 |
mber | -0.049 |
Token | purple |
Token ID | 14032 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
utes | +0.037 |
ub | +0.033 |
ico | +0.032 |
asper | +0.032 |
us | +0.032 |
Neg logit contributions | |
Sue | -0.025 |
Kitty | -0.021 |
Tim | -0.020 |
hy | -0.020 |
shake | -0.019 |
Token | sunset |
Token ID | 26428 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
utes | +0.021 |
ya | +0.019 |
mber | +0.019 |
dolphins | +0.019 |
ub | +0.019 |
Neg logit contributions | |
Sue | -0.019 |
Kitty | -0.016 |
hy | -0.015 |
Tim | -0.015 |
She | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Sue | +0.024 |
Kitty | +0.019 |
Tim | +0.018 |
She | +0.017 |
hy | +0.017 |
Neg logit contributions | |
utes | -0.048 |
ya | -0.046 |
maid | -0.045 |
mber | -0.045 |
asper | -0.045 |
Token | She |
Token ID | 1375 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Sue | +0.011 |
Kitty | +0.006 |
hy | +0.005 |
Kim | +0.005 |
Tim | +0.004 |
Neg logit contributions | |
utes | -0.065 |
ya | -0.064 |
mber | -0.063 |
maid | -0.063 |
dolphins | -0.062 |
Token | wasn |
Token ID | 2492 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.004 |
She | +0.003 |
Tim | +0.003 |
shake | +0.003 |
Neg logit contributions | |
utes | -0.008 |
submarine | -0.008 |
asper | -0.007 |
us | -0.007 |
ub | -0.007 |
Token | â |
Token ID | 22940 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Sue | +0.008 |
Kitty | +0.007 |
Kim | +0.007 |
hy | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
utes | -0.010 |
ya | -0.010 |
dolphins | -0.010 |
mber | -0.010 |
ub | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.014 |
Kim | +0.013 |
Tim | +0.013 |
Spot | +0.012 |
Neg logit contributions | |
ya | -0.012 |
mber | -0.012 |
va | -0.011 |
utes | -0.011 |
ub | -0.011 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
utes | +0.026 |
mber | +0.024 |
ya | +0.024 |
ub | +0.024 |
maid | +0.023 |
Neg logit contributions | |
Sue | -0.026 |
Kitty | -0.022 |
Tim | -0.022 |
Kim | -0.022 |
hy | -0.021 |
Token | t |
Token ID | 83 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
Sue | +0.190 |
Kitty | +0.170 |
blond | +0.164 |
Kim | +0.162 |
Tim | +0.161 |
Neg logit contributions | |
utes | -0.139 |
ub | -0.133 |
mber | -0.130 |
ya | -0.128 |
va | -0.127 |
Token | ashamed |
Token ID | 22461 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Sue | +0.016 |
Kitty | +0.012 |
Kim | +0.012 |
Tim | +0.012 |
hy | +0.012 |
Neg logit contributions | |
utes | -0.025 |
maid | -0.023 |
submarine | -0.023 |
ya | -0.023 |
dolphins | -0.022 |
Token | anymore |
Token ID | 7471 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ya | +0.011 |
utes | +0.011 |
dolphins | +0.011 |
mber | +0.011 |
maid | +0.011 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.006 |
hy | -0.006 |
Kim | -0.006 |
Kim | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
Sue | +0.019 |
Kitty | +0.014 |
Tim | +0.013 |
She | +0.013 |
Kim | +0.012 |
Neg logit contributions | |
utes | -0.054 |
maid | -0.050 |
mber | -0.050 |
ya | -0.050 |
asper | -0.050 |
Token | everyone |
Token ID | 2506 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Sue | +0.019 |
Kitty | +0.016 |
hy | +0.016 |
Kim | +0.016 |
Tim | +0.015 |
Neg logit contributions | |
ya | -0.027 |
utes | -0.027 |
dolphins | -0.026 |
mber | -0.026 |
maid | -0.026 |
Token | € |
Token ID | 26391 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ya | +0.034 |
mber | +0.033 |
utes | +0.033 |
va | +0.031 |
ub | +0.031 |
Neg logit contributions | |
Sue | -0.035 |
Kitty | -0.031 |
Kim | -0.029 |
Tim | -0.029 |
blond | -0.027 |
Token | Luigi |
Token ID | 39139 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
utes | +0.062 |
ya | +0.059 |
mber | +0.058 |
dolphins | +0.057 |
maid | +0.057 |
Neg logit contributions | |
Sue | -0.059 |
Kitty | -0.051 |
hy | -0.050 |
Kim | -0.049 |
Tim | -0.048 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
utes | +0.073 |
dolphins | +0.069 |
targets | +0.068 |
ya | +0.068 |
mber | +0.068 |
Neg logit contributions | |
Sue | -0.047 |
Kitty | -0.040 |
Tim | -0.038 |
hy | -0.038 |
She | -0.038 |
Token | â |
Token ID | 22940 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
Sue | +0.005 |
Kitty | +0.004 |
hy | +0.004 |
Kim | +0.004 |
Tim | +0.004 |
Neg logit contributions | |
utes | -0.007 |
ya | -0.007 |
mber | -0.007 |
dolphins | -0.007 |
maid | -0.007 |
Token | € |
Token ID | 26391 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
Sue | +0.019 |
Kitty | +0.017 |
Kim | +0.016 |
Tim | +0.016 |
blond | +0.015 |
Neg logit contributions | |
ya | -0.017 |
mber | -0.017 |
utes | -0.016 |
va | -0.016 |
asper | -0.016 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
utes | +0.027 |
ya | +0.025 |
mber | +0.025 |
maid | +0.025 |
dolphins | +0.024 |
Neg logit contributions | |
Sue | -0.031 |
Kitty | -0.027 |
hy | -0.026 |
Kim | -0.026 |
Tim | -0.025 |
Token | t |
Token ID | 83 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Sue | +0.185 |
Kitty | +0.164 |
Kim | +0.156 |
blond | +0.153 |
Tim | +0.153 |
Neg logit contributions | |
utes | -0.149 |
ub | -0.141 |
mber | -0.139 |
ya | -0.139 |
va | -0.136 |
Token | so |
Token ID | 523 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.010 |
Kim | +0.010 |
hy | +0.010 |
Tim | +0.010 |
Neg logit contributions | |
utes | -0.021 |
maid | -0.020 |
submarine | -0.020 |
ya | -0.019 |
coral | -0.019 |
Token | sure |
Token ID | 1654 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
utes | +0.010 |
ya | +0.010 |
dolphins | +0.010 |
mber | +0.010 |
maid | +0.010 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.006 |
hy | -0.006 |
Kim | -0.006 |
Tim | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
utes | +0.023 |
ya | +0.022 |
maid | +0.022 |
mber | +0.021 |
dolphins | +0.021 |
Neg logit contributions | |
Sue | -0.019 |
Kitty | -0.016 |
Kim | -0.015 |
Tim | -0.015 |
hy | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Sue | +0.007 |
Kitty | +0.006 |
hy | +0.005 |
Kim | +0.005 |
Tim | +0.005 |
Neg logit contributions | |
utes | -0.010 |
ya | -0.010 |
mber | -0.009 |
dolphins | -0.009 |
maid | -0.009 |
Token | but |
Token ID | 475 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ya | +0.022 |
utes | +0.022 |
dolphins | +0.022 |
mber | +0.021 |
dolphin | +0.021 |
Neg logit contributions | |
Sue | -0.014 |
hy | -0.013 |
Kitty | -0.012 |
hetically | -0.012 |
Kim | -0.011 |
Token | Emma |
Token ID | 18966 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.005 |
mber | +0.005 |
maid | +0.005 |
dolphins | +0.005 |
Neg logit contributions | |
Sue | -0.003 |
Kitty | -0.003 |
hy | -0.003 |
Kim | -0.002 |
Tim | -0.002 |
Token | wasn |
Token ID | 2492 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
utes | +0.046 |
ya | +0.046 |
mber | +0.045 |
maid | +0.044 |
dolphins | +0.044 |
Neg logit contributions | |
Sue | -0.040 |
Kitty | -0.034 |
hy | -0.033 |
Kim | -0.032 |
Tim | -0.031 |
Token | â |
Token ID | 22940 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Sue | +0.008 |
Kitty | +0.007 |
hy | +0.007 |
Kim | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
utes | -0.011 |
ya | -0.010 |
mber | -0.010 |
dolphins | -0.010 |
ub | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Sue | +0.010 |
Kitty | +0.009 |
Kim | +0.008 |
Tim | +0.008 |
blond | +0.008 |
Neg logit contributions | |
ya | -0.008 |
mber | -0.008 |
va | -0.008 |
utes | -0.008 |
asper | -0.008 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
utes | +0.019 |
mber | +0.018 |
ya | +0.017 |
ub | +0.017 |
asper | +0.017 |
Neg logit contributions | |
Sue | -0.018 |
Kitty | -0.016 |
hy | -0.015 |
Kim | -0.015 |
Tim | -0.015 |
Token | t |
Token ID | 83 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
Sue | +0.183 |
Kitty | +0.163 |
blond | +0.156 |
Kim | +0.154 |
Tim | +0.152 |
Neg logit contributions | |
utes | -0.149 |
ub | -0.137 |
mber | -0.135 |
ya | -0.135 |
va | -0.133 |
Token | sure |
Token ID | 1654 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
Sue | +0.024 |
Kitty | +0.021 |
hy | +0.020 |
Kim | +0.020 |
Tim | +0.020 |
Neg logit contributions | |
utes | -0.027 |
ya | -0.026 |
maid | -0.026 |
mber | -0.026 |
dolphins | -0.026 |
Token | what |
Token ID | 644 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
Sue | +0.012 |
Kitty | +0.010 |
hy | +0.010 |
Kim | +0.010 |
Tim | +0.010 |
Neg logit contributions | |
utes | -0.017 |
ya | -0.016 |
mber | -0.016 |
dolphins | -0.016 |
maid | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Sue | +0.021 |
Kitty | +0.018 |
hy | +0.017 |
Kim | +0.017 |
Tim | +0.017 |
Neg logit contributions | |
utes | -0.029 |
ya | -0.028 |
mber | -0.027 |
dolphins | -0.027 |
maid | -0.027 |
Token | meant |
Token ID | 4001 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
Sue | +0.010 |
hy | +0.009 |
Kitty | +0.009 |
Kim | +0.009 |
hetically | +0.009 |
Neg logit contributions | |
mber | -0.012 |
ya | -0.011 |
utes | -0.011 |
dolphins | -0.011 |
va | -0.011 |
Token | while |
Token ID | 981 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
utes | +0.029 |
ya | +0.028 |
dolphins | +0.028 |
maid | +0.027 |
mber | +0.027 |
Neg logit contributions | |
Sue | -0.015 |
Kitty | -0.013 |
hy | -0.012 |
Kim | -0.012 |
Tim | -0.011 |
Token | Molly |
Token ID | 30236 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
utes | +0.024 |
ya | +0.023 |
dolphins | +0.023 |
maid | +0.023 |
mber | +0.022 |
Neg logit contributions | |
Sue | -0.017 |
Kitty | -0.015 |
hy | -0.014 |
Kim | -0.014 |
Tim | -0.013 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
utes | +0.071 |
ya | +0.068 |
maid | +0.067 |
mber | +0.067 |
dolphins | +0.066 |
Neg logit contributions | |
Sue | -0.047 |
Kitty | -0.039 |
hy | -0.038 |
Tim | -0.037 |
Kim | -0.037 |
Token | â |
Token ID | 22940 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
Sue | +0.006 |
Kitty | +0.005 |
Kim | +0.005 |
hy | +0.005 |
Tim | +0.004 |
Neg logit contributions | |
utes | -0.007 |
ya | -0.007 |
dolphins | -0.007 |
mber | -0.007 |
ub | -0.007 |
Token | € |
Token ID | 26391 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
Sue | +0.018 |
Kitty | +0.016 |
Kim | +0.015 |
Tim | +0.015 |
blond | +0.014 |
Neg logit contributions | |
ya | -0.015 |
mber | -0.015 |
va | -0.014 |
utes | -0.014 |
ub | -0.014 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
utes | +0.021 |
ya | +0.020 |
mber | +0.019 |
maid | +0.019 |
dolphins | +0.019 |
Neg logit contributions | |
Sue | -0.021 |
Kitty | -0.018 |
hy | -0.017 |
Kim | -0.017 |
Tim | -0.017 |
Token | t |
Token ID | 83 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Sue | +0.183 |
Kitty | +0.164 |
Kim | +0.156 |
blond | +0.154 |
Tim | +0.153 |
Neg logit contributions | |
utes | -0.147 |
ub | -0.139 |
ya | -0.137 |
mber | -0.136 |
va | -0.133 |
Token | looking |
Token ID | 2045 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
Sue | +0.010 |
Kitty | +0.008 |
Tim | +0.008 |
Kim | +0.008 |
hy | +0.008 |
Neg logit contributions | |
utes | -0.014 |
ya | -0.012 |
mber | -0.012 |
maid | -0.012 |
submarine | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
Sue | +0.001 |
Kitty | +0.001 |
Tim | +0.001 |
hy | +0.001 |
She | +0.001 |
Neg logit contributions | |
utes | -0.003 |
mber | -0.003 |
ya | -0.003 |
maid | -0.003 |
dolphins | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
hy | +0.002 |
Kim | +0.001 |
Tim | +0.001 |
Neg logit contributions | |
utes | -0.004 |
ya | -0.004 |
mber | -0.003 |
dolphins | -0.003 |
maid | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
maid | +0.003 |
utes | +0.003 |
ya | +0.003 |
dolphins | +0.002 |
submarine | +0.002 |
Neg logit contributions | |
Sue | -0.001 |
Kitty | -0.001 |
Tim | -0.001 |
She | -0.001 |
Kim | -0.001 |
Token | ig |
Token ID | 328 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
utes | +0.017 |
ya | +0.016 |
maid | +0.016 |
mber | +0.015 |
ub | +0.015 |
Neg logit contributions | |
Sue | -0.034 |
Kitty | -0.031 |
hy | -0.030 |
Tim | -0.029 |
Kim | -0.029 |
Token | ail |
Token ID | 603 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
Sue | +0.023 |
Kitty | +0.021 |
hy | +0.020 |
Kim | +0.020 |
Tim | +0.020 |
Neg logit contributions | |
utes | -0.016 |
ya | -0.015 |
maid | -0.015 |
mber | -0.015 |
dolphins | -0.015 |
Token | wasn |
Token ID | 2492 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.001 |
Tim | +0.001 |
hy | +0.001 |
Kim | +0.001 |
Neg logit contributions | |
utes | -0.003 |
ya | -0.003 |
maid | -0.003 |
dolphins | -0.003 |
mber | -0.003 |
Token | â |
Token ID | 22940 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
Kim | +0.010 |
hy | +0.010 |
Tim | +0.010 |
Neg logit contributions | |
utes | -0.016 |
ya | -0.015 |
dolphins | -0.015 |
mber | -0.015 |
ub | -0.015 |
Token | € |
Token ID | 26391 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Sue | +0.021 |
Kitty | +0.020 |
Kim | +0.018 |
Tim | +0.018 |
blond | +0.018 |
Neg logit contributions | |
ya | -0.018 |
mber | -0.017 |
va | -0.017 |
utes | -0.016 |
ub | -0.016 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
utes | +0.024 |
ub | +0.022 |
mber | +0.022 |
ya | +0.022 |
maid | +0.021 |
Neg logit contributions | |
Sue | -0.023 |
Kitty | -0.020 |
hy | -0.019 |
hetically | -0.019 |
Tim | -0.019 |
Token | t |
Token ID | 83 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
Sue | +0.185 |
Kitty | +0.168 |
Kim | +0.159 |
blond | +0.159 |
Tim | +0.156 |
Neg logit contributions | |
utes | -0.140 |
ub | -0.137 |
mber | -0.133 |
va | -0.131 |
ya | -0.131 |
Token | sure |
Token ID | 1654 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Sue | +0.017 |
Kitty | +0.014 |
Kim | +0.013 |
Tim | +0.013 |
hy | +0.013 |
Neg logit contributions | |
utes | -0.024 |
ya | -0.022 |
maid | -0.022 |
mber | -0.022 |
dolphins | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Sue | +0.010 |
hy | +0.009 |
Kitty | +0.009 |
Kim | +0.008 |
hetically | +0.008 |
Neg logit contributions | |
utes | -0.016 |
ya | -0.016 |
dolphins | -0.016 |
mber | -0.016 |
maid | -0.015 |
Token | but |
Token ID | 475 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ya | +0.012 |
utes | +0.012 |
dolphins | +0.012 |
mber | +0.011 |
maid | +0.011 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.007 |
hy | -0.007 |
Kim | -0.006 |
hetically | -0.006 |
Token | Emily |
Token ID | 17608 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
ya | +0.006 |
utes | +0.006 |
mber | +0.006 |
dolphins | +0.006 |
maid | +0.006 |
Neg logit contributions | |
Sue | -0.004 |
hy | -0.003 |
Kitty | -0.003 |
Kim | -0.003 |
Kim | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
utes | +0.030 |
ya | +0.028 |
maid | +0.028 |
dolphins | +0.028 |
mber | +0.028 |
Neg logit contributions | |
Sue | -0.022 |
Kitty | -0.019 |
Tim | -0.018 |
hy | -0.018 |
Kim | -0.018 |
Token | Please |
Token ID | 5492 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
utes | +0.010 |
ya | +0.010 |
mber | +0.010 |
dolphins | +0.010 |
maid | +0.010 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.007 |
hy | -0.006 |
Kim | -0.006 |
Tim | -0.006 |
Token | keep |
Token ID | 1394 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
Sue | +0.001 |
Kitty | +0.001 |
hy | +0.001 |
Kim | +0.001 |
hetically | +0.001 |
Neg logit contributions | |
maid | -0.001 |
utes | -0.001 |
ub | -0.001 |
ya | -0.001 |
dolphins | -0.001 |
Token | your |
Token ID | 534 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Sue | +0.014 |
Kitty | +0.012 |
Tim | +0.012 |
Kim | +0.012 |
hy | +0.011 |
Neg logit contributions | |
utes | -0.020 |
mber | -0.019 |
maid | -0.019 |
ya | -0.019 |
asper | -0.019 |
Token | seat |
Token ID | 5852 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Sue | +0.040 |
Kitty | +0.035 |
hy | +0.034 |
Kim | +0.034 |
Tim | +0.033 |
Neg logit contributions | |
utes | -0.039 |
mber | -0.038 |
ya | -0.038 |
maid | -0.037 |
va | -0.037 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
Sue | +0.059 |
Kitty | +0.051 |
Tim | +0.048 |
Kim | +0.046 |
She | +0.046 |
Neg logit contributions | |
utes | -0.062 |
maid | -0.058 |
ya | -0.058 |
fish | -0.057 |
ub | -0.057 |
Token | ts |
Token ID | 912 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Sue | +0.204 |
Kitty | +0.181 |
Kim | +0.173 |
Tim | +0.172 |
hy | +0.172 |
Neg logit contributions | |
utes | -0.138 |
ya | -0.129 |
dolphins | -0.124 |
mber | -0.124 |
maid | -0.123 |
Token | on |
Token ID | 319 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
Sue | +0.033 |
Kitty | +0.028 |
hy | +0.027 |
Tim | +0.026 |
Kim | +0.026 |
Neg logit contributions | |
utes | -0.046 |
ya | -0.044 |
mber | -0.043 |
maid | -0.043 |
dolphins | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
utes | +0.002 |
mber | +0.002 |
maid | +0.002 |
ya | +0.002 |
va | +0.002 |
Neg logit contributions | |
Sue | -0.001 |
Kitty | -0.001 |
Tim | -0.001 |
Kim | -0.001 |
hy | -0.001 |
Token | We |
Token ID | 775 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
utes | +0.023 |
ya | +0.021 |
dolphins | +0.021 |
mber | +0.021 |
maid | +0.021 |
Neg logit contributions | |
Sue | -0.021 |
Kitty | -0.018 |
hy | -0.017 |
Kim | -0.017 |
Tim | -0.017 |
Token | will |
Token ID | 481 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Sue | +0.017 |
Kitty | +0.015 |
hy | +0.014 |
Tim | +0.014 |
Kim | +0.014 |
Neg logit contributions | |
utes | -0.024 |
ya | -0.023 |
mber | -0.023 |
maid | -0.022 |
dolphins | -0.022 |
Token | But |
Token ID | 887 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
Sue | +0.008 |
Kitty | +0.006 |
Tim | +0.006 |
Kim | +0.005 |
She | +0.005 |
Neg logit contributions | |
utes | -0.017 |
ya | -0.017 |
maid | -0.017 |
dolphins | -0.017 |
mber | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
utes | +0.000 |
ya | +0.000 |
maid | +0.000 |
dolphins | +0.000 |
mber | +0.000 |
Neg logit contributions | |
Sue | -0.000 |
Kitty | -0.000 |
hy | -0.000 |
Kim | -0.000 |
Tim | -0.000 |
Token | weren |
Token ID | 6304 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Sue | +0.006 |
Tim | +0.005 |
Kitty | +0.005 |
shake | +0.004 |
Tom | +0.004 |
Neg logit contributions | |
utes | -0.013 |
ya | -0.012 |
mber | -0.012 |
maid | -0.012 |
asper | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Sue | +0.012 |
Kitty | +0.010 |
hy | +0.009 |
Kim | +0.009 |
Tim | +0.009 |
Neg logit contributions | |
utes | -0.017 |
ya | -0.016 |
dolphins | -0.016 |
mber | -0.016 |
maid | -0.016 |
Token | € |
Token ID | 26391 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Sue | +0.014 |
Kitty | +0.013 |
Kim | +0.012 |
Tim | +0.012 |
blond | +0.011 |
Neg logit contributions | |
utes | -0.013 |
ya | -0.013 |
mber | -0.013 |
ub | -0.012 |
asper | -0.012 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
utes | +0.026 |
ya | +0.024 |
maid | +0.024 |
dolphins | +0.024 |
mber | +0.024 |
Neg logit contributions | |
Sue | -0.023 |
Kitty | -0.019 |
hy | -0.019 |
Kim | -0.018 |
Tim | -0.018 |
Token | t |
Token ID | 83 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
Sue | +0.178 |
Kitty | +0.157 |
Kim | +0.150 |
blond | +0.148 |
hy | +0.148 |
Neg logit contributions | |
utes | -0.152 |
ub | -0.141 |
ya | -0.138 |
mber | -0.138 |
maid | -0.135 |
Token | careful |
Token ID | 8161 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.013 |
Kim | +0.012 |
Tim | +0.012 |
She | +0.011 |
Neg logit contributions | |
utes | -0.025 |
maid | -0.024 |
submarine | -0.023 |
asper | -0.023 |
ya | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.004 |
maid | +0.004 |
dolphins | +0.004 |
mber | +0.004 |
Neg logit contributions | |
Sue | -0.002 |
Kitty | -0.002 |
hy | -0.002 |
Kim | -0.002 |
Tim | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
Sue | +0.019 |
Kitty | +0.016 |
hy | +0.015 |
Tim | +0.015 |
Kim | +0.015 |
Neg logit contributions | |
utes | -0.026 |
ya | -0.024 |
maid | -0.024 |
mber | -0.024 |
dolphins | -0.024 |
Token | wind |
Token ID | 2344 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Sue | +0.002 |
shake | +0.001 |
Tim | +0.001 |
hy | +0.001 |
Kitty | +0.001 |
Neg logit contributions | |
utes | -0.002 |
ub | -0.002 |
mber | -0.002 |
va | -0.002 |
asper | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
utes | +0.043 |
ya | +0.042 |
maid | +0.041 |
mber | +0.041 |
dolphins | +0.041 |
Neg logit contributions | |
Sue | -0.020 |
Kitty | -0.016 |
hy | -0.015 |
Kim | -0.014 |
Tim | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
Sue | +0.006 |
Kitty | +0.004 |
hy | +0.003 |
Kim | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
utes | -0.032 |
ya | -0.031 |
mber | -0.031 |
maid | -0.030 |
dolphins | -0.030 |
Token | wasn |
Token ID | 2492 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Sue | +0.003 |
Kitty | +0.002 |
hy | +0.002 |
Tim | +0.002 |
Kim | +0.002 |
Neg logit contributions | |
utes | -0.004 |
ya | -0.004 |
maid | -0.004 |
dolphins | -0.003 |
mber | -0.003 |
Token | â |
Token ID | 22940 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Sue | +0.007 |
Kitty | +0.006 |
Kim | +0.006 |
hy | +0.006 |
blond | +0.006 |
Neg logit contributions | |
utes | -0.009 |
ya | -0.009 |
dolphins | -0.008 |
mber | -0.008 |
ub | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Sue | +0.006 |
Kitty | +0.005 |
Kim | +0.005 |
Tim | +0.005 |
blond | +0.005 |
Neg logit contributions | |
ya | -0.005 |
mber | -0.004 |
va | -0.004 |
asper | -0.004 |
ub | -0.004 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
utes | +0.036 |
ub | +0.034 |
mber | +0.033 |
ya | +0.033 |
maid | +0.032 |
Neg logit contributions | |
Sue | -0.036 |
Kitty | -0.031 |
hetically | -0.029 |
hy | -0.029 |
Tim | -0.029 |
Token | t |
Token ID | 83 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Sue | +0.187 |
Kitty | +0.168 |
blond | +0.162 |
Kim | +0.159 |
Tim | +0.157 |
Neg logit contributions | |
utes | -0.135 |
ub | -0.132 |
mber | -0.126 |
va | -0.125 |
us | -0.125 |
Token | so |
Token ID | 523 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
hy | +0.010 |
Kim | +0.010 |
Tim | +0.010 |
Neg logit contributions | |
utes | -0.018 |
ya | -0.017 |
maid | -0.017 |
mber | -0.017 |
dolphins | -0.017 |
Token | scared |
Token ID | 12008 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
ya | +0.008 |
mber | +0.008 |
dolphins | +0.008 |
va | +0.008 |
utes | +0.008 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.007 |
hy | -0.006 |
house | -0.006 |
Kim | -0.006 |
Token | anymore |
Token ID | 7471 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
Sue | +0.009 |
hy | +0.008 |
Kitty | +0.008 |
Kim | +0.007 |
house | +0.007 |
Neg logit contributions | |
ya | -0.015 |
dolphins | -0.015 |
ub | -0.015 |
utes | -0.014 |
mber | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
utes | +0.003 |
ya | +0.003 |
maid | +0.003 |
mber | +0.003 |
dolphins | +0.003 |
Neg logit contributions | |
Sue | -0.001 |
Kitty | -0.001 |
Tim | -0.001 |
hy | -0.001 |
Kim | -0.001 |
Token | but |
Token ID | 475 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
Sue | +0.009 |
Kitty | +0.007 |
hy | +0.007 |
Kim | +0.007 |
Tim | +0.006 |
Neg logit contributions | |
utes | -0.017 |
ya | -0.016 |
dolphins | -0.016 |
maid | -0.016 |
mber | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
Sue | +0.001 |
Kitty | +0.001 |
hy | +0.001 |
Kim | +0.001 |
Tim | +0.001 |
Neg logit contributions | |
utes | -0.002 |
ya | -0.002 |
mber | -0.002 |
dolphins | -0.002 |
maid | -0.002 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
utes | +0.018 |
ya | +0.017 |
maid | +0.016 |
dolphins | +0.016 |
mber | +0.016 |
Neg logit contributions | |
Sue | -0.013 |
Kitty | -0.011 |
Tim | -0.011 |
hy | -0.011 |
Kim | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Sue | +0.000 |
Kitty | +0.000 |
hy | +0.000 |
Kim | +0.000 |
Tim | +0.000 |
Neg logit contributions | |
utes | -0.001 |
ya | -0.001 |
dolphins | -0.001 |
mber | -0.001 |
maid | -0.001 |
Token | € |
Token ID | 26391 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.014 |
Kim | +0.012 |
Tim | +0.012 |
blond | +0.012 |
Neg logit contributions | |
ya | -0.014 |
mber | -0.013 |
utes | -0.013 |
asper | -0.013 |
ub | -0.013 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
utes | +0.020 |
ub | +0.019 |
mber | +0.018 |
asper | +0.018 |
maid | +0.018 |
Neg logit contributions | |
Sue | -0.024 |
Kitty | -0.021 |
hy | -0.020 |
Kim | -0.019 |
lick | -0.019 |
Token | t |
Token ID | 83 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Sue | +0.186 |
Kitty | +0.167 |
Kim | +0.158 |
blond | +0.157 |
Tim | +0.155 |
Neg logit contributions | |
utes | -0.141 |
ub | -0.134 |
us | -0.129 |
mber | -0.129 |
ya | -0.128 |
Token | sure |
Token ID | 1654 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Sue | +0.014 |
Kitty | +0.012 |
Kim | +0.012 |
Tim | +0.012 |
She | +0.011 |
Neg logit contributions | |
utes | -0.015 |
maid | -0.015 |
ya | -0.014 |
submarine | -0.014 |
mber | -0.014 |
Token | what |
Token ID | 644 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.004 |
hy | +0.003 |
Tim | +0.003 |
Kim | +0.003 |
Neg logit contributions | |
utes | -0.005 |
ya | -0.005 |
dolphins | -0.004 |
mber | -0.004 |
ub | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.012 |
hy | +0.011 |
Kim | +0.011 |
Tim | +0.011 |
Neg logit contributions | |
utes | -0.022 |
ya | -0.022 |
maid | -0.021 |
mber | -0.021 |
dolphins | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Sue | +0.010 |
Kitty | +0.008 |
hy | +0.008 |
hetically | +0.007 |
Kim | +0.006 |
Neg logit contributions | |
utes | -0.023 |
ub | -0.022 |
ya | -0.022 |
mber | -0.022 |
asper | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
utes | +0.048 |
mber | +0.044 |
ub | +0.044 |
maid | +0.043 |
ya | +0.043 |
Neg logit contributions | |
Sue | -0.052 |
hy | -0.045 |
Kitty | -0.043 |
blond | -0.042 |
Tim | -0.042 |
Token | it |
Token ID | 340 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
Sue | +0.007 |
hy | +0.006 |
Kitty | +0.005 |
blond | +0.005 |
� | +0.005 |
Neg logit contributions | |
ya | -0.010 |
mber | -0.010 |
utes | -0.010 |
maid | -0.009 |
dolphins | -0.009 |
Token | wasn |
Token ID | 2492 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
mber | +0.001 |
ya | +0.001 |
maid | +0.001 |
fish | +0.001 |
dolphins | +0.001 |
Neg logit contributions | |
Sue | -0.001 |
hy | -0.001 |
Kitty | -0.001 |
Kim | -0.001 |
blond | -0.001 |
Token | â |
Token ID | 22940 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Sue | +0.009 |
blond | +0.009 |
hy | +0.008 |
hetically | +0.008 |
house | +0.008 |
Neg logit contributions | |
utes | -0.008 |
ub | -0.007 |
dolphins | -0.007 |
va | -0.007 |
chen | -0.007 |
Token | € |
Token ID | 26391 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Sue | +0.035 |
Kitty | +0.032 |
blond | +0.030 |
Tim | +0.030 |
Kim | +0.029 |
Neg logit contributions | |
mber | -0.028 |
va | -0.027 |
ya | -0.026 |
utes | -0.025 |
ub | -0.025 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
utes | +0.013 |
ub | +0.012 |
mber | +0.012 |
va | +0.011 |
maid | +0.011 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.010 |
hetically | -0.010 |
hy | -0.010 |
Tim | -0.010 |
Token | t |
Token ID | 83 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
Sue | +0.190 |
Kitty | +0.170 |
blond | +0.165 |
Kim | +0.162 |
Tim | +0.159 |
Neg logit contributions | |
utes | -0.132 |
ub | -0.128 |
mber | -0.122 |
va | -0.122 |
us | -0.121 |
Token | long |
Token ID | 890 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Sue | +0.020 |
hy | +0.017 |
Kitty | +0.017 |
Kim | +0.016 |
hetically | +0.016 |
Neg logit contributions | |
ya | -0.025 |
utes | -0.025 |
mber | -0.025 |
maid | -0.025 |
dolphins | -0.025 |
Token | until |
Token ID | 1566 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
Sue | +0.062 |
Kitty | +0.054 |
Kim | +0.050 |
Kim | +0.048 |
hy | +0.048 |
Neg logit contributions | |
ya | -0.082 |
utes | -0.081 |
dolphins | -0.081 |
maid | -0.080 |
ub | -0.080 |
Token | Chloe |
Token ID | 29476 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
Sue | +0.022 |
hy | +0.021 |
Kitty | +0.019 |
hetically | +0.019 |
blond | +0.018 |
Neg logit contributions | |
ya | -0.028 |
dolphins | -0.028 |
utes | -0.027 |
mber | -0.027 |
maid | -0.027 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
Kim | +0.002 |
hy | +0.002 |
Tim | +0.002 |
Neg logit contributions | |
utes | -0.003 |
ya | -0.003 |
mber | -0.003 |
maid | -0.003 |
dolphins | -0.003 |
Token | but |
Token ID | 475 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
Sue | +0.011 |
Kitty | +0.009 |
hy | +0.009 |
Kim | +0.008 |
Tim | +0.008 |
Neg logit contributions | |
utes | -0.016 |
ya | -0.016 |
maid | -0.015 |
mber | -0.015 |
dolphins | -0.015 |
Token | she |
Token ID | 673 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Sue | +0.002 |
hy | +0.002 |
Kitty | +0.001 |
blond | +0.001 |
Kim | +0.001 |
Neg logit contributions | |
ya | -0.004 |
mber | -0.004 |
utes | -0.004 |
dolphins | -0.004 |
maid | -0.004 |
Token | hadn |
Token ID | 8020 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
utes | +0.018 |
ya | +0.017 |
maid | +0.017 |
mber | +0.017 |
dolphins | +0.017 |
Neg logit contributions | |
Sue | -0.015 |
Kitty | -0.012 |
hy | -0.012 |
Kim | -0.012 |
Tim | -0.012 |
Token | â |
Token ID | 22940 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
utes | +0.049 |
ya | +0.047 |
maid | +0.046 |
dolphins | +0.046 |
mber | +0.046 |
Neg logit contributions | |
Sue | -0.030 |
Kitty | -0.025 |
hy | -0.023 |
Kim | -0.023 |
Tim | -0.023 |
Token | € |
Token ID | 26391 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.013 |
Tim | +0.013 |
Kim | +0.012 |
blond | +0.011 |
Neg logit contributions | |
ya | -0.012 |
mber | -0.012 |
va | -0.011 |
utes | -0.011 |
asper | -0.011 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
utes | +0.020 |
ub | +0.018 |
mber | +0.018 |
ya | +0.017 |
va | +0.017 |
Neg logit contributions | |
Sue | -0.022 |
lick | -0.019 |
Kitty | -0.019 |
shake | -0.019 |
hetically | -0.019 |
Token | t |
Token ID | 83 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Sue | +0.180 |
Kitty | +0.160 |
blond | +0.156 |
Kim | +0.154 |
shake | +0.153 |
Neg logit contributions | |
utes | -0.137 |
ub | -0.131 |
mber | -0.130 |
ya | -0.129 |
va | -0.127 |
Token | listened |
Token ID | 16399 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.004 |
hy | +0.003 |
Kim | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
utes | -0.005 |
ya | -0.005 |
maid | -0.005 |
mber | -0.005 |
dolphins | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
utes | +0.044 |
ya | +0.044 |
mber | +0.042 |
dolphins | +0.042 |
maid | +0.042 |
Neg logit contributions | |
Sue | -0.028 |
Kitty | -0.024 |
Kim | -0.022 |
hy | -0.022 |
Tim | -0.021 |
Token | Fortunately |
Token ID | 20525 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Sue | +0.006 |
hy | +0.004 |
Kitty | +0.004 |
Kim | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
utes | -0.024 |
ya | -0.023 |
mber | -0.023 |
ub | -0.023 |
maid | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
ya | +0.020 |
utes | +0.020 |
mber | +0.019 |
maid | +0.019 |
ub | +0.019 |
Neg logit contributions | |
Sue | -0.010 |
hy | -0.008 |
Kitty | -0.008 |
Kim | -0.007 |
blond | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
utes | +0.045 |
dolphins | +0.044 |
ya | +0.043 |
mber | +0.043 |
ub | +0.043 |
Neg logit contributions | |
Sue | -0.021 |
hy | -0.018 |
Kitty | -0.017 |
Kim | -0.016 |
hetically | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
utes | +0.018 |
ya | +0.017 |
maid | +0.017 |
mber | +0.017 |
dolphins | +0.017 |
Neg logit contributions | |
Sue | -0.015 |
Kitty | -0.012 |
hy | -0.012 |
Tim | -0.012 |
Kim | -0.012 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
utes | +0.046 |
ya | +0.043 |
maid | +0.042 |
mber | +0.042 |
dolphins | +0.041 |
Neg logit contributions | |
Sue | -0.028 |
Kitty | -0.023 |
Tim | -0.022 |
hy | -0.021 |
Kim | -0.021 |
Token | â |
Token ID | 22940 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Sue | +0.005 |
Kitty | +0.004 |
Kim | +0.004 |
hy | +0.004 |
Tim | +0.004 |
Neg logit contributions | |
utes | -0.006 |
ya | -0.006 |
dolphins | -0.006 |
mber | -0.006 |
ub | -0.006 |
Token | € |
Token ID | 26391 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
Sue | +0.005 |
Kitty | +0.005 |
Kim | +0.004 |
Tim | +0.004 |
blond | +0.004 |
Neg logit contributions | |
ya | -0.004 |
mber | -0.004 |
utes | -0.004 |
va | -0.004 |
ub | -0.004 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
utes | +0.020 |
ub | +0.018 |
mber | +0.018 |
ya | +0.018 |
asper | +0.018 |
Neg logit contributions | |
Sue | -0.029 |
Kitty | -0.025 |
Kim | -0.024 |
Tim | -0.024 |
hy | -0.024 |
Token | t |
Token ID | 83 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Sue | +0.178 |
Kitty | +0.158 |
Kim | +0.150 |
blond | +0.149 |
Tim | +0.149 |
Neg logit contributions | |
utes | -0.147 |
ub | -0.137 |
ya | -0.135 |
mber | -0.135 |
va | -0.131 |
Token | an |
Token ID | 281 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
Kim | +0.010 |
hy | +0.010 |
Tim | +0.010 |
Neg logit contributions | |
utes | -0.019 |
ya | -0.017 |
maid | -0.017 |
mber | -0.017 |
dolphins | -0.017 |
Token | ordinary |
Token ID | 8850 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Sue | +0.027 |
Kitty | +0.023 |
hy | +0.022 |
Kim | +0.022 |
Tim | +0.022 |
Neg logit contributions | |
utes | -0.030 |
ya | -0.030 |
dolphins | -0.029 |
maid | -0.029 |
mber | -0.029 |
Token | kid |
Token ID | 5141 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ya | +0.019 |
dolphins | +0.019 |
dolphin | +0.019 |
mber | +0.019 |
utes | +0.018 |
Neg logit contributions | |
Sue | -0.019 |
Kim | -0.017 |
Kitty | -0.017 |
hy | -0.017 |
Kim | -0.016 |
Token | anymore |
Token ID | 7471 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
ya | +0.006 |
utes | +0.006 |
dolphins | +0.006 |
maid | +0.006 |
mber | +0.006 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.003 |
Kim | -0.003 |
hy | -0.003 |
Tim | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Sue | +0.007 |
Kitty | +0.006 |
hy | +0.006 |
Kim | +0.005 |
Tim | +0.005 |
Neg logit contributions | |
ya | -0.009 |
utes | -0.009 |
mber | -0.009 |
dolphins | -0.008 |
maid | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.002 |
hy | +0.002 |
Kim | +0.002 |
Tim | +0.002 |
Neg logit contributions | |
utes | -0.027 |
ya | -0.026 |
mber | -0.026 |
maid | -0.026 |
dolphins | -0.026 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Sue | +0.003 |
Kitty | +0.002 |
Tim | +0.002 |
hy | +0.002 |
She | +0.002 |
Neg logit contributions | |
utes | -0.005 |
maid | -0.004 |
dolphins | -0.004 |
ya | -0.004 |
ub | -0.004 |
Token | â |
Token ID | 22940 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
Sue | +0.004 |
Kitty | +0.003 |
hy | +0.003 |
Kim | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
utes | -0.004 |
ya | -0.004 |
dolphins | -0.004 |
mber | -0.004 |
ub | -0.004 |
Token | € |
Token ID | 26391 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
Kim | +0.002 |
Tim | +0.002 |
blond | +0.002 |
Neg logit contributions | |
ya | -0.002 |
mber | -0.002 |
va | -0.002 |
utes | -0.002 |
asper | -0.002 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
utes | +0.039 |
ub | +0.037 |
mber | +0.036 |
ya | +0.036 |
maid | +0.035 |
Neg logit contributions | |
Sue | -0.039 |
Kitty | -0.033 |
hy | -0.032 |
Tim | -0.031 |
Kim | -0.031 |
Token | t |
Token ID | 83 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Sue | +0.180 |
Kitty | +0.160 |
blond | +0.154 |
Kim | +0.152 |
Tim | +0.150 |
Neg logit contributions | |
utes | -0.141 |
ub | -0.134 |
mber | -0.130 |
ya | -0.129 |
va | -0.128 |
Token | sure |
Token ID | 1654 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Sue | +0.012 |
Kitty | +0.010 |
Kim | +0.009 |
Tim | +0.009 |
hy | +0.009 |
Neg logit contributions | |
utes | -0.016 |
ya | -0.015 |
maid | -0.015 |
dolphins | -0.015 |
mber | -0.015 |
Token | what |
Token ID | 644 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
Sue | +0.010 |
hy | +0.009 |
Kitty | +0.009 |
Tim | +0.008 |
Kim | +0.008 |
Neg logit contributions | |
utes | -0.012 |
ya | -0.012 |
dolphins | -0.012 |
mber | -0.011 |
maid | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
Sue | +0.021 |
Kitty | +0.017 |
Tim | +0.016 |
Kim | +0.016 |
hy | +0.016 |
Neg logit contributions | |
utes | -0.029 |
maid | -0.028 |
ya | -0.028 |
mber | -0.027 |
dolphins | -0.027 |
Token | do |
Token ID | 466 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
hy | +0.011 |
Kim | +0.010 |
Tim | +0.009 |
Neg logit contributions | |
utes | -0.025 |
ya | -0.024 |
maid | -0.024 |
dolphins | -0.024 |
mber | -0.024 |
Token | But |
Token ID | 887 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Sue | +0.009 |
Kitty | +0.007 |
hy | +0.007 |
Kim | +0.006 |
Tim | +0.006 |
Neg logit contributions | |
utes | -0.018 |
ya | -0.018 |
mber | -0.017 |
dolphins | -0.017 |
maid | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.005 |
dolphins | +0.005 |
maid | +0.005 |
mber | +0.005 |
Neg logit contributions | |
Sue | -0.004 |
hy | -0.003 |
Kitty | -0.003 |
Kim | -0.003 |
She | -0.003 |
Token | weren |
Token ID | 6304 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Sue | +0.006 |
Kitty | +0.005 |
Tim | +0.005 |
Kim | +0.005 |
hy | +0.005 |
Neg logit contributions | |
utes | -0.010 |
ya | -0.009 |
mber | -0.009 |
maid | -0.009 |
dolphins | -0.009 |
Token | â |
Token ID | 22940 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Sue | +0.016 |
Kitty | +0.014 |
hy | +0.014 |
blond | +0.013 |
Kim | +0.013 |
Neg logit contributions | |
utes | -0.020 |
ya | -0.018 |
dolphins | -0.018 |
mber | -0.018 |
ub | -0.018 |
Token | € |
Token ID | 26391 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
Sue | +0.011 |
Kitty | +0.010 |
Kim | +0.010 |
blond | +0.009 |
Tim | +0.009 |
Neg logit contributions | |
ya | -0.009 |
mber | -0.009 |
utes | -0.009 |
asper | -0.008 |
ub | -0.008 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
utes | +0.024 |
ya | +0.022 |
mber | +0.022 |
maid | +0.022 |
dolphins | +0.022 |
Neg logit contributions | |
Sue | -0.021 |
Kitty | -0.018 |
hy | -0.018 |
Kim | -0.017 |
Tim | -0.017 |
Token | t |
Token ID | 83 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
Sue | +0.177 |
Kitty | +0.157 |
Kim | +0.150 |
blond | +0.149 |
Tim | +0.147 |
Neg logit contributions | |
utes | -0.146 |
ub | -0.137 |
mber | -0.134 |
ya | -0.133 |
maid | -0.130 |
Token | scared |
Token ID | 12008 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.010 |
Kim | +0.010 |
Tim | +0.010 |
hy | +0.009 |
Neg logit contributions | |
utes | -0.019 |
ya | -0.018 |
maid | -0.018 |
mber | -0.018 |
dolphins | -0.018 |
Token | anymore |
Token ID | 7471 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Sue | +0.017 |
hy | +0.014 |
Kitty | +0.014 |
Kim | +0.014 |
Kim | +0.013 |
Neg logit contributions | |
dolphins | -0.024 |
ya | -0.024 |
utes | -0.024 |
ub | -0.024 |
maid | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
hy | +0.010 |
Tim | +0.010 |
Kim | +0.010 |
Neg logit contributions | |
utes | -0.031 |
ya | -0.030 |
maid | -0.029 |
mber | -0.029 |
dolphins | -0.029 |
Token | Now |
Token ID | 2735 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Sue | +0.010 |
Kitty | +0.008 |
Tim | +0.007 |
Kim | +0.007 |
She | +0.007 |
Neg logit contributions | |
utes | -0.022 |
ya | -0.021 |
maid | -0.021 |
dolphins | -0.021 |
fish | -0.021 |
Token | garden |
Token ID | 11376 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ya | +0.005 |
dolphins | +0.005 |
mber | +0.005 |
utes | +0.005 |
maid | +0.005 |
Neg logit contributions | |
Sue | -0.006 |
Kitty | -0.005 |
hy | -0.005 |
Kim | -0.005 |
Tim | -0.005 |
Token | because |
Token ID | 780 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
Kim | +0.005 |
Sue | +0.005 |
hy | +0.005 |
Kim | +0.005 |
hetically | +0.005 |
Neg logit contributions | |
dolphins | -0.005 |
ya | -0.005 |
coral | -0.005 |
fish | -0.005 |
dolphin | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
dolphins | +0.025 |
utes | +0.025 |
ya | +0.024 |
mber | +0.024 |
dolphin | +0.023 |
Neg logit contributions | |
hy | -0.020 |
Sue | -0.020 |
hetically | -0.018 |
blond | -0.018 |
Kitty | -0.017 |
Token | could |
Token ID | 714 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
utes | +0.026 |
maid | +0.024 |
dolphins | +0.024 |
ya | +0.023 |
ub | +0.023 |
Neg logit contributions | |
Sue | -0.016 |
Kitty | -0.014 |
Tim | -0.013 |
She | -0.013 |
Kim | -0.012 |
Token | see |
Token ID | 766 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
dolphins | +0.008 |
ya | +0.007 |
fish | +0.007 |
dolphin | +0.007 |
utes | +0.007 |
Neg logit contributions | |
hetically | -0.006 |
hy | -0.006 |
Kim | -0.006 |
Sue | -0.006 |
Kitty | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Sue | +0.017 |
hy | +0.017 |
Kitty | +0.015 |
Kim | +0.015 |
Kim | +0.015 |
Neg logit contributions | |
dolphins | -0.022 |
ya | -0.021 |
utes | -0.021 |
maid | -0.021 |
coral | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
ya | +0.105 |
dolphins | +0.105 |
utes | +0.104 |
mber | +0.101 |
coral | +0.099 |
Neg logit contributions | |
Sue | -0.064 |
hy | -0.061 |
Kitty | -0.057 |
hetically | -0.054 |
Kim | -0.054 |
Token | pretty |
Token ID | 2495 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
utes | +0.014 |
maid | +0.013 |
ya | +0.013 |
ub | +0.013 |
mber | +0.013 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.010 |
Tim | -0.010 |
She | -0.010 |
Kim | -0.010 |
Token | flowers |
Token ID | 12734 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
utes | +0.068 |
ya | +0.063 |
mber | +0.062 |
maid | +0.062 |
dolphins | +0.061 |
Neg logit contributions | |
Sue | -0.076 |
Kitty | -0.066 |
Tim | -0.063 |
Kim | -0.063 |
hy | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
fish | +0.024 |
dolphins | +0.024 |
utes | +0.023 |
ya | +0.023 |
maid | +0.023 |
Neg logit contributions | |
Sue | -0.018 |
hy | -0.016 |
Kim | -0.016 |
Kitty | -0.016 |
Kim | -0.015 |
Token | butterflies |
Token ID | 44571 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
utes | +0.044 |
ya | +0.041 |
maid | +0.041 |
mber | +0.041 |
ub | +0.040 |
Neg logit contributions | |
Sue | -0.036 |
Kitty | -0.031 |
Tim | -0.029 |
Kim | -0.029 |
hy | -0.028 |
Token | little |
Token ID | 1310 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
utes | +0.011 |
ya | +0.010 |
maid | +0.010 |
asper | +0.010 |
ub | +0.010 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.007 |
Tim | -0.007 |
hy | -0.007 |
Kim | -0.007 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
utes | +0.015 |
ya | +0.014 |
maid | +0.014 |
mber | +0.014 |
dolphins | +0.014 |
Neg logit contributions | |
Sue | -0.017 |
Kitty | -0.015 |
hy | -0.014 |
Kim | -0.014 |
Tim | -0.014 |
Token | called |
Token ID | 1444 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Sue | +0.011 |
hetically | +0.009 |
hy | +0.009 |
Kitty | +0.009 |
Kim | +0.009 |
Neg logit contributions | |
utes | -0.013 |
ya | -0.013 |
dolphins | -0.012 |
maid | -0.012 |
dolphin | -0.012 |
Token | Stella |
Token ID | 45856 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ya | +0.075 |
va | +0.075 |
mber | +0.074 |
utes | +0.071 |
ub | +0.070 |
Neg logit contributions | |
hetically | -0.034 |
itch | -0.027 |
bleed | -0.027 |
hy | -0.027 |
lick | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
utes | +0.144 |
mber | +0.138 |
ya | +0.138 |
dolphins | +0.137 |
maid | +0.137 |
Neg logit contributions | |
Sue | -0.044 |
Kitty | -0.032 |
hy | -0.027 |
Tim | -0.027 |
Kim | -0.027 |
Token | Stella |
Token ID | 45856 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
hetically | +0.004 |
Kim | +0.003 |
Kim | +0.003 |
bruises | +0.003 |
house | +0.003 |
Neg logit contributions | |
ya | -0.009 |
mber | -0.008 |
perspective | -0.008 |
va | -0.008 |
utes | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
utes | +0.094 |
ya | +0.093 |
mber | +0.090 |
maid | +0.089 |
dolphins | +0.088 |
Neg logit contributions | |
Sue | -0.095 |
Kitty | -0.083 |
hy | -0.080 |
Kim | -0.080 |
hetically | -0.078 |
Token | only |
Token ID | 691 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
hetically | +0.003 |
Sue | +0.003 |
Kim | +0.003 |
Kitty | +0.003 |
hy | +0.002 |
Neg logit contributions | |
dolphins | -0.002 |
utes | -0.002 |
dolphin | -0.002 |
ya | -0.002 |
actor | -0.002 |
Token | three |
Token ID | 1115 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
utes | +0.020 |
ya | +0.019 |
dolphins | +0.019 |
maid | +0.018 |
mber | +0.018 |
Neg logit contributions | |
Sue | -0.024 |
Kitty | -0.021 |
hy | -0.020 |
Kim | -0.020 |
Tim | -0.020 |
Token | years |
Token ID | 812 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Sue | +0.034 |
Kitty | +0.031 |
hy | +0.030 |
Kim | +0.030 |
Kim | +0.029 |
Neg logit contributions | |
ya | -0.019 |
dolphins | -0.018 |
utes | -0.017 |
maid | -0.017 |
mber | -0.016 |
Token | old |
Token ID | 1468 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
utes | +0.010 |
ya | +0.009 |
maid | +0.009 |
mber | +0.009 |
dolphins | +0.009 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.007 |
hy | -0.007 |
Kim | -0.007 |
Tim | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
Sue | +0.007 |
hy | +0.005 |
Kitty | +0.005 |
hetically | +0.005 |
lick | +0.005 |
Neg logit contributions | |
utes | -0.015 |
ub | -0.014 |
dolphins | -0.014 |
mber | -0.014 |
submarine | -0.014 |
Token | turned |
Token ID | 2900 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
house | +0.010 |
hy | +0.010 |
Kim | +0.010 |
Neg logit contributions | |
ya | -0.017 |
dolphins | -0.017 |
utes | -0.016 |
dolphin | -0.016 |
maid | -0.016 |
Token | around |
Token ID | 1088 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
utes | +0.007 |
dolphins | +0.007 |
ya | +0.007 |
dolphin | +0.007 |
targets | +0.007 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.006 |
hy | -0.006 |
house | -0.006 |
blond | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Sue | +0.003 |
Kitty | +0.002 |
hy | +0.002 |
Kim | +0.002 |
blond | +0.002 |
Neg logit contributions | |
utes | -0.004 |
dolphins | -0.004 |
ya | -0.004 |
maid | -0.003 |
ub | -0.003 |
Token | ran |
Token ID | 4966 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
dolphins | +0.004 |
ya | +0.004 |
submarine | +0.004 |
dolphin | +0.004 |
targets | +0.004 |
Neg logit contributions | |
Sue | -0.004 |
� | -0.004 |
Kitty | -0.004 |
hy | -0.004 |
house | -0.003 |
Token | away |
Token ID | 1497 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Sue | +0.028 |
Kitty | +0.024 |
hy | +0.023 |
Kim | +0.023 |
Tim | +0.022 |
Neg logit contributions | |
utes | -0.030 |
ya | -0.028 |
dolphins | -0.028 |
maid | -0.027 |
ub | -0.027 |
Token | from |
Token ID | 422 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
utes | +0.128 |
ya | +0.124 |
maid | +0.123 |
dolphins | +0.122 |
mber | +0.121 |
Neg logit contributions | |
Sue | -0.055 |
Kitty | -0.044 |
hy | -0.041 |
Kim | -0.040 |
Tim | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
dolphins | +0.019 |
utes | +0.019 |
ya | +0.019 |
maid | +0.019 |
dolphin | +0.018 |
Neg logit contributions | |
Sue | -0.010 |
hy | -0.008 |
Kitty | -0.008 |
She | -0.008 |
blond | -0.007 |
Token | gate |
Token ID | 8946 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
utes | +0.012 |
ya | +0.011 |
dolphins | +0.011 |
mber | +0.011 |
maid | +0.011 |
Neg logit contributions | |
Sue | -0.014 |
Kitty | -0.013 |
hy | -0.012 |
Kim | -0.012 |
Tim | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Sue | +0.025 |
Kitty | +0.024 |
blond | +0.022 |
Kim | +0.021 |
Kim | +0.021 |
Neg logit contributions | |
utes | -0.035 |
ub | -0.034 |
dolphins | -0.033 |
targets | -0.033 |
fish | -0.033 |
Token | They |
Token ID | 1119 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Sue | +0.011 |
hy | +0.009 |
Kitty | +0.009 |
hetically | +0.008 |
blond | +0.008 |
Neg logit contributions | |
utes | -0.020 |
ub | -0.018 |
dolphins | -0.018 |
mber | -0.018 |
ya | -0.018 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Sue | +0.042 |
Kitty | +0.035 |
hy | +0.033 |
Tim | +0.033 |
Kim | +0.033 |
Neg logit contributions | |
utes | -0.059 |
ya | -0.056 |
maid | -0.055 |
mber | -0.055 |
dolphins | -0.055 |
Token | They |
Token ID | 1119 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Sue | +0.006 |
hy | +0.006 |
hetically | +0.005 |
Kitty | +0.005 |
blond | +0.005 |
Neg logit contributions | |
utes | -0.010 |
mber | -0.010 |
ya | -0.010 |
ub | -0.010 |
va | -0.010 |
Token | walked |
Token ID | 6807 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ya | +0.004 |
utes | +0.004 |
dolphins | +0.004 |
maid | +0.004 |
asper | +0.004 |
Neg logit contributions | |
Sue | -0.003 |
Kitty | -0.002 |
hy | -0.002 |
Kim | -0.002 |
She | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Sue | +0.047 |
Kitty | +0.040 |
hy | +0.039 |
Kim | +0.038 |
Tim | +0.038 |
Neg logit contributions | |
utes | -0.054 |
ya | -0.051 |
dolphins | -0.050 |
maid | -0.050 |
mber | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
utes | +0.015 |
ya | +0.015 |
dolphins | +0.014 |
mber | +0.014 |
maid | +0.014 |
Neg logit contributions | |
Sue | -0.007 |
hy | -0.006 |
Kitty | -0.006 |
hetically | -0.005 |
Kim | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
utes | +0.026 |
ya | +0.025 |
mber | +0.024 |
dolphins | +0.024 |
maid | +0.024 |
Neg logit contributions | |
Sue | -0.022 |
Kitty | -0.020 |
Kim | -0.019 |
hy | -0.018 |
Tim | -0.018 |
Token | back |
Token ID | 736 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
utes | +0.135 |
maid | +0.134 |
dolphins | +0.133 |
mber | +0.130 |
submarine | +0.130 |
Neg logit contributions | |
Sue | -0.088 |
Kitty | -0.069 |
Tim | -0.066 |
Kim | -0.065 |
She | -0.063 |
Token | of |
Token ID | 286 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
utes | +0.051 |
ya | +0.049 |
maid | +0.048 |
dolphins | +0.048 |
mber | +0.048 |
Neg logit contributions | |
Sue | -0.038 |
Kitty | -0.032 |
Kim | -0.031 |
hy | -0.030 |
Tim | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Sue | +0.026 |
hy | +0.025 |
Kitty | +0.023 |
hetically | +0.022 |
She | +0.021 |
Neg logit contributions | |
ya | -0.051 |
utes | -0.051 |
dolphins | -0.050 |
mber | -0.048 |
dolphin | -0.048 |
Token | store |
Token ID | 3650 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.004 |
mber | +0.004 |
submarine | +0.004 |
va | +0.004 |
Neg logit contributions | |
Sue | -0.005 |
Kitty | -0.004 |
Kim | -0.004 |
hy | -0.004 |
hetically | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
hy | +0.002 |
Kim | +0.002 |
Tim | +0.002 |
Neg logit contributions | |
utes | -0.004 |
ya | -0.004 |
maid | -0.004 |
mber | -0.004 |
dolphins | -0.004 |
Token | an |
Token ID | 281 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
Sue | +0.029 |
Kitty | +0.023 |
hy | +0.022 |
Kim | +0.021 |
She | +0.020 |
Neg logit contributions | |
utes | -0.062 |
dolphins | -0.061 |
ya | -0.061 |
maid | -0.059 |
submarine | -0.059 |
Token | elderly |
Token ID | 13830 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
utes | +0.017 |
ub | +0.016 |
mber | +0.016 |
maid | +0.016 |
fish | +0.016 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.010 |
Tim | -0.010 |
hy | -0.010 |
Kim | -0.010 |
Token | man |
Token ID | 582 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
utes | +0.074 |
ya | +0.071 |
maid | +0.069 |
mber | +0.069 |
dolphins | +0.069 |
Neg logit contributions | |
Sue | -0.072 |
Kitty | -0.062 |
hy | -0.060 |
Kim | -0.059 |
Tim | -0.059 |
Token | on |
Token ID | 319 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
utes | +0.012 |
ya | +0.012 |
maid | +0.012 |
dolphins | +0.012 |
ub | +0.012 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.006 |
Kim | -0.006 |
hy | -0.006 |
Tim | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
utes | +0.017 |
dolphins | +0.017 |
ya | +0.017 |
submarine | +0.016 |
targets | +0.016 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.007 |
hy | -0.007 |
hetically | -0.007 |
Kim | -0.007 |
Token | other |
Token ID | 584 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
utes | +0.047 |
ya | +0.045 |
maid | +0.044 |
mber | +0.044 |
dolphins | +0.044 |
Neg logit contributions | |
Sue | -0.048 |
Kitty | -0.042 |
hy | -0.041 |
Kim | -0.040 |
Tim | -0.040 |
Token | side |
Token ID | 1735 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
utes | +0.105 |
ya | +0.101 |
maid | +0.099 |
mber | +0.099 |
dolphins | +0.099 |
Neg logit contributions | |
Sue | -0.074 |
Kitty | -0.063 |
hy | -0.060 |
Kim | -0.059 |
Tim | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
Sue | +0.005 |
Kitty | +0.004 |
hy | +0.004 |
Kim | +0.004 |
Tim | +0.004 |
Neg logit contributions | |
utes | -0.008 |
ya | -0.008 |
dolphins | -0.008 |
maid | -0.008 |
mber | -0.008 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.001 |
hy | +0.001 |
Kim | +0.001 |
Tim | +0.001 |
Neg logit contributions | |
utes | -0.005 |
ya | -0.004 |
mber | -0.004 |
maid | -0.004 |
dolphins | -0.004 |
Token | thought |
Token ID | 1807 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
utes | +0.072 |
ya | +0.068 |
maid | +0.068 |
dolphins | +0.067 |
mber | +0.067 |
Neg logit contributions | |
Sue | -0.046 |
Kitty | -0.039 |
hy | -0.037 |
Tim | -0.037 |
Kim | -0.036 |
Token | this |
Token ID | 428 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ya | +0.012 |
dolphins | +0.012 |
utes | +0.012 |
mber | +0.011 |
fish | +0.011 |
Neg logit contributions | |
Sue | -0.013 |
Kitty | -0.011 |
hy | -0.011 |
Kim | -0.010 |
Kim | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
dolphins | +0.011 |
utes | +0.011 |
fish | +0.011 |
ya | +0.011 |
maid | +0.011 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.006 |
hy | -0.006 |
Kim | -0.006 |
blond | -0.005 |
Token | But |
Token ID | 887 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Sue | +0.005 |
Kitty | +0.004 |
hy | +0.004 |
Kim | +0.004 |
Tim | +0.004 |
Neg logit contributions | |
utes | -0.011 |
ya | -0.011 |
mber | -0.011 |
dolphins | -0.010 |
maid | -0.010 |
Token | soon |
Token ID | 2582 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
utes | +0.016 |
ya | +0.015 |
dolphins | +0.015 |
maid | +0.015 |
mber | +0.015 |
Neg logit contributions | |
Sue | -0.011 |
Kitty | -0.009 |
hy | -0.009 |
Kim | -0.008 |
She | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.012 |
hy | +0.012 |
Kim | +0.011 |
Tim | +0.011 |
Neg logit contributions | |
utes | -0.029 |
ya | -0.029 |
dolphins | -0.029 |
maid | -0.028 |
mber | -0.028 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
utes | +0.029 |
ya | +0.027 |
mber | +0.027 |
maid | +0.026 |
dolphins | +0.026 |
Neg logit contributions | |
Sue | -0.019 |
Kitty | -0.016 |
Tim | -0.016 |
hy | -0.015 |
Kim | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
Sue | +0.035 |
Kitty | +0.029 |
hy | +0.028 |
� | +0.027 |
hetically | +0.026 |
Neg logit contributions | |
dolphins | -0.066 |
ya | -0.065 |
utes | -0.065 |
dolphin | -0.063 |
crew | -0.063 |
Token | big |
Token ID | 1263 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
utes | +0.016 |
ya | +0.016 |
maid | +0.015 |
dolphins | +0.015 |
mber | +0.015 |
Neg logit contributions | |
Sue | -0.010 |
Kitty | -0.008 |
hy | -0.008 |
Tim | -0.008 |
Kim | -0.008 |
Token | slur |
Token ID | 40066 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Sue | +0.014 |
Kitty | +0.012 |
hy | +0.012 |
Kim | +0.012 |
Tim | +0.011 |
Neg logit contributions | |
ya | -0.016 |
utes | -0.016 |
dolphins | -0.016 |
maid | -0.016 |
dolphin | -0.016 |
Token | p |
Token ID | 79 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Sue | +0.025 |
Kitty | +0.022 |
blond | +0.022 |
Kim | +0.021 |
hy | +0.021 |
Neg logit contributions | |
utes | -0.017 |
ya | -0.016 |
maid | -0.016 |
fish | -0.016 |
dolphins | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
utes | +0.009 |
maid | +0.009 |
dolphins | +0.009 |
fish | +0.008 |
ub | +0.008 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.006 |
Kim | -0.006 |
hy | -0.006 |
Tim | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.005 |
dolphins | +0.005 |
maid | +0.005 |
mber | +0.005 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.003 |
hy | -0.003 |
Kim | -0.003 |
Tim | -0.003 |
Token | told |
Token ID | 1297 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Sue | +0.018 |
Kitty | +0.014 |
Tim | +0.014 |
Kim | +0.013 |
She | +0.013 |
Neg logit contributions | |
utes | -0.031 |
maid | -0.029 |
ya | -0.029 |
ub | -0.029 |
dolphins | -0.028 |
Token | her |
Token ID | 607 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ya | +0.022 |
dolphins | +0.021 |
utes | +0.021 |
mber | +0.021 |
maid | +0.021 |
Neg logit contributions | |
Sue | -0.007 |
hy | -0.007 |
Kitty | -0.006 |
hetically | -0.005 |
blond | -0.005 |
Token | they |
Token ID | 484 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
Sue | +0.010 |
Kitty | +0.008 |
hy | +0.008 |
Kim | +0.008 |
Tim | +0.008 |
Neg logit contributions | |
utes | -0.016 |
ya | -0.015 |
maid | -0.015 |
mber | -0.015 |
dolphins | -0.015 |
Token | were |
Token ID | 547 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
utes | +0.026 |
ya | +0.025 |
mber | +0.025 |
maid | +0.025 |
ub | +0.025 |
Neg logit contributions | |
Sue | -0.013 |
Kitty | -0.010 |
Tim | -0.010 |
hy | -0.009 |
She | -0.009 |
Token | going |
Token ID | 1016 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
Sue | +0.014 |
Kitty | +0.011 |
Tim | +0.010 |
Kim | +0.010 |
She | +0.009 |
Neg logit contributions | |
utes | -0.027 |
mber | -0.026 |
asper | -0.026 |
ya | -0.026 |
ub | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
Sue | +0.025 |
Kitty | +0.020 |
Kim | +0.019 |
hy | +0.019 |
Tim | +0.019 |
Neg logit contributions | |
utes | -0.037 |
ya | -0.036 |
maid | -0.036 |
mber | -0.035 |
dolphins | -0.035 |
Token | prepare |
Token ID | 8335 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
utes | +0.020 |
ya | +0.019 |
maid | +0.019 |
mber | +0.019 |
dolphins | +0.019 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.008 |
Tim | -0.007 |
Kim | -0.007 |
hy | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
utes | +0.029 |
ya | +0.028 |
maid | +0.028 |
mber | +0.028 |
ub | +0.028 |
Neg logit contributions | |
Sue | -0.011 |
Kitty | -0.009 |
Tim | -0.008 |
Kim | -0.008 |
hy | -0.007 |
Token | surprise |
Token ID | 5975 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
utes | +0.029 |
ub | +0.029 |
asper | +0.029 |
targets | +0.028 |
chen | +0.028 |
Neg logit contributions | |
Sue | -0.017 |
Kitty | -0.014 |
Tim | -0.013 |
chocolate | -0.012 |
house | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
utes | +0.005 |
ya | +0.005 |
mber | +0.005 |
maid | +0.005 |
ub | +0.005 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.003 |
Tim | -0.003 |
Kim | -0.003 |
hy | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
utes | +0.030 |
ya | +0.029 |
dolphins | +0.029 |
maid | +0.029 |
mber | +0.029 |
Neg logit contributions | |
Sue | -0.014 |
Kitty | -0.011 |
hy | -0.011 |
Kim | -0.010 |
Tim | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
ya | +0.024 |
utes | +0.024 |
maid | +0.024 |
mber | +0.024 |
dolphins | +0.024 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.010 |
Tim | -0.009 |
Kim | -0.009 |
She | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
maid | +0.026 |
utes | +0.026 |
ya | +0.026 |
mber | +0.025 |
dolphins | +0.025 |
Neg logit contributions | |
Sue | -0.020 |
Kitty | -0.017 |
Kim | -0.016 |
Tim | -0.015 |
She | -0.015 |
Token | dog |
Token ID | 3290 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Sue | +0.040 |
Kitty | +0.035 |
Kim | +0.034 |
hy | +0.033 |
Tim | +0.033 |
Neg logit contributions | |
utes | -0.040 |
dolphins | -0.039 |
dolphin | -0.039 |
ya | -0.037 |
submarine | -0.037 |
Token | did |
Token ID | 750 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
dolphins | +0.011 |
dolphin | +0.011 |
fish | +0.010 |
maid | +0.010 |
submarine | +0.010 |
Neg logit contributions | |
Sue | -0.009 |
Kim | -0.008 |
Kitty | -0.008 |
hy | -0.007 |
Kim | -0.007 |
Token | not |
Token ID | 407 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
Sue | +0.003 |
hy | +0.003 |
Kitty | +0.003 |
blond | +0.003 |
hetically | +0.003 |
Neg logit contributions | |
utes | -0.004 |
dolphins | -0.004 |
ya | -0.004 |
maid | -0.004 |
fish | -0.004 |
Token | listen |
Token ID | 6004 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Sue | +0.025 |
� | +0.022 |
Kitty | +0.022 |
hy | +0.021 |
hetically | +0.021 |
Neg logit contributions | |
dolphins | -0.033 |
utes | -0.033 |
ya | -0.033 |
fish | -0.032 |
maid | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
utes | +0.018 |
ya | +0.018 |
dolphins | +0.018 |
ub | +0.018 |
maid | +0.017 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.011 |
hy | -0.010 |
Kim | -0.010 |
blond | -0.010 |
Token | It |
Token ID | 632 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
Sue | +0.000 |
hetically | +0.000 |
Kitty | +0.000 |
house | +0.000 |
hy | +0.000 |
Neg logit contributions | |
dolphins | -0.001 |
dolphin | -0.001 |
mber | -0.001 |
utes | -0.001 |
ub | -0.001 |
Token | sniff |
Token ID | 26300 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
Sue | +0.020 |
Kim | +0.018 |
Kitty | +0.017 |
hy | +0.017 |
Kim | +0.016 |
Neg logit contributions | |
dolphins | -0.023 |
fish | -0.023 |
dolphin | -0.023 |
submarine | -0.022 |
maid | -0.022 |
Token | ed |
Token ID | 276 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
dolphins | +0.023 |
utes | +0.022 |
ya | +0.022 |
maid | +0.022 |
ub | +0.022 |
Neg logit contributions | |
Sue | -0.030 |
hy | -0.026 |
Kitty | -0.026 |
Kim | -0.026 |
blond | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Sue | +0.008 |
� | +0.008 |
hy | +0.008 |
Kim | +0.007 |
house | +0.007 |
Neg logit contributions | |
dolphins | -0.009 |
maid | -0.009 |
ya | -0.009 |
dolphin | -0.009 |
ub | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
dolphins | +0.070 |
maid | +0.069 |
fish | +0.068 |
utes | +0.068 |
ya | +0.068 |
Neg logit contributions | |
Sue | -0.054 |
Kitty | -0.048 |
Kim | -0.046 |
hy | -0.044 |
Kim | -0.044 |
Token | He |
Token ID | 679 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
Sue | +0.010 |
Kitty | +0.008 |
hy | +0.007 |
Kim | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
utes | -0.019 |
ya | -0.019 |
mber | -0.018 |
maid | -0.018 |
dolphins | -0.018 |
Token | smiled |
Token ID | 13541 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
Tim | +0.002 |
hy | +0.001 |
Kim | +0.001 |
Neg logit contributions | |
utes | -0.003 |
ya | -0.003 |
mber | -0.003 |
maid | -0.003 |
ub | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
utes | +0.016 |
maid | +0.016 |
ya | +0.016 |
dolphins | +0.016 |
dolphin | +0.015 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.010 |
hy | -0.010 |
Kim | -0.009 |
Kim | -0.009 |
Token | knew |
Token ID | 2993 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
Sue | +0.036 |
hy | +0.031 |
Kitty | +0.031 |
Kim | +0.029 |
house | +0.028 |
Neg logit contributions | |
ya | -0.045 |
utes | -0.045 |
dolphins | -0.044 |
mber | -0.044 |
maid | -0.043 |
Token | he |
Token ID | 339 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
Sue | +0.001 |
hy | +0.001 |
Kitty | +0.001 |
house | +0.001 |
blond | +0.001 |
Neg logit contributions | |
dolphins | -0.001 |
ya | -0.001 |
utes | -0.001 |
mber | -0.001 |
crew | -0.001 |
Token | could |
Token ID | 714 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ya | +0.026 |
utes | +0.026 |
mber | +0.025 |
maid | +0.025 |
dolphins | +0.025 |
Neg logit contributions | |
Sue | -0.027 |
Kitty | -0.023 |
hy | -0.022 |
Kim | -0.022 |
Tim | -0.022 |
Token | stay |
Token ID | 2652 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
fish | +0.011 |
utes | +0.011 |
dolphins | +0.011 |
ub | +0.011 |
maid | +0.011 |
Neg logit contributions | |
Sue | -0.009 |
hy | -0.008 |
Kim | -0.008 |
Kitty | -0.008 |
blond | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
maid | +0.003 |
utes | +0.003 |
dolphins | +0.003 |
ya | +0.003 |
dolphin | +0.003 |
Neg logit contributions | |
Sue | -0.002 |
hy | -0.002 |
Kitty | -0.002 |
Kim | -0.002 |
hetically | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
dolphins | +0.004 |
ya | +0.004 |
utes | +0.004 |
submarine | +0.004 |
coral | +0.004 |
Neg logit contributions | |
Sue | -0.002 |
hy | -0.002 |
Kitty | -0.002 |
Kim | -0.002 |
hetically | -0.002 |
Token | me |
Token ID | 502 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
utes | +0.009 |
ya | +0.009 |
dolphins | +0.009 |
maid | +0.009 |
mber | +0.009 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.008 |
hy | -0.007 |
Kim | -0.007 |
Tim | -0.007 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ya | +0.010 |
utes | +0.010 |
mber | +0.010 |
dolphins | +0.010 |
maid | +0.010 |
Neg logit contributions | |
Sue | -0.010 |
Kitty | -0.009 |
Kim | -0.008 |
hy | -0.008 |
Tim | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Sue | +0.008 |
Kitty | +0.007 |
hy | +0.006 |
Kim | +0.006 |
Tim | +0.006 |
Neg logit contributions | |
utes | -0.009 |
ya | -0.009 |
dolphins | -0.009 |
maid | -0.009 |
mber | -0.009 |
Token | sit |
Token ID | 1650 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Sue | +0.003 |
Kitty | +0.002 |
hy | +0.002 |
Kim | +0.002 |
hetically | +0.002 |
Neg logit contributions | |
utes | -0.004 |
dolphins | -0.004 |
ya | -0.004 |
dolphin | -0.004 |
maid | -0.004 |
Token | still |
Token ID | 991 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Sue | +0.042 |
hy | +0.036 |
Kitty | +0.036 |
Kim | +0.034 |
lick | +0.032 |
Neg logit contributions | |
utes | -0.051 |
maid | -0.049 |
fish | -0.047 |
dolphins | -0.047 |
ya | -0.047 |
Token | even |
Token ID | 772 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
utes | +0.027 |
ya | +0.026 |
dolphins | +0.026 |
maid | +0.025 |
fish | +0.025 |
Neg logit contributions | |
Sue | -0.016 |
Kitty | -0.013 |
hy | -0.013 |
Kim | -0.013 |
Kim | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
utes | +0.025 |
ya | +0.025 |
dolphins | +0.024 |
mber | +0.024 |
maid | +0.024 |
Neg logit contributions | |
Sue | -0.021 |
Kitty | -0.018 |
hy | -0.017 |
Kim | -0.017 |
Tim | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
utes | +0.026 |
dolphins | +0.026 |
ya | +0.026 |
maid | +0.025 |
mber | +0.025 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.010 |
hy | -0.009 |
Kim | -0.009 |
She | -0.009 |
Token | moment |
Token ID | 2589 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
utes | +0.011 |
ya | +0.011 |
maid | +0.011 |
dolphins | +0.010 |
asper | +0.010 |
Neg logit contributions | |
Sue | -0.007 |
Kitty | -0.006 |
hy | -0.006 |
Tim | -0.006 |
Kim | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
Sue | +0.023 |
Kitty | +0.019 |
hy | +0.017 |
Kim | +0.017 |
Tim | +0.016 |
Neg logit contributions | |
utes | -0.042 |
ya | -0.041 |
dolphins | -0.040 |
mber | -0.040 |
maid | -0.039 |
Token | One |
Token ID | 1881 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
Sue | +0.017 |
Kitty | +0.014 |
hy | +0.013 |
Kim | +0.013 |
Tim | +0.012 |
Neg logit contributions | |
utes | -0.035 |
ya | -0.033 |
mber | -0.033 |
dolphins | -0.033 |
maid | -0.032 |
Token | day |
Token ID | 1110 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
Sue | +0.036 |
hy | +0.033 |
Kitty | +0.033 |
hetically | +0.033 |
Kim | +0.032 |
Neg logit contributions | |
ya | -0.024 |
mber | -0.023 |
dolphin | -0.023 |
dolphins | -0.023 |
utes | -0.022 |
Token | is |
Token ID | 318 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
utes | +0.052 |
ya | +0.050 |
maid | +0.050 |
ub | +0.049 |
mber | +0.049 |
Neg logit contributions | |
Sue | -0.025 |
She | -0.020 |
Tim | -0.020 |
Kitty | -0.019 |
shake | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.012 |
Tim | +0.011 |
Kim | +0.011 |
Tom | +0.010 |
Neg logit contributions | |
utes | -0.023 |
maid | -0.023 |
ya | -0.023 |
mber | -0.023 |
ub | -0.022 |
Token | moral |
Token ID | 6573 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
Sue | +0.003 |
Kitty | +0.002 |
hy | +0.002 |
Tim | +0.002 |
Kim | +0.002 |
Neg logit contributions | |
utes | -0.005 |
ya | -0.005 |
mber | -0.004 |
maid | -0.004 |
ub | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
utes | +0.028 |
maid | +0.028 |
ya | +0.028 |
mber | +0.027 |
dolphins | +0.027 |
Neg logit contributions | |
Sue | -0.015 |
Kitty | -0.012 |
hy | -0.012 |
Kim | -0.011 |
Tim | -0.011 |
Token | this |
Token ID | 428 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
utes | +0.003 |
ya | +0.003 |
mber | +0.003 |
maid | +0.003 |
ub | +0.003 |
Neg logit contributions | |
Sue | -0.002 |
Kitty | -0.001 |
Tim | -0.001 |
Kim | -0.001 |
Tom | -0.001 |
Token | story |
Token ID | 1621 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
maid | +0.018 |
ub | +0.018 |
asper | +0.018 |
utes | +0.018 |
ya | +0.018 |
Neg logit contributions | |
Sue | -0.009 |
Kitty | -0.007 |
Tim | -0.006 |
She | -0.006 |
Tom | -0.006 |
Token | ." |
Token ID | 526 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
Kim | +0.010 |
Tim | +0.010 |
She | +0.010 |
Neg logit contributions | |
utes | -0.017 |
ya | -0.017 |
dolphins | -0.017 |
maid | -0.017 |
submarine | -0.016 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
utes | +0.003 |
ya | +0.003 |
dolphins | +0.003 |
mber | +0.003 |
maid | +0.003 |
Neg logit contributions | |
Sue | -0.002 |
Kitty | -0.001 |
hy | -0.001 |
Kim | -0.001 |
Tim | -0.001 |
Token | L |
Token ID | 43 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
utes | +0.050 |
dolphins | +0.048 |
mber | +0.047 |
ya | +0.046 |
maid | +0.046 |
Neg logit contributions | |
Sue | -0.071 |
Kitty | -0.064 |
hy | -0.064 |
Kim | -0.063 |
hetically | -0.060 |
Token | ily |
Token ID | 813 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Sue | +0.036 |
Tim | +0.027 |
Kim | +0.027 |
Tom | +0.027 |
Kitty | +0.025 |
Neg logit contributions | |
utes | -0.062 |
submarine | -0.060 |
mber | -0.060 |
ya | -0.059 |
culture | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Sue | +0.009 |
Kitty | +0.008 |
hy | +0.007 |
Kim | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
ya | -0.011 |
utes | -0.011 |
mber | -0.011 |
maid | -0.011 |
dolphins | -0.011 |
Token | trap |
Token ID | 12840 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
utes | +0.001 |
ya | +0.001 |
dolphins | +0.001 |
maid | +0.001 |
mber | +0.001 |
Neg logit contributions | |
Sue | -0.001 |
Kitty | -0.001 |
Kim | -0.001 |
hy | -0.001 |
Tim | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
utes | +0.040 |
ya | +0.039 |
dolphins | +0.039 |
fish | +0.038 |
maid | +0.038 |
Neg logit contributions | |
Sue | -0.028 |
Kitty | -0.025 |
hy | -0.024 |
Kim | -0.024 |
Kim | -0.022 |
Token | touched |
Token ID | 12615 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
ya | +0.019 |
utes | +0.019 |
dolphins | +0.019 |
maid | +0.019 |
mber | +0.019 |
Neg logit contributions | |
Sue | -0.014 |
hy | -0.012 |
Kitty | -0.012 |
Kim | -0.011 |
She | -0.011 |
Token | them |
Token ID | 606 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
dolphins | +0.020 |
ya | +0.019 |
utes | +0.019 |
dolphin | +0.019 |
maid | +0.018 |
Neg logit contributions | |
Sue | -0.022 |
hy | -0.022 |
Kitty | -0.020 |
blond | -0.019 |
house | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Sue | +0.029 |
Kitty | +0.025 |
hy | +0.025 |
Kim | +0.025 |
Kim | +0.025 |
Neg logit contributions | |
utes | -0.033 |
maid | -0.033 |
fish | -0.033 |
ub | -0.032 |
targets | -0.032 |
Token | The |
Token ID | 383 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Sue | +0.003 |
hy | +0.002 |
Kitty | +0.002 |
Kim | +0.002 |
hetically | +0.002 |
Neg logit contributions | |
utes | -0.006 |
ya | -0.006 |
mber | -0.006 |
dolphins | -0.006 |
ub | -0.006 |
Token | frogs |
Token ID | 37475 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
Sue | +0.039 |
Kitty | +0.034 |
hy | +0.033 |
Tim | +0.032 |
Kim | +0.031 |
Neg logit contributions | |
utes | -0.041 |
ya | -0.039 |
maid | -0.038 |
mber | -0.038 |
ub | -0.038 |
Token | were |
Token ID | 547 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
utes | +0.032 |
dolphins | +0.031 |
fish | +0.031 |
ya | +0.031 |
maid | +0.031 |
Neg logit contributions | |
Sue | -0.020 |
Kitty | -0.017 |
Kim | -0.017 |
hy | -0.016 |
Kim | -0.015 |
Token | very |
Token ID | 845 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
Sue | +0.024 |
Kitty | +0.021 |
hy | +0.021 |
Kim | +0.020 |
Tim | +0.020 |
Neg logit contributions | |
utes | -0.029 |
dolphins | -0.028 |
ya | -0.028 |
maid | -0.028 |
mber | -0.027 |
Token | still |
Token ID | 991 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
utes | +0.035 |
ya | +0.034 |
maid | +0.033 |
dolphins | +0.033 |
mber | +0.033 |
Neg logit contributions | |
Sue | -0.026 |
Kitty | -0.022 |
hy | -0.021 |
Kim | -0.021 |
Tim | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
utes | +0.017 |
dolphins | +0.017 |
maid | +0.017 |
ya | +0.017 |
fish | +0.016 |
Neg logit contributions | |
Sue | -0.015 |
Kitty | -0.013 |
hy | -0.013 |
Kim | -0.013 |
Kim | -0.012 |
Token | Yes |
Token ID | 5297 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
utes | +0.000 |
ya | +0.000 |
maid | +0.000 |
dolphins | +0.000 |
mber | +0.000 |
Neg logit contributions | |
Sue | -0.000 |
Kitty | -0.000 |
hy | -0.000 |
Kim | -0.000 |
Tim | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Sue | +0.015 |
hy | +0.013 |
Kitty | +0.012 |
blond | +0.012 |
Kim | +0.011 |
Neg logit contributions | |
ya | -0.026 |
maid | -0.026 |
utes | -0.025 |
ub | -0.025 |
mber | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Sue | +0.011 |
hy | +0.010 |
Kitty | +0.009 |
hetically | +0.009 |
blond | +0.009 |
Neg logit contributions | |
ya | -0.010 |
dolphins | -0.010 |
utes | -0.010 |
mber | -0.010 |
dolphin | -0.010 |
Token | does |
Token ID | 857 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
Sue | +0.004 |
hy | +0.003 |
Kitty | +0.003 |
Kim | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
maid | -0.003 |
ya | -0.003 |
utes | -0.003 |
dolphins | -0.003 |
mber | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Sue | +0.024 |
Kitty | +0.020 |
hy | +0.020 |
Kim | +0.019 |
Tim | +0.018 |
Neg logit contributions | |
utes | -0.041 |
ya | -0.040 |
dolphins | -0.039 |
maid | -0.039 |
mber | -0.039 |
Token | Do |
Token ID | 2141 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
utes | +0.009 |
ub | +0.008 |
ya | +0.008 |
mber | +0.008 |
dolphins | +0.008 |
Neg logit contributions | |
Sue | -0.007 |
hy | -0.006 |
Kitty | -0.006 |
hetically | -0.006 |
Kim | -0.006 |
Token | you |
Token ID | 345 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Sue | +0.047 |
hy | +0.043 |
Kitty | +0.043 |
Kim | +0.041 |
hetically | +0.041 |
Neg logit contributions | |
utes | -0.026 |
ya | -0.025 |
dolphins | -0.025 |
mber | -0.024 |
ub | -0.022 |
Token | want |
Token ID | 765 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Sue | +0.005 |
Kitty | +0.004 |
hy | +0.004 |
Tim | +0.004 |
Kim | +0.004 |
Neg logit contributions | |
utes | -0.007 |
ya | -0.007 |
maid | -0.007 |
mber | -0.007 |
dolphins | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
Sue | +0.003 |
Kitty | +0.002 |
Tim | +0.002 |
Spot | +0.002 |
Tom | +0.002 |
Neg logit contributions | |
utes | -0.006 |
maid | -0.005 |
ub | -0.005 |
ya | -0.005 |
mber | -0.005 |
Token | collect |
Token ID | 2824 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
hy | +0.001 |
Kim | +0.001 |
Tim | +0.001 |
Neg logit contributions | |
utes | -0.003 |
ya | -0.003 |
maid | -0.003 |
dolphins | -0.003 |
mber | -0.003 |
Token | some |
Token ID | 617 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
Sue | +0.006 |
Kitty | +0.005 |
Tim | +0.005 |
Kim | +0.004 |
hy | +0.004 |
Neg logit contributions | |
utes | -0.011 |
mber | -0.011 |
ya | -0.011 |
maid | -0.010 |
asper | -0.010 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
Sue | +0.051 |
Kitty | +0.045 |
hy | +0.044 |
Kim | +0.042 |
blond | +0.040 |
Neg logit contributions | |
utes | -0.056 |
ya | -0.056 |
dolphins | -0.055 |
mber | -0.054 |
maid | -0.053 |
Token | 't |
Token ID | 470 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Sue | +0.000 |
hy | +0.000 |
Kitty | +0.000 |
blond | +0.000 |
Kim | +0.000 |
Neg logit contributions | |
utes | -0.000 |
ub | -0.000 |
dolphins | -0.000 |
asper | -0.000 |
ya | -0.000 |
Token | know |
Token ID | 760 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.012 |
hy | +0.011 |
Kim | +0.011 |
Tim | +0.011 |
Neg logit contributions | |
utes | -0.012 |
ya | -0.012 |
mber | -0.012 |
maid | -0.012 |
dolphins | -0.012 |
Token | what |
Token ID | 644 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
hy | +0.014 |
Sue | +0.014 |
� | +0.013 |
lick | +0.013 |
coat | +0.013 |
Neg logit contributions | |
dolphins | -0.009 |
utes | -0.008 |
crew | -0.008 |
maid | -0.008 |
fish | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Sue | +0.036 |
Kitty | +0.031 |
hy | +0.030 |
Kim | +0.029 |
Tim | +0.029 |
Neg logit contributions | |
utes | -0.039 |
ya | -0.038 |
dolphins | -0.037 |
mber | -0.037 |
maid | -0.036 |
Token | do |
Token ID | 466 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
Sue | +0.031 |
Kitty | +0.027 |
hy | +0.027 |
blond | +0.025 |
hetically | +0.025 |
Neg logit contributions | |
utes | -0.042 |
fish | -0.040 |
ya | -0.040 |
maid | -0.039 |
dolphins | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
hy | +0.002 |
Kim | +0.002 |
blond | +0.001 |
Neg logit contributions | |
utes | -0.003 |
ya | -0.003 |
ub | -0.003 |
maid | -0.003 |
dolphins | -0.003 |
Token | |
Token ID | 220 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Sue | +0.019 |
hy | +0.016 |
Kitty | +0.015 |
Kim | +0.014 |
blond | +0.013 |
Neg logit contributions | |
utes | -0.036 |
mber | -0.035 |
ya | -0.035 |
ub | -0.034 |
va | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
utes | +0.026 |
ya | +0.024 |
mber | +0.024 |
maid | +0.024 |
dolphins | +0.024 |
Neg logit contributions | |
Sue | -0.017 |
Kitty | -0.014 |
hy | -0.014 |
Kim | -0.013 |
Tim | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Sue | +0.015 |
Kitty | +0.012 |
Tim | +0.011 |
Kim | +0.011 |
She | +0.011 |
Neg logit contributions | |
utes | -0.029 |
maid | -0.029 |
ya | -0.029 |
dolphins | -0.028 |
mber | -0.028 |
Token | Then |
Token ID | 6423 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Sue | +0.017 |
Kitty | +0.015 |
hy | +0.015 |
Kim | +0.015 |
Tim | +0.015 |
Neg logit contributions | |
utes | -0.014 |
ya | -0.013 |
mber | -0.013 |
maid | -0.013 |
dolphins | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
utes | +0.018 |
ya | +0.017 |
mber | +0.017 |
maid | +0.017 |
dolphins | +0.017 |
Neg logit contributions | |
Sue | -0.008 |
Kitty | -0.006 |
hy | -0.006 |
Tim | -0.006 |
Kim | -0.006 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Sue | +0.007 |
Kitty | +0.006 |
hy | +0.006 |
Kim | +0.006 |
Tim | +0.006 |
Neg logit contributions | |
utes | -0.012 |
ya | -0.012 |
maid | -0.012 |
mber | -0.012 |
dolphins | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
utes | +0.059 |
ya | +0.058 |
mber | +0.058 |
asper | +0.056 |
maid | +0.056 |
Neg logit contributions | |
Sue | -0.019 |
Kitty | -0.013 |
Tim | -0.012 |
Kim | -0.011 |
She | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
hetically | +0.003 |
hy | +0.003 |
Sue | +0.003 |
Kitty | +0.003 |
shake | +0.003 |
Neg logit contributions | |
utes | -0.005 |
dolphins | -0.004 |
mber | -0.004 |
ub | -0.004 |
submarine | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
maid | +0.012 |
ya | +0.012 |
mber | +0.011 |
utes | +0.011 |
submarine | +0.011 |
Neg logit contributions | |
Sue | -0.006 |
Kitty | -0.004 |
Tim | -0.004 |
Kim | -0.004 |
She | -0.004 |
Token | They |
Token ID | 2990 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
maid | +0.014 |
utes | +0.014 |
ya | +0.013 |
dolphins | +0.013 |
mber | +0.013 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.010 |
Tim | -0.009 |
Kim | -0.009 |
hy | -0.009 |
Token | show |
Token ID | 905 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
Kim | +0.010 |
hy | +0.010 |
Tim | +0.010 |
Neg logit contributions | |
utes | -0.021 |
ya | -0.021 |
dolphins | -0.021 |
maid | -0.021 |
ub | -0.020 |
Token | their |
Token ID | 511 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
utes | +0.027 |
ya | +0.026 |
maid | +0.026 |
mber | +0.026 |
dolphins | +0.026 |
Neg logit contributions | |
Sue | -0.017 |
Kitty | -0.014 |
hy | -0.014 |
Kim | -0.013 |
Tim | -0.013 |
Token | map |
Token ID | 3975 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Sue | +0.025 |
Tom | +0.021 |
Tim | +0.021 |
Kitty | +0.021 |
shake | +0.021 |
Neg logit contributions | |
mber | -0.030 |
ub | -0.029 |
va | -0.029 |
us | -0.029 |
ya | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
utes | +0.006 |
ya | +0.006 |
mber | +0.006 |
va | +0.006 |
ub | +0.006 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.003 |
hy | -0.003 |
Kim | -0.003 |
Tim | -0.003 |
Token | their |
Token ID | 511 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
dolphins | +0.021 |
ya | +0.020 |
utes | +0.020 |
dolphin | +0.020 |
crew | +0.020 |
Neg logit contributions | |
hy | -0.017 |
hetically | -0.016 |
blond | -0.015 |
coat | -0.015 |
� | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
utes | +0.018 |
fish | +0.017 |
ya | +0.017 |
ub | +0.017 |
dolphins | +0.017 |
Neg logit contributions | |
Sue | -0.017 |
Kitty | -0.015 |
Kim | -0.015 |
hy | -0.014 |
Kim | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Sue | +0.005 |
Kitty | +0.005 |
hy | +0.005 |
Kim | +0.004 |
Tim | +0.004 |
Neg logit contributions | |
utes | -0.006 |
ya | -0.006 |
dolphins | -0.006 |
maid | -0.006 |
mber | -0.006 |
Token | sound |
Token ID | 2128 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Sue | +0.005 |
Kitty | +0.004 |
hy | +0.004 |
Tim | +0.004 |
Kim | +0.004 |
Neg logit contributions | |
utes | -0.006 |
ya | -0.005 |
mber | -0.005 |
maid | -0.005 |
ub | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
fish | +0.014 |
dolphins | +0.014 |
utes | +0.014 |
maid | +0.013 |
dolphin | +0.013 |
Neg logit contributions | |
Sue | -0.012 |
Kitty | -0.011 |
Kim | -0.010 |
hy | -0.010 |
blond | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Sue | +0.016 |
Kitty | +0.013 |
hy | +0.013 |
Kim | +0.013 |
She | +0.013 |
Neg logit contributions | |
utes | -0.018 |
dolphins | -0.017 |
ya | -0.017 |
maid | -0.017 |
mber | -0.016 |
Token | loud |
Token ID | 7812 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
utes | +0.005 |
dolphins | +0.004 |
ya | +0.004 |
ub | +0.004 |
mber | +0.004 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.004 |
Kim | -0.004 |
hy | -0.004 |
hetically | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
Sue | +0.087 |
blond | +0.073 |
Kitty | +0.073 |
Kim | +0.072 |
Kim | +0.071 |
Neg logit contributions | |
ya | -0.097 |
dolphins | -0.097 |
ub | -0.096 |
utes | -0.094 |
targets | -0.093 |
Token | it |
Token ID | 340 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Sue | +0.023 |
hy | +0.021 |
Kitty | +0.020 |
hetically | +0.019 |
� | +0.019 |
Neg logit contributions | |
utes | -0.030 |
ya | -0.029 |
dolphins | -0.029 |
mber | -0.029 |
maid | -0.028 |
Token | made |
Token ID | 925 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
utes | +0.013 |
ya | +0.012 |
dolphins | +0.012 |
maid | +0.012 |
mber | +0.012 |
Neg logit contributions | |
Sue | -0.010 |
Kitty | -0.008 |
hy | -0.008 |
Kim | -0.008 |
Tim | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
hy | +0.020 |
Sue | +0.020 |
hetically | +0.018 |
� | +0.018 |
lick | +0.018 |
Neg logit contributions | |
utes | -0.038 |
targets | -0.037 |
ya | -0.037 |
asper | -0.036 |
dolphins | -0.036 |
Token | feel |
Token ID | 1254 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
Sue | +0.039 |
Kitty | +0.032 |
Tim | +0.031 |
hy | +0.030 |
She | +0.030 |
Neg logit contributions | |
utes | -0.048 |
maid | -0.046 |
ya | -0.045 |
dolphins | -0.044 |
crew | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
utes | +0.002 |
ya | +0.002 |
dolphins | +0.002 |
maid | +0.002 |
fish | +0.002 |
Neg logit contributions | |
Sue | -0.001 |
hy | -0.001 |
Kitty | -0.001 |
Kim | -0.001 |
hetically | -0.001 |
Token | Max |
Token ID | 5436 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
utes | +0.007 |
submarine | +0.007 |
targets | +0.007 |
Dolphin | +0.007 |
icated | +0.007 |
Neg logit contributions | |
Sue | -0.006 |
hetically | -0.005 |
hy | -0.005 |
pies | -0.005 |
wipe | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
utes | +0.021 |
ya | +0.020 |
mber | +0.019 |
dolphins | +0.019 |
maid | +0.019 |
Neg logit contributions | |
Sue | -0.018 |
Kitty | -0.015 |
hy | -0.015 |
Kim | -0.014 |
Tim | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
utes | +0.048 |
dolphins | +0.048 |
targets | +0.046 |
dolphin | +0.045 |
crew | +0.045 |
Neg logit contributions | |
Sue | -0.026 |
hetically | -0.023 |
� | -0.021 |
Kitty | -0.020 |
house | -0.019 |
Token | lot |
Token ID | 1256 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
Sue | +0.021 |
Kitty | +0.018 |
hy | +0.017 |
Kim | +0.017 |
Tim | +0.017 |
Neg logit contributions | |
utes | -0.032 |
ya | -0.030 |
maid | -0.030 |
mber | -0.030 |
dolphins | -0.030 |
Token | of |
Token ID | 286 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
utes | +0.038 |
dolphins | +0.035 |
ya | +0.035 |
mber | +0.034 |
fish | +0.034 |
Neg logit contributions | |
Sue | -0.029 |
Kitty | -0.026 |
Kim | -0.025 |
Tim | -0.024 |
hy | -0.024 |
Token | fle |
Token ID | 5104 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Sue | +0.087 |
Kitty | +0.075 |
hy | +0.073 |
Kim | +0.071 |
Tim | +0.070 |
Neg logit contributions | |
utes | -0.100 |
ya | -0.095 |
dolphins | -0.094 |
mber | -0.092 |
maid | -0.092 |
Token | as |
Token ID | 292 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ya | +0.046 |
mber | +0.043 |
utes | +0.043 |
dolphins | +0.041 |
maid | +0.041 |
Neg logit contributions | |
Sue | -0.109 |
Kitty | -0.099 |
hy | -0.097 |
Kim | -0.095 |
Tim | -0.095 |
Token | on |
Token ID | 319 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Sue | +0.038 |
Kitty | +0.032 |
Kim | +0.030 |
Kim | +0.029 |
blond | +0.028 |
Neg logit contributions | |
utes | -0.055 |
dolphins | -0.054 |
fish | -0.054 |
targets | -0.053 |
ya | -0.053 |
Token | his |
Token ID | 465 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Sue | +0.004 |
hy | +0.003 |
Kitty | +0.003 |
Kim | +0.003 |
hetically | +0.003 |
Neg logit contributions | |
utes | -0.008 |
dolphins | -0.008 |
ya | -0.008 |
targets | -0.008 |
dolphin | -0.007 |
Token | fur |
Token ID | 9230 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Sue | +0.019 |
Kitty | +0.016 |
hy | +0.015 |
Kim | +0.015 |
Tim | +0.015 |
Neg logit contributions | |
utes | -0.023 |
ya | -0.022 |
maid | -0.022 |
dolphins | -0.022 |
mber | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Sue | +0.042 |
Kitty | +0.037 |
Kim | +0.036 |
hy | +0.033 |
blond | +0.033 |
Neg logit contributions | |
ya | -0.053 |
utes | -0.052 |
maid | -0.050 |
dolphins | -0.050 |
mber | -0.050 |
Token | Jenn |
Token ID | 9777 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Sue | +0.014 |
Kitty | +0.012 |
hy | +0.011 |
hetically | +0.011 |
blond | +0.010 |
Neg logit contributions | |
utes | -0.025 |
ya | -0.024 |
ub | -0.023 |
mber | -0.023 |
asper | -0.023 |
Token | ie |
Token ID | 494 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Sue | +0.013 |
Kitty | +0.011 |
Kim | +0.011 |
Tim | +0.010 |
hy | +0.010 |
Neg logit contributions | |
utes | -0.013 |
submarine | -0.013 |
dolphins | -0.012 |
coral | -0.012 |
mber | -0.012 |
Token | had |
Token ID | 550 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
utes | +0.011 |
maid | +0.010 |
ya | +0.010 |
dolphins | +0.010 |
ub | +0.010 |
Neg logit contributions | |
Sue | -0.006 |
Kitty | -0.005 |
hy | -0.005 |
Tim | -0.005 |
She | -0.005 |
Token | lots |
Token ID | 6041 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
utes | +0.037 |
ya | +0.036 |
maid | +0.036 |
dolphins | +0.035 |
mber | +0.035 |
Neg logit contributions | |
Sue | -0.019 |
Kitty | -0.015 |
hy | -0.014 |
Kim | -0.014 |
Tim | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
Sue | +0.029 |
Kitty | +0.026 |
Kim | +0.026 |
Kim | +0.025 |
Tim | +0.024 |
Neg logit contributions | |
dolphins | -0.029 |
ya | -0.029 |
mber | -0.028 |
utes | -0.027 |
va | -0.027 |
Token | fun |
Token ID | 1257 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
Sue | +0.107 |
Kitty | +0.092 |
hy | +0.089 |
Kim | +0.088 |
Tim | +0.085 |
Neg logit contributions | |
utes | -0.134 |
ya | -0.131 |
dolphins | -0.131 |
mber | -0.125 |
maid | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Sue | +0.028 |
Kitty | +0.023 |
hy | +0.023 |
Kim | +0.022 |
Tim | +0.021 |
Neg logit contributions | |
utes | -0.037 |
ya | -0.036 |
dolphins | -0.036 |
maid | -0.035 |
mber | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
dolphins | +0.012 |
ya | +0.012 |
utes | +0.011 |
mber | +0.011 |
dolphin | +0.011 |
Neg logit contributions | |
Sue | -0.011 |
Kitty | -0.010 |
hy | -0.010 |
hetically | -0.010 |
Kim | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Sue | +0.014 |
� | +0.012 |
Kitty | +0.012 |
hy | +0.012 |
hetically | +0.012 |
Neg logit contributions | |
ya | -0.020 |
utes | -0.020 |
dolphins | -0.020 |
mber | -0.019 |
crew | -0.019 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
utes | +0.042 |
maid | +0.039 |
ya | +0.039 |
dolphins | +0.038 |
mber | +0.038 |
Neg logit contributions | |
Sue | -0.025 |
Kitty | -0.021 |
Tim | -0.020 |
hy | -0.020 |
She | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
utes | +0.040 |
ub | +0.038 |
ya | +0.038 |
fish | +0.037 |
maid | +0.037 |
Neg logit contributions | |
Sue | -0.030 |
Kitty | -0.027 |
hy | -0.026 |
blond | -0.025 |
Kim | -0.024 |
Token | With |
Token ID | 2080 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Sue | +0.003 |
She | +0.002 |
Kitty | +0.002 |
Tim | +0.001 |
Kim | +0.001 |
Neg logit contributions | |
utes | -0.013 |
maid | -0.013 |
fish | -0.013 |
ya | -0.013 |
dolphins | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
dolphins | +0.010 |
utes | +0.010 |
ya | +0.010 |
dolphin | +0.010 |
targets | +0.010 |
Neg logit contributions | |
Sue | -0.006 |
hy | -0.005 |
Kitty | -0.005 |
house | -0.004 |
Kim | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Sue | +0.029 |
Kitty | +0.023 |
hy | +0.022 |
Kim | +0.022 |
Tim | +0.022 |
Neg logit contributions | |
utes | -0.052 |
ya | -0.050 |
maid | -0.049 |
dolphins | -0.049 |
mber | -0.049 |
Token | bit |
Token ID | 1643 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Sue | +0.019 |
Kitty | +0.017 |
Kim | +0.016 |
Kim | +0.015 |
hy | +0.015 |
Neg logit contributions | |
utes | -0.021 |
maid | -0.021 |
ub | -0.021 |
ya | -0.021 |
dolphin | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ub | +0.012 |
utes | +0.012 |
dolphins | +0.012 |
ya | +0.012 |
maid | +0.011 |
Neg logit contributions | |
Sue | -0.011 |
Kitty | -0.010 |
hy | -0.010 |
Kim | -0.009 |
Kim | -0.009 |
Token | help |
Token ID | 1037 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
Sue | +0.083 |
hy | +0.076 |
Kitty | +0.074 |
house | +0.069 |
Kim | +0.067 |
Neg logit contributions | |
utes | -0.106 |
dolphins | -0.103 |
targets | -0.101 |
ya | -0.101 |
dolphin | -0.098 |
Token | from |
Token ID | 422 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Sue | +0.021 |
hy | +0.018 |
Kitty | +0.017 |
blond | +0.017 |
Kim | +0.016 |
Neg logit contributions | |
utes | -0.035 |
ya | -0.035 |
ub | -0.034 |
dolphins | -0.034 |
maid | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
Sue | +0.002 |
Kitty | +0.002 |
Tim | +0.002 |
Kim | +0.002 |
hy | +0.002 |
Neg logit contributions | |
utes | -0.005 |
ya | -0.004 |
maid | -0.004 |
mber | -0.004 |
dolphins | -0.004 |
Token | mum |
Token ID | 25682 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Sue | +0.028 |
Kitty | +0.025 |
hy | +0.025 |
Kim | +0.023 |
Kim | +0.022 |
Neg logit contributions | |
utes | -0.031 |
maid | -0.030 |
ya | -0.029 |
dolphins | -0.029 |
crew | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
ya | +0.007 |
maid | +0.006 |
dolphins | +0.006 |
utes | +0.006 |
isha | +0.006 |
Neg logit contributions | |
Sue | -0.004 |
Kitty | -0.004 |
hy | -0.004 |
Kim | -0.004 |
Kim | -0.004 |
Token | other |
Token ID | 584 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
utes | +0.034 |
ub | +0.032 |
maid | +0.031 |
mber | +0.031 |
ya | +0.030 |
Neg logit contributions | |
Sue | -0.031 |
Kitty | -0.026 |
Tim | -0.024 |
She | -0.023 |
Amy | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
utes | +0.059 |
ya | +0.058 |
dolphins | +0.057 |
maid | +0.057 |
ub | +0.055 |
Neg logit contributions | |
Sue | -0.040 |
Kitty | -0.034 |
Kim | -0.032 |
hy | -0.031 |
Tim | -0.031 |
Token | After |
Token ID | 2293 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
Sue | +0.011 |
hy | +0.009 |
Kitty | +0.009 |
Kim | +0.008 |
Kim | +0.008 |
Neg logit contributions | |
utes | -0.024 |
ya | -0.023 |
dolphins | -0.022 |
maid | -0.022 |
mber | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Sue | +0.001 |
hy | +0.001 |
Kitty | +0.001 |
Kim | +0.001 |
hetically | +0.001 |
Neg logit contributions | |
dolphins | -0.002 |
utes | -0.002 |
ya | -0.002 |
crew | -0.002 |
dolphin | -0.002 |
Token | few |
Token ID | 1178 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Sue | +0.051 |
Kitty | +0.044 |
lick | +0.041 |
shake | +0.040 |
hy | +0.040 |
Neg logit contributions | |
utes | -0.080 |
eds | -0.074 |
maid | -0.073 |
targets | -0.073 |
beings | -0.072 |
Token | moments |
Token ID | 7188 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
Sue | +0.082 |
Kitty | +0.075 |
Kim | +0.075 |
hy | +0.074 |
Tim | +0.073 |
Neg logit contributions | |
ya | -0.056 |
dolphins | -0.055 |
mber | -0.051 |
utes | -0.050 |
fish | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Sue | +0.089 |
hy | +0.089 |
bleed | +0.086 |
blond | +0.086 |
Kim | +0.085 |
Neg logit contributions | |
dolphins | -0.123 |
ub | -0.122 |
ya | -0.121 |
utes | -0.118 |
fish | -0.117 |
Token | the |
Token ID | 262 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
Sue | +0.004 |
hy | +0.004 |
Kitty | +0.004 |
Kim | +0.004 |
blond | +0.003 |
Neg logit contributions | |
dolphins | -0.008 |
ya | -0.008 |
utes | -0.008 |
maid | -0.008 |
mber | -0.007 |
Token | dragon |
Token ID | 10441 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Sue | +0.026 |
Kitty | +0.022 |
hy | +0.022 |
Tim | +0.021 |
She | +0.021 |
Neg logit contributions | |
utes | -0.020 |
ub | -0.018 |
ya | -0.017 |
asper | -0.017 |
mber | -0.017 |
Token | bent |
Token ID | 17157 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
utes | +0.008 |
ya | +0.008 |
maid | +0.008 |
mber | +0.008 |
dolphins | +0.008 |
Neg logit contributions | |
Sue | -0.006 |
Kitty | -0.005 |
hy | -0.005 |
Kim | -0.005 |
Tim | -0.005 |
Token | down |
Token ID | 866 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
Sue | +0.014 |
hy | +0.013 |
Kitty | +0.012 |
� | +0.012 |
blond | +0.011 |
Neg logit contributions | |
maid | -0.016 |
utes | -0.016 |
ya | -0.016 |
dolphins | -0.016 |
fish | -0.015 |