Token | have |
Token ID | 423 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
brothers | +0.011 |
chambers | +0.010 |
mun | +0.009 |
promises | +0.009 |
more | +0.009 |
Neg logit contributions | |
tha | -0.024 |
flake | -0.024 |
icol | -0.024 |
iya | -0.023 |
essa | -0.023 |
Token | fun |
Token ID | 1257 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
brothers | +0.006 |
more | +0.005 |
friends | +0.005 |
chambers | +0.005 |
chores | +0.004 |
Neg logit contributions | |
flake | -0.023 |
tha | -0.022 |
ich | -0.021 |
icol | -0.021 |
AP | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
brothers | +0.010 |
more | +0.009 |
friends | +0.009 |
of | +0.009 |
questions | +0.007 |
Neg logit contributions | |
tha | -0.028 |
icol | -0.027 |
iya | -0.027 |
OW | -0.026 |
essa | -0.026 |
Token | my |
Token ID | 616 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
flake | +0.015 |
icol | +0.015 |
tha | +0.014 |
iya | +0.014 |
OW | +0.014 |
Neg logit contributions | |
brothers | -0.007 |
chambers | -0.005 |
friends | -0.005 |
more | -0.005 |
promises | -0.005 |
Token | d |
Token ID | 288 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
tha | +0.092 |
flake | +0.092 |
icol | +0.090 |
enda | +0.088 |
AR | +0.087 |
Neg logit contributions | |
brothers | -0.060 |
friends | -0.052 |
chambers | -0.047 |
questions | -0.046 |
promises | -0.046 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
icol | +0.035 |
tha | +0.034 |
flake | +0.033 |
peac | +0.033 |
iya | +0.032 |
Neg logit contributions | |
brothers | -0.023 |
ins | -0.021 |
of | -0.021 |
chambers | -0.020 |
questions | -0.019 |
Token | ings |
Token ID | 654 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
tha | +0.160 |
flake | +0.156 |
icol | +0.155 |
peac | +0.153 |
iya | +0.150 |
Neg logit contributions | |
brothers | -0.224 |
chambers | -0.210 |
mun | -0.207 |
promises | -0.203 |
friends | -0.196 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
icol | +0.017 |
tha | +0.016 |
iya | +0.015 |
flake | +0.015 |
OW | +0.015 |
Neg logit contributions | |
of | -0.013 |
brothers | -0.013 |
more | -0.011 |
mun | -0.011 |
chambers | -0.011 |
Token | she |
Token ID | 673 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
flake | +0.081 |
tha | +0.078 |
icol | +0.077 |
iya | +0.075 |
peac | +0.074 |
Neg logit contributions | |
brothers | -0.037 |
chambers | -0.034 |
mun | -0.032 |
promises | -0.030 |
more | -0.029 |
Token | asks |
Token ID | 7893 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
chambers | +0.032 |
mun | +0.031 |
brothers | +0.030 |
ins | +0.029 |
ways | +0.027 |
Neg logit contributions | |
tha | -0.045 |
essa | -0.044 |
la | -0.044 |
peac | -0.044 |
iya | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
chambers | +0.003 |
brothers | +0.003 |
mun | +0.003 |
promises | +0.003 |
goals | +0.002 |
Neg logit contributions | |
tha | -0.005 |
flake | -0.004 |
essa | -0.004 |
peac | -0.004 |
iya | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
tha | +0.035 |
flake | +0.035 |
peac | +0.034 |
icol | +0.034 |
iya | +0.033 |
Neg logit contributions | |
brothers | -0.007 |
chambers | -0.006 |
mun | -0.005 |
more | -0.005 |
promises | -0.005 |
Token | Santa |
Token ID | 8909 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
tha | +0.052 |
flake | +0.051 |
iya | +0.049 |
peac | +0.049 |
essa | +0.048 |
Neg logit contributions | |
brothers | -0.037 |
chambers | -0.036 |
mun | -0.035 |
promises | -0.032 |
ins | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
flake | +0.080 |
tha | +0.078 |
iya | +0.073 |
essa | +0.072 |
peac | +0.071 |
Neg logit contributions | |
brothers | -0.074 |
chambers | -0.073 |
mun | -0.071 |
promises | -0.067 |
goals | -0.067 |
Token | his |
Token ID | 465 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
tha | +0.052 |
flake | +0.051 |
peac | +0.050 |
iya | +0.050 |
icol | +0.050 |
Neg logit contributions | |
brothers | -0.026 |
mun | -0.025 |
chambers | -0.025 |
promises | -0.022 |
ins | -0.022 |
Token | re |
Token ID | 302 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
tha | +0.050 |
flake | +0.049 |
icol | +0.048 |
iya | +0.047 |
peac | +0.047 |
Neg logit contributions | |
brothers | -0.029 |
chambers | -0.027 |
mun | -0.025 |
promises | -0.025 |
more | -0.023 |
Token | ind |
Token ID | 521 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
icol | +0.039 |
flake | +0.037 |
tha | +0.036 |
storm | +0.036 |
peac | +0.035 |
Neg logit contributions | |
brothers | -0.075 |
promises | -0.070 |
chambers | -0.070 |
ins | -0.069 |
mun | -0.069 |
Token | eer |
Token ID | 28153 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
icol | +0.195 |
tha | +0.194 |
flake | +0.191 |
peac | +0.186 |
AR | +0.180 |
Neg logit contributions | |
brothers | -0.192 |
chambers | -0.181 |
mun | -0.171 |
promises | -0.167 |
questions | -0.164 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
flake | +0.097 |
tha | +0.096 |
peac | +0.092 |
iya | +0.091 |
icol | +0.090 |
Neg logit contributions | |
brothers | -0.041 |
chambers | -0.039 |
mun | -0.039 |
promises | -0.035 |
goals | -0.032 |
Token | They |
Token ID | 1119 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
tha | +0.030 |
flake | +0.030 |
icol | +0.029 |
iya | +0.028 |
essa | +0.028 |
Neg logit contributions | |
brothers | -0.019 |
chambers | -0.018 |
mun | -0.018 |
promises | -0.017 |
more | -0.016 |
Token | hope |
Token ID | 2911 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
tha | +0.034 |
flake | +0.034 |
icol | +0.032 |
iya | +0.032 |
peac | +0.032 |
Neg logit contributions | |
brothers | -0.018 |
chambers | -0.017 |
mun | -0.016 |
promises | -0.015 |
more | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
flake | +0.042 |
tha | +0.041 |
icol | +0.040 |
peac | +0.039 |
AR | +0.039 |
Neg logit contributions | |
brothers | -0.030 |
chambers | -0.028 |
more | -0.028 |
promises | -0.027 |
mun | -0.027 |
Token | let |
Token ID | 1309 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
tha | +0.017 |
icol | +0.017 |
flake | +0.017 |
iya | +0.017 |
essa | +0.017 |
Neg logit contributions | |
brothers | -0.008 |
chambers | -0.007 |
mun | -0.007 |
more | -0.006 |
promises | -0.006 |
Token | out |
Token ID | 503 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
flake | +0.018 |
tha | +0.018 |
icol | +0.017 |
iya | +0.017 |
peac | +0.017 |
Neg logit contributions | |
brothers | -0.009 |
chambers | -0.008 |
mun | -0.008 |
promises | -0.008 |
more | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
brothers | +0.029 |
mun | +0.029 |
chambers | +0.028 |
promises | +0.026 |
goals | +0.025 |
Neg logit contributions | |
flake | -0.039 |
tha | -0.038 |
peac | -0.038 |
icol | -0.037 |
iya | -0.036 |
Token | big |
Token ID | 1263 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
brothers | +0.025 |
chambers | +0.023 |
mun | +0.023 |
promises | +0.022 |
goals | +0.020 |
Neg logit contributions | |
flake | -0.039 |
tha | -0.039 |
icol | -0.038 |
peac | -0.037 |
iya | -0.037 |
Token | sn |
Token ID | 3013 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
tha | +0.010 |
flake | +0.010 |
la | +0.010 |
iya | +0.010 |
essa | +0.010 |
Neg logit contributions | |
brothers | -0.006 |
chambers | -0.005 |
more | -0.005 |
promises | -0.005 |
mun | -0.005 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
tha | +0.017 |
flake | +0.016 |
icol | +0.016 |
iya | +0.015 |
peac | +0.015 |
Neg logit contributions | |
brothers | -0.019 |
chambers | -0.018 |
mun | -0.017 |
promises | -0.017 |
more | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
tha | +0.224 |
flake | +0.220 |
icol | +0.216 |
iya | +0.215 |
peac | +0.215 |
Neg logit contributions | |
brothers | -0.153 |
chambers | -0.141 |
mun | -0.136 |
promises | -0.130 |
more | -0.126 |
Token | the |
Token ID | 262 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
tha | +0.004 |
flake | +0.004 |
icol | +0.004 |
peac | +0.004 |
iya | +0.004 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
mun | -0.002 |
promises | -0.002 |
goals | -0.002 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
flake | +0.026 |
tha | +0.025 |
peac | +0.024 |
iya | +0.023 |
icol | +0.023 |
Neg logit contributions | |
brothers | -0.023 |
chambers | -0.022 |
mun | -0.021 |
promises | -0.020 |
goals | -0.019 |
Token | knew |
Token ID | 2993 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
flake | +0.012 |
tha | +0.012 |
peac | +0.012 |
icol | +0.011 |
iya | +0.011 |
Neg logit contributions | |
brothers | -0.009 |
chambers | -0.008 |
mun | -0.008 |
promises | -0.008 |
goals | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
tha | +0.035 |
flake | +0.035 |
icol | +0.033 |
iya | +0.033 |
peac | +0.033 |
Neg logit contributions | |
brothers | -0.021 |
chambers | -0.020 |
mun | -0.019 |
promises | -0.018 |
more | -0.017 |
Token | Spot |
Token ID | 32565 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
brothers | +0.018 |
chambers | +0.018 |
mun | +0.017 |
promises | +0.016 |
questions | +0.016 |
Neg logit contributions | |
tha | -0.019 |
flake | -0.019 |
iya | -0.018 |
peac | -0.017 |
icol | -0.017 |
Token | grow |
Token ID | 1663 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
brothers | +0.013 |
chambers | +0.012 |
mun | +0.011 |
promises | +0.010 |
ins | +0.010 |
Neg logit contributions | |
flake | -0.023 |
tha | -0.023 |
icol | -0.023 |
iya | -0.022 |
peac | -0.022 |
Token | ls |
Token ID | 7278 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
flake | +0.003 |
la | +0.003 |
tha | +0.003 |
ller | +0.003 |
rus | +0.003 |
Neg logit contributions | |
chambers | -0.004 |
mun | -0.004 |
brothers | -0.003 |
promises | -0.003 |
importantly | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
flake | +0.012 |
tha | +0.011 |
peac | +0.011 |
icol | +0.011 |
la | +0.011 |
Neg logit contributions | |
mun | -0.011 |
chambers | -0.011 |
brothers | -0.011 |
ins | -0.010 |
chores | -0.010 |
Token | sn |
Token ID | 3013 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
icol | +0.009 |
tha | +0.009 |
flake | +0.009 |
peac | +0.009 |
da | +0.008 |
Neg logit contributions | |
brothers | -0.006 |
chambers | -0.006 |
ins | -0.006 |
mun | -0.006 |
importantly | -0.005 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
tha | +0.026 |
flake | +0.026 |
icol | +0.025 |
iya | +0.024 |
peac | +0.024 |
Neg logit contributions | |
brothers | -0.028 |
chambers | -0.027 |
mun | -0.026 |
promises | -0.025 |
more | -0.024 |
Token | s |
Token ID | 82 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
flake | +0.191 |
tha | +0.187 |
icol | +0.176 |
essa | +0.174 |
iya | +0.173 |
Neg logit contributions | |
chambers | -0.175 |
brothers | -0.174 |
mun | -0.168 |
promises | -0.161 |
more | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
tha | +0.031 |
flake | +0.031 |
icol | +0.030 |
iya | +0.029 |
peac | +0.029 |
Neg logit contributions | |
brothers | -0.025 |
chambers | -0.024 |
mun | -0.023 |
promises | -0.022 |
more | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
icol | +0.021 |
tha | +0.021 |
flake | +0.020 |
iya | +0.020 |
peac | +0.019 |
Neg logit contributions | |
brothers | -0.010 |
mun | -0.010 |
chambers | -0.010 |
promises | -0.009 |
ins | -0.009 |
Token | tries |
Token ID | 8404 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
flake | +0.012 |
tha | +0.012 |
icol | +0.012 |
peac | +0.012 |
iya | +0.011 |
Neg logit contributions | |
brothers | -0.007 |
chambers | -0.006 |
mun | -0.006 |
promises | -0.005 |
ins | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
brothers | +0.042 |
chambers | +0.040 |
mun | +0.039 |
promises | +0.038 |
more | +0.037 |
Neg logit contributions | |
tha | -0.041 |
flake | -0.041 |
icol | -0.039 |
iya | -0.039 |
peac | -0.038 |
Token | have |
Token ID | 423 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
brothers | +0.008 |
chambers | +0.007 |
promises | +0.006 |
mun | +0.006 |
more | +0.006 |
Neg logit contributions | |
tha | -0.018 |
flake | -0.018 |
icol | -0.017 |
iya | -0.017 |
essa | -0.017 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
more | +0.003 |
friends | +0.003 |
brothers | +0.002 |
cookies | +0.002 |
chambers | +0.002 |
Neg logit contributions | |
flake | -0.014 |
tha | -0.014 |
ich | -0.013 |
icol | -0.013 |
essa | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
brothers | +0.008 |
more | +0.008 |
friends | +0.007 |
of | +0.007 |
chambers | +0.006 |
Neg logit contributions | |
icol | -0.018 |
tha | -0.018 |
essa | -0.018 |
iya | -0.018 |
OW | -0.017 |
Token | my |
Token ID | 616 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
flake | +0.004 |
icol | +0.004 |
tha | +0.004 |
iya | +0.004 |
OW | +0.004 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
more | -0.002 |
friends | -0.002 |
promises | -0.002 |
Token | d |
Token ID | 288 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
AR | +0.092 |
flake | +0.091 |
da | +0.088 |
icol | +0.088 |
storm | +0.088 |
Neg logit contributions | |
brothers | -0.047 |
friends | -0.046 |
promises | -0.038 |
questions | -0.037 |
more | -0.036 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
icol | +0.037 |
tha | +0.037 |
flake | +0.036 |
iya | +0.035 |
da | +0.034 |
Neg logit contributions | |
of | -0.019 |
brothers | -0.018 |
ins | -0.018 |
chambers | -0.015 |
oll | -0.015 |
Token | ings |
Token ID | 654 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
tha | +0.163 |
icol | +0.162 |
peac | +0.162 |
flake | +0.159 |
iya | +0.156 |
Neg logit contributions | |
brothers | -0.205 |
mun | -0.189 |
chambers | -0.187 |
promises | -0.185 |
friends | -0.183 |
Token | ?" |
Token ID | 1701 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
icol | +0.016 |
tha | +0.015 |
iya | +0.014 |
flake | +0.014 |
peac | +0.014 |
Neg logit contributions | |
of | -0.015 |
brothers | -0.014 |
more | -0.014 |
mun | -0.013 |
chambers | -0.013 |
Token | Their |
Token ID | 5334 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
flake | +0.066 |
tha | +0.063 |
icol | +0.063 |
iya | +0.060 |
OW | +0.060 |
Neg logit contributions | |
brothers | -0.039 |
chambers | -0.035 |
mun | -0.033 |
more | -0.032 |
promises | -0.032 |
Token | mother |
Token ID | 2802 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
brothers | +0.004 |
friends | +0.003 |
chambers | +0.003 |
promises | +0.003 |
questions | +0.003 |
Neg logit contributions | |
flake | -0.006 |
storm | -0.005 |
tha | -0.005 |
da | -0.005 |
icol | -0.005 |
Token | asked |
Token ID | 1965 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
goals | +0.008 |
chambers | +0.008 |
chores | +0.008 |
brothers | +0.007 |
ways | +0.007 |
Neg logit contributions | |
tha | -0.006 |
flake | -0.006 |
la | -0.006 |
peac | -0.006 |
da | -0.005 |
Token | We |
Token ID | 1135 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
brothers | +0.003 |
mun | +0.003 |
chambers | +0.003 |
promises | +0.002 |
more | +0.002 |
Neg logit contributions | |
tha | -0.004 |
icol | -0.004 |
flake | -0.004 |
iya | -0.004 |
peac | -0.004 |
Token | know |
Token ID | 760 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
brothers | +0.008 |
mun | +0.007 |
promises | +0.007 |
chambers | +0.007 |
more | +0.007 |
Neg logit contributions | |
tha | -0.016 |
flake | -0.016 |
icol | -0.016 |
iya | -0.015 |
peac | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
brothers | +0.044 |
chambers | +0.041 |
more | +0.040 |
mun | +0.039 |
promises | +0.039 |
Neg logit contributions | |
flake | -0.062 |
tha | -0.060 |
icol | -0.058 |
iya | -0.057 |
peac | -0.057 |
Token | my |
Token ID | 616 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
flake | +0.015 |
tha | +0.015 |
icol | +0.014 |
iya | +0.014 |
peac | +0.014 |
Neg logit contributions | |
brothers | -0.012 |
chambers | -0.011 |
mun | -0.011 |
promises | -0.011 |
more | -0.010 |
Token | d |
Token ID | 288 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
tha | +0.074 |
flake | +0.074 |
iya | +0.072 |
icol | +0.071 |
peac | +0.071 |
Neg logit contributions | |
brothers | -0.032 |
chambers | -0.028 |
promises | -0.027 |
friends | -0.026 |
mun | -0.026 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
tha | +0.017 |
flake | +0.017 |
icol | +0.016 |
iya | +0.016 |
peac | +0.016 |
Neg logit contributions | |
brothers | -0.013 |
chambers | -0.012 |
ins | -0.011 |
of | -0.011 |
mun | -0.011 |
Token | ings |
Token ID | 654 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
tha | +0.151 |
flake | +0.147 |
icol | +0.145 |
peac | +0.145 |
iya | +0.142 |
Neg logit contributions | |
brothers | -0.218 |
chambers | -0.204 |
mun | -0.204 |
promises | -0.200 |
friends | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
tha | +0.000 |
icol | +0.000 |
flake | +0.000 |
iya | +0.000 |
peac | +0.000 |
Neg logit contributions | |
brothers | -0.000 |
mun | -0.000 |
more | -0.000 |
chambers | -0.000 |
of | -0.000 |
Token | We |
Token ID | 775 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
flake | +0.006 |
tha | +0.006 |
iya | +0.006 |
peac | +0.006 |
essa | +0.006 |
Neg logit contributions | |
brothers | -0.004 |
chambers | -0.004 |
promises | -0.003 |
mun | -0.003 |
goals | -0.003 |
Token | miss |
Token ID | 2051 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
brothers | +0.004 |
promises | +0.003 |
friends | +0.003 |
mun | +0.003 |
more | +0.003 |
Neg logit contributions | |
icol | -0.010 |
tha | -0.010 |
flake | -0.009 |
ich | -0.009 |
iya | -0.009 |
Token | them |
Token ID | 606 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
flake | +0.047 |
icol | +0.045 |
storm | +0.043 |
opter | +0.043 |
ANG | +0.043 |
Neg logit contributions | |
more | -0.027 |
brothers | -0.026 |
friends | -0.026 |
questions | -0.024 |
promises | -0.024 |
Token | 'm |
Token ID | 1101 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
brothers | +0.003 |
mun | +0.003 |
promises | +0.003 |
chambers | +0.003 |
more | +0.002 |
Neg logit contributions | |
tha | -0.006 |
flake | -0.006 |
icol | -0.006 |
ich | -0.006 |
iya | -0.006 |
Token | sorry |
Token ID | 7926 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
flake | +0.079 |
icol | +0.076 |
tha | +0.072 |
storm | +0.072 |
OW | +0.072 |
Neg logit contributions | |
brothers | -0.023 |
more | -0.018 |
friends | -0.016 |
promises | -0.014 |
chambers | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
brothers | +0.017 |
chambers | +0.015 |
more | +0.015 |
friends | +0.015 |
promises | +0.014 |
Neg logit contributions | |
flake | -0.032 |
tha | -0.031 |
icol | -0.030 |
peac | -0.030 |
iya | -0.030 |
Token | my |
Token ID | 616 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
flake | +0.016 |
icol | +0.015 |
tha | +0.015 |
peac | +0.014 |
storm | +0.014 |
Neg logit contributions | |
brothers | -0.010 |
more | -0.009 |
promises | -0.009 |
friends | -0.008 |
chambers | -0.008 |
Token | d |
Token ID | 288 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
tha | +0.069 |
flake | +0.069 |
iya | +0.068 |
peac | +0.067 |
icol | +0.065 |
Neg logit contributions | |
brothers | -0.031 |
chambers | -0.027 |
friends | -0.027 |
promises | -0.027 |
mun | -0.025 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
tha | +0.012 |
flake | +0.012 |
icol | +0.011 |
iya | +0.011 |
peac | +0.011 |
Neg logit contributions | |
brothers | -0.009 |
chambers | -0.008 |
of | -0.008 |
ins | -0.008 |
mun | -0.007 |
Token | ings |
Token ID | 654 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
tha | +0.156 |
peac | +0.153 |
icol | +0.152 |
flake | +0.149 |
iya | +0.147 |
Neg logit contributions | |
brothers | -0.207 |
mun | -0.193 |
chambers | -0.191 |
promises | -0.188 |
friends | -0.183 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
brothers | +0.001 |
of | +0.001 |
more | +0.001 |
mun | +0.000 |
chambers | +0.000 |
Neg logit contributions | |
tha | -0.002 |
icol | -0.002 |
flake | -0.002 |
iya | -0.002 |
peac | -0.002 |
Token | The |
Token ID | 383 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
flake | +0.007 |
tha | +0.007 |
iya | +0.007 |
peac | +0.007 |
icol | +0.007 |
Neg logit contributions | |
brothers | -0.006 |
chambers | -0.006 |
promises | -0.006 |
mun | -0.005 |
more | -0.005 |
Token | tornado |
Token ID | 33718 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
tha | +0.033 |
flake | +0.033 |
iya | +0.032 |
icol | +0.031 |
essa | +0.031 |
Neg logit contributions | |
brothers | -0.016 |
chambers | -0.015 |
promises | -0.014 |
more | -0.014 |
friends | -0.013 |
Token | took |
Token ID | 1718 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
icol | +0.069 |
tha | +0.068 |
iya | +0.068 |
flake | +0.067 |
essa | +0.067 |
Neg logit contributions | |
brothers | -0.027 |
promises | -0.025 |
mun | -0.025 |
chambers | -0.023 |
more | -0.023 |
Token | perfect |
Token ID | 2818 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
tha | +0.022 |
flake | +0.022 |
icol | +0.021 |
iya | +0.021 |
peac | +0.021 |
Neg logit contributions | |
brothers | -0.014 |
chambers | -0.013 |
mun | -0.012 |
promises | -0.012 |
more | -0.011 |
Token | fish |
Token ID | 5916 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
flake | +0.037 |
icol | +0.036 |
tha | +0.036 |
OW | +0.035 |
da | +0.035 |
Neg logit contributions | |
brothers | -0.019 |
friends | -0.018 |
more | -0.015 |
of | -0.015 |
sisters | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
icol | +0.045 |
tha | +0.043 |
flake | +0.042 |
iya | +0.042 |
enda | +0.042 |
Neg logit contributions | |
brothers | -0.024 |
friends | -0.021 |
of | -0.021 |
more | -0.020 |
chambers | -0.020 |
Token | my |
Token ID | 616 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
flake | +0.025 |
tha | +0.025 |
icol | +0.024 |
iya | +0.024 |
peac | +0.023 |
Neg logit contributions | |
brothers | -0.014 |
chambers | -0.013 |
mun | -0.012 |
promises | -0.012 |
more | -0.011 |
Token | d |
Token ID | 288 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
tha | +0.076 |
enda | +0.074 |
flake | +0.074 |
storm | +0.073 |
la | +0.071 |
Neg logit contributions | |
brothers | -0.044 |
friends | -0.042 |
more | -0.035 |
promises | -0.034 |
goals | -0.033 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
tha | +0.019 |
flake | +0.018 |
icol | +0.017 |
storm | +0.017 |
iya | +0.016 |
Neg logit contributions | |
brothers | -0.013 |
of | -0.013 |
ins | -0.012 |
goals | -0.011 |
chambers | -0.011 |
Token | ings |
Token ID | 654 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
tha | +0.155 |
flake | +0.151 |
icol | +0.148 |
peac | +0.148 |
iya | +0.145 |
Neg logit contributions | |
brothers | -0.210 |
chambers | -0.195 |
mun | -0.192 |
promises | -0.189 |
friends | -0.185 |
Token | ," |
Token ID | 553 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
icol | +0.002 |
tha | +0.002 |
iya | +0.002 |
flake | +0.002 |
peac | +0.002 |
Neg logit contributions | |
of | -0.001 |
brothers | -0.001 |
more | -0.001 |
chambers | -0.000 |
mun | -0.000 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
tha | +0.017 |
flake | +0.017 |
peac | +0.016 |
iya | +0.016 |
icol | +0.016 |
Neg logit contributions | |
chambers | -0.015 |
brothers | -0.015 |
mun | -0.014 |
promises | -0.013 |
ins | -0.013 |
Token | says |
Token ID | 1139 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
chambers | +0.046 |
mun | +0.042 |
goals | +0.041 |
brothers | +0.041 |
chores | +0.040 |
Neg logit contributions | |
essa | -0.054 |
tha | -0.054 |
la | -0.053 |
flake | -0.052 |
iya | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
chambers | +0.025 |
brothers | +0.024 |
mun | +0.023 |
goals | +0.022 |
exercises | +0.020 |
Neg logit contributions | |
tha | -0.030 |
flake | -0.029 |
essa | -0.028 |
work | -0.028 |
icol | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
flake | +0.068 |
tha | +0.067 |
OW | +0.064 |
iya | +0.064 |
essa | +0.064 |
Neg logit contributions | |
brothers | -0.031 |
mun | -0.027 |
chambers | -0.026 |
friends | -0.026 |
more | -0.026 |
Token | Rudolph |
Token ID | 48684 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
brothers | +0.005 |
chambers | +0.004 |
friends | +0.004 |
mun | +0.004 |
more | +0.004 |
Neg logit contributions | |
flake | -0.010 |
tha | -0.009 |
icol | -0.009 |
peac | -0.009 |
essa | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
icol | +0.084 |
tha | +0.083 |
AR | +0.082 |
storm | +0.081 |
flake | +0.081 |
Neg logit contributions | |
brothers | -0.025 |
friends | -0.020 |
's | -0.018 |
more | -0.018 |
mun | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
tha | +0.010 |
flake | +0.010 |
icol | +0.010 |
iya | +0.010 |
peac | +0.010 |
Neg logit contributions | |
brothers | -0.003 |
chambers | -0.003 |
mun | -0.003 |
promises | -0.003 |
more | -0.002 |
Token | re |
Token ID | 302 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
flake | +0.018 |
tha | +0.018 |
icol | +0.018 |
essa | +0.017 |
iya | +0.017 |
Neg logit contributions | |
brothers | -0.007 |
friends | -0.006 |
chambers | -0.005 |
promises | -0.005 |
more | -0.005 |
Token | ind |
Token ID | 521 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
icol | +0.037 |
flake | +0.037 |
storm | +0.034 |
tha | +0.034 |
peac | +0.032 |
Neg logit contributions | |
brothers | -0.072 |
friends | -0.066 |
chambers | -0.065 |
mun | -0.064 |
promises | -0.064 |
Token | eer |
Token ID | 28153 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
icol | +0.205 |
tha | +0.199 |
flake | +0.196 |
AR | +0.193 |
peac | +0.191 |
Neg logit contributions | |
brothers | -0.173 |
chambers | -0.158 |
mun | -0.149 |
friends | -0.146 |
questions | -0.142 |
Token | friends |
Token ID | 2460 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
icol | +0.095 |
tha | +0.094 |
flake | +0.093 |
essa | +0.090 |
AR | +0.089 |
Neg logit contributions | |
brothers | -0.036 |
friends | -0.030 |
mun | -0.030 |
chambers | -0.029 |
more | -0.028 |
Token | were |
Token ID | 547 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
icol | +0.068 |
flake | +0.066 |
tha | +0.066 |
AR | +0.065 |
ich | +0.064 |
Neg logit contributions | |
brothers | -0.022 |
mun | -0.019 |
friends | -0.018 |
more | -0.017 |
of | -0.016 |
Token | all |
Token ID | 477 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
flake | +0.057 |
icol | +0.056 |
tha | +0.056 |
essa | +0.054 |
peac | +0.053 |
Neg logit contributions | |
brothers | -0.027 |
friends | -0.023 |
more | -0.023 |
mun | -0.021 |
chambers | -0.020 |
Token | out |
Token ID | 503 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
tha | +0.064 |
flake | +0.064 |
icol | +0.062 |
iya | +0.061 |
peac | +0.061 |
Neg logit contributions | |
brothers | -0.038 |
chambers | -0.036 |
mun | -0.035 |
promises | -0.033 |
more | -0.031 |
Token | " |
Token ID | 1 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
flake | +0.019 |
tha | +0.018 |
icol | +0.018 |
peac | +0.017 |
iya | +0.017 |
Neg logit contributions | |
brothers | -0.013 |
chambers | -0.013 |
mun | -0.012 |
promises | -0.012 |
more | -0.011 |
Token | Hello |
Token ID | 15496 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
tha | +0.053 |
flake | +0.053 |
icol | +0.051 |
peac | +0.050 |
iya | +0.050 |
Neg logit contributions | |
brothers | -0.042 |
chambers | -0.040 |
mun | -0.039 |
more | -0.037 |
promises | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
flake | +0.070 |
icol | +0.068 |
peac | +0.067 |
storm | +0.066 |
tha | +0.066 |
Neg logit contributions | |
brothers | -0.031 |
more | -0.028 |
chambers | -0.027 |
friends | -0.027 |
mun | -0.026 |
Token | my |
Token ID | 616 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
brothers | +0.014 |
chambers | +0.014 |
mun | +0.013 |
promises | +0.013 |
more | +0.012 |
Neg logit contributions | |
tha | -0.016 |
flake | -0.016 |
icol | -0.015 |
iya | -0.015 |
peac | -0.015 |
Token | d |
Token ID | 288 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
flake | +0.058 |
tha | +0.057 |
peac | +0.056 |
storm | +0.054 |
iya | +0.054 |
Neg logit contributions | |
brothers | -0.035 |
chambers | -0.029 |
friends | -0.029 |
more | -0.029 |
promises | -0.028 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
tha | +0.005 |
flake | +0.005 |
peac | +0.004 |
icol | +0.004 |
iya | +0.004 |
Neg logit contributions | |
brothers | -0.003 |
chambers | -0.003 |
of | -0.003 |
ins | -0.003 |
questions | -0.003 |
Token | ings |
Token ID | 654 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
tha | +0.147 |
peac | +0.145 |
icol | +0.143 |
flake | +0.142 |
iya | +0.139 |
Neg logit contributions | |
brothers | -0.208 |
chambers | -0.195 |
mun | -0.194 |
promises | -0.189 |
friends | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
brothers | +0.003 |
of | +0.003 |
more | +0.003 |
mun | +0.003 |
chambers | +0.003 |
Neg logit contributions | |
tha | -0.005 |
icol | -0.005 |
flake | -0.005 |
peac | -0.005 |
iya | -0.005 |
Token | I |
Token ID | 314 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
brothers | +0.008 |
chambers | +0.008 |
mun | +0.007 |
questions | +0.007 |
promises | +0.007 |
Neg logit contributions | |
flake | -0.012 |
tha | -0.012 |
iya | -0.011 |
peac | -0.011 |
icol | -0.011 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
brothers | +0.000 |
mun | +0.000 |
chambers | +0.000 |
promises | +0.000 |
more | +0.000 |
Neg logit contributions | |
tha | -0.001 |
icol | -0.001 |
flake | -0.001 |
iya | -0.001 |
essa | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
flake | +0.082 |
icol | +0.077 |
OW | +0.074 |
tha | +0.073 |
opter | +0.073 |
Neg logit contributions | |
brothers | -0.039 |
friends | -0.033 |
more | -0.033 |
sleepy | -0.031 |
of | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
tha | +0.028 |
flake | +0.028 |
icol | +0.027 |
iya | +0.026 |
peac | +0.026 |
Neg logit contributions | |
brothers | -0.014 |
chambers | -0.013 |
mun | -0.013 |
promises | -0.012 |
more | -0.011 |
Token | One |
Token ID | 3198 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
flake | +0.036 |
tha | +0.035 |
peac | +0.034 |
iya | +0.034 |
icol | +0.033 |
Neg logit contributions | |
brothers | -0.027 |
chambers | -0.025 |
mun | -0.025 |
promises | -0.024 |
more | -0.022 |
Token | day |
Token ID | 1110 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
flake | +0.029 |
peac | +0.028 |
tha | +0.026 |
iya | +0.026 |
storm | +0.025 |
Neg logit contributions | |
mun | -0.046 |
chambers | -0.045 |
ins | -0.044 |
promises | -0.043 |
goals | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
brothers | +0.012 |
chambers | +0.012 |
mun | +0.011 |
promises | +0.011 |
more | +0.010 |
Neg logit contributions | |
tha | -0.018 |
flake | -0.018 |
icol | -0.017 |
iya | -0.017 |
peac | -0.017 |
Token | mis |
Token ID | 2984 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
tha | +0.021 |
flake | +0.021 |
icol | +0.020 |
iya | +0.020 |
essa | +0.019 |
Neg logit contributions | |
brothers | -0.011 |
chambers | -0.010 |
mun | -0.009 |
more | -0.009 |
promises | -0.008 |
Token | chie |
Token ID | 3043 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
brothers | +0.054 |
chambers | +0.053 |
mun | +0.052 |
promises | +0.050 |
more | +0.050 |
Neg logit contributions | |
tha | -0.013 |
flake | -0.013 |
icol | -0.012 |
iya | -0.010 |
peac | -0.010 |
Token | vous |
Token ID | 31222 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
tha | +0.224 |
flake | +0.224 |
icol | +0.214 |
iya | +0.213 |
peac | +0.213 |
Neg logit contributions | |
brothers | -0.131 |
chambers | -0.124 |
mun | -0.119 |
promises | -0.114 |
more | -0.107 |
Token | monkey |
Token ID | 21657 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
tha | +0.012 |
flake | +0.011 |
la | +0.011 |
iya | +0.011 |
icol | +0.011 |
Neg logit contributions | |
brothers | -0.007 |
chambers | -0.006 |
mun | -0.006 |
friends | -0.006 |
more | -0.006 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
flake | +0.018 |
tha | +0.018 |
peac | +0.017 |
icol | +0.017 |
iya | +0.017 |
Neg logit contributions | |
brothers | -0.013 |
chambers | -0.012 |
mun | -0.011 |
promises | -0.011 |
goals | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
flake | +0.023 |
tha | +0.023 |
icol | +0.022 |
iya | +0.022 |
storm | +0.021 |
Neg logit contributions | |
brothers | -0.009 |
chambers | -0.008 |
mun | -0.008 |
more | -0.008 |
promises | -0.007 |
Token | bear |
Token ID | 6842 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
tha | +0.034 |
flake | +0.034 |
icol | +0.032 |
iya | +0.032 |
peac | +0.032 |
Neg logit contributions | |
brothers | -0.022 |
chambers | -0.021 |
mun | -0.020 |
promises | -0.019 |
more | -0.018 |
Token | Christmas |
Token ID | 6786 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
tha | +0.022 |
flake | +0.022 |
peac | +0.022 |
icol | +0.021 |
iya | +0.021 |
Neg logit contributions | |
brothers | -0.028 |
chambers | -0.027 |
mun | -0.027 |
promises | -0.026 |
goals | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
flake | +0.033 |
tha | +0.033 |
icol | +0.031 |
iya | +0.031 |
peac | +0.031 |
Neg logit contributions | |
brothers | -0.020 |
chambers | -0.019 |
mun | -0.018 |
promises | -0.017 |
goals | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
tha | +0.016 |
iya | +0.016 |
icol | +0.015 |
flake | +0.015 |
essa | +0.015 |
Neg logit contributions | |
chambers | -0.015 |
brothers | -0.015 |
mun | -0.014 |
ins | -0.014 |
promises | -0.014 |
Token | loved |
Token ID | 6151 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
tha | +0.021 |
flake | +0.021 |
icol | +0.020 |
iya | +0.020 |
peac | +0.020 |
Neg logit contributions | |
brothers | -0.014 |
chambers | -0.013 |
mun | -0.013 |
promises | -0.012 |
more | -0.011 |
Token | re |
Token ID | 302 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
tha | +0.039 |
flake | +0.039 |
icol | +0.036 |
iya | +0.036 |
peac | +0.036 |
Neg logit contributions | |
brothers | -0.046 |
chambers | -0.044 |
mun | -0.043 |
promises | -0.041 |
more | -0.040 |
Token | ind |
Token ID | 521 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
flake | +0.021 |
tha | +0.021 |
icol | +0.020 |
peac | +0.019 |
iya | +0.019 |
Neg logit contributions | |
brothers | -0.063 |
chambers | -0.061 |
mun | -0.060 |
promises | -0.059 |
more | -0.057 |
Token | eer |
Token ID | 28153 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
flake | +0.156 |
tha | +0.155 |
iya | +0.145 |
icol | +0.144 |
essa | +0.143 |
Neg logit contributions | |
brothers | -0.198 |
chambers | -0.192 |
mun | -0.188 |
promises | -0.183 |
more | -0.175 |
Token | . |
Token ID | 13 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
flake | +0.053 |
peac | +0.051 |
work | +0.051 |
la | +0.050 |
tha | +0.050 |
Neg logit contributions | |
chambers | -0.040 |
mun | -0.038 |
brothers | -0.038 |
promises | -0.036 |
cabinets | -0.036 |
Token | He |
Token ID | 679 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
flake | +0.007 |
tha | +0.007 |
icol | +0.007 |
iya | +0.007 |
peac | +0.006 |
Neg logit contributions | |
brothers | -0.004 |
chambers | -0.004 |
mun | -0.003 |
promises | -0.003 |
more | -0.003 |
Token | would |
Token ID | 561 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
tha | +0.008 |
flake | +0.008 |
icol | +0.008 |
AR | +0.008 |
peac | +0.008 |
Neg logit contributions | |
brothers | -0.004 |
chambers | -0.004 |
mun | -0.004 |
more | -0.004 |
promises | -0.004 |
Token | often |
Token ID | 1690 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
flake | +0.044 |
tha | +0.044 |
icol | +0.042 |
essa | +0.041 |
ich | +0.041 |
Neg logit contributions | |
brothers | -0.021 |
chambers | -0.019 |
mun | -0.019 |
more | -0.018 |
promises | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
tha | +0.013 |
flake | +0.013 |
icol | +0.013 |
iya | +0.012 |
peac | +0.012 |
Neg logit contributions | |
brothers | -0.007 |
chambers | -0.006 |
mun | -0.006 |
promises | -0.006 |
more | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
brothers | +0.007 |
chambers | +0.006 |
mun | +0.006 |
promises | +0.006 |
questions | +0.006 |
Neg logit contributions | |
flake | -0.011 |
tha | -0.011 |
iya | -0.010 |
icol | -0.010 |
peac | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
flake | +0.028 |
tha | +0.028 |
iya | +0.027 |
icol | +0.027 |
peac | +0.027 |
Neg logit contributions | |
chambers | -0.025 |
brothers | -0.024 |
mun | -0.024 |
promises | -0.023 |
questions | -0.022 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
tha | +0.011 |
flake | +0.011 |
icol | +0.010 |
iya | +0.010 |
peac | +0.010 |
Neg logit contributions | |
brothers | -0.006 |
chambers | -0.006 |
mun | -0.005 |
promises | -0.005 |
more | -0.005 |
Token | re |
Token ID | 302 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
brothers | +0.009 |
friends | +0.009 |
chambers | +0.007 |
of | +0.007 |
more | +0.007 |
Neg logit contributions | |
tha | -0.023 |
OW | -0.022 |
la | -0.022 |
flake | -0.022 |
enda | -0.022 |
Token | ind |
Token ID | 521 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
icol | +0.030 |
flake | +0.027 |
tha | +0.027 |
OW | +0.026 |
storm | +0.025 |
Neg logit contributions | |
brothers | -0.058 |
chambers | -0.056 |
mun | -0.055 |
ins | -0.053 |
friends | -0.053 |
Token | eer |
Token ID | 28153 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
tha | +0.178 |
icol | +0.178 |
flake | +0.174 |
peac | +0.168 |
iya | +0.164 |
Neg logit contributions | |
brothers | -0.180 |
chambers | -0.170 |
mun | -0.163 |
promises | -0.156 |
more | -0.154 |
Token | named |
Token ID | 3706 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
tha | +0.068 |
icol | +0.067 |
flake | +0.066 |
iya | +0.064 |
essa | +0.064 |
Neg logit contributions | |
brothers | -0.032 |
chambers | -0.028 |
mun | -0.028 |
more | -0.026 |
friends | -0.025 |
Token | Rudolph |
Token ID | 48684 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
flake | +0.009 |
storm | +0.008 |
icol | +0.008 |
peac | +0.008 |
tha | +0.008 |
Neg logit contributions | |
brothers | -0.006 |
his | -0.005 |
friends | -0.005 |
bears | -0.005 |
more | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
icol | +0.120 |
tha | +0.119 |
flake | +0.115 |
OW | +0.113 |
peac | +0.113 |
Neg logit contributions | |
brothers | -0.030 |
chambers | -0.022 |
mun | -0.020 |
friends | -0.019 |
more | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
tha | +0.004 |
flake | +0.004 |
peac | +0.004 |
OW | +0.004 |
icol | +0.004 |
Neg logit contributions | |
brothers | -0.005 |
chambers | -0.005 |
mun | -0.005 |
promises | -0.005 |
more | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
brothers | +0.021 |
chambers | +0.018 |
mun | +0.018 |
friends | +0.017 |
more | +0.017 |
Neg logit contributions | |
tha | -0.038 |
flake | -0.036 |
icol | -0.036 |
iya | -0.035 |
essa | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
tha | +0.005 |
flake | +0.005 |
icol | +0.005 |
iya | +0.005 |
OW | +0.004 |
Neg logit contributions | |
brothers | -0.002 |
more | -0.002 |
chambers | -0.002 |
mun | -0.002 |
friends | -0.002 |
Token | group |
Token ID | 1448 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
brothers | +0.001 |
more | +0.001 |
chambers | +0.001 |
mun | +0.001 |
friends | +0.001 |
Neg logit contributions | |
tha | -0.002 |
la | -0.002 |
iya | -0.002 |
essa | -0.002 |
icol | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
peac | +0.030 |
tha | +0.027 |
storm | +0.027 |
flake | +0.027 |
essa | +0.027 |
Neg logit contributions | |
promises | -0.010 |
brothers | -0.010 |
chambers | -0.010 |
goals | -0.009 |
mun | -0.009 |
Token | re |
Token ID | 302 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
tha | +0.060 |
flake | +0.059 |
peac | +0.058 |
iya | +0.057 |
icol | +0.057 |
Neg logit contributions | |
brothers | -0.027 |
chambers | -0.026 |
mun | -0.025 |
promises | -0.024 |
goals | -0.021 |
Token | ind |
Token ID | 521 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
flake | +0.022 |
tha | +0.021 |
icol | +0.021 |
peac | +0.018 |
essa | +0.018 |
Neg logit contributions | |
brothers | -0.053 |
chambers | -0.052 |
mun | -0.051 |
promises | -0.049 |
ins | -0.049 |
Token | eer |
Token ID | 28153 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
tha | +0.162 |
flake | +0.161 |
icol | +0.153 |
iya | +0.150 |
peac | +0.150 |
Neg logit contributions | |
brothers | -0.194 |
chambers | -0.186 |
mun | -0.181 |
promises | -0.176 |
more | -0.170 |
Token | running |
Token ID | 2491 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
flake | +0.035 |
tha | +0.035 |
peac | +0.034 |
ich | +0.033 |
iya | +0.033 |
Neg logit contributions | |
chambers | -0.021 |
brothers | -0.021 |
mun | -0.019 |
promises | -0.019 |
goals | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
tha | +0.000 |
flake | +0.000 |
iya | +0.000 |
essa | +0.000 |
icol | +0.000 |
Neg logit contributions | |
brothers | -0.000 |
chambers | -0.000 |
more | -0.000 |
mun | -0.000 |
friends | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
tha | +0.046 |
flake | +0.045 |
icol | +0.044 |
peac | +0.043 |
iya | +0.043 |
Neg logit contributions | |
brothers | -0.029 |
chambers | -0.027 |
mun | -0.027 |
promises | -0.025 |
ins | -0.024 |
Token | field |
Token ID | 2214 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
brothers | +0.011 |
chambers | +0.011 |
mun | +0.010 |
promises | +0.010 |
more | +0.009 |
Neg logit contributions | |
tha | -0.024 |
flake | -0.023 |
icol | -0.022 |
iya | -0.022 |
essa | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
chambers | +0.003 |
brothers | +0.003 |
mun | +0.003 |
promises | +0.003 |
goals | +0.003 |
Neg logit contributions | |
tha | -0.004 |
flake | -0.004 |
essa | -0.004 |
icol | -0.004 |
peac | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
brothers | +0.001 |
chambers | +0.001 |
mun | +0.001 |
promises | +0.001 |
goals | +0.001 |
Neg logit contributions | |
flake | -0.001 |
tha | -0.001 |
icol | -0.001 |
peac | -0.001 |
iya | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
brothers | +0.013 |
chambers | +0.013 |
mun | +0.012 |
promises | +0.011 |
more | +0.011 |
Neg logit contributions | |
tha | -0.025 |
flake | -0.025 |
icol | -0.024 |
iya | -0.023 |
peac | -0.023 |
Token | Rex |
Token ID | 47389 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
brothers | +0.006 |
chambers | +0.006 |
mun | +0.006 |
promises | +0.006 |
ways | +0.006 |
Neg logit contributions | |
tha | -0.006 |
flake | -0.006 |
peac | -0.006 |
icol | -0.006 |
iya | -0.005 |
Token | sn |
Token ID | 3013 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
brothers | +0.008 |
chambers | +0.008 |
mun | +0.008 |
promises | +0.007 |
more | +0.007 |
Neg logit contributions | |
tha | -0.018 |
flake | -0.018 |
icol | -0.017 |
iya | -0.017 |
peac | -0.017 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
tha | +0.008 |
flake | +0.008 |
icol | +0.007 |
iya | +0.007 |
peac | +0.007 |
Neg logit contributions | |
brothers | -0.009 |
chambers | -0.009 |
mun | -0.008 |
promises | -0.008 |
more | -0.008 |
Token | s |
Token ID | 82 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
flake | +0.173 |
tha | +0.171 |
icol | +0.160 |
iya | +0.157 |
peac | +0.156 |
Neg logit contributions | |
brothers | -0.179 |
chambers | -0.177 |
mun | -0.170 |
promises | -0.164 |
more | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
tha | +0.001 |
flake | +0.001 |
peac | +0.001 |
icol | +0.001 |
iya | +0.001 |
Neg logit contributions | |
brothers | -0.001 |
chambers | -0.001 |
mun | -0.001 |
promises | -0.001 |
ins | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
flake | +0.015 |
tha | +0.015 |
icol | +0.015 |
peac | +0.014 |
iya | +0.014 |
Neg logit contributions | |
mun | -0.007 |
chambers | -0.007 |
brothers | -0.007 |
promises | -0.006 |
ins | -0.006 |
Token | does |
Token ID | 857 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
tha | +0.014 |
flake | +0.014 |
icol | +0.014 |
peac | +0.014 |
la | +0.014 |
Neg logit contributions | |
brothers | -0.009 |
chambers | -0.008 |
mun | -0.007 |
ins | -0.007 |
ways | -0.007 |
Token | not |
Token ID | 407 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
brothers | +0.029 |
chambers | +0.027 |
mun | +0.026 |
promises | +0.026 |
more | +0.026 |
Neg logit contributions | |
tha | -0.027 |
flake | -0.026 |
icol | -0.025 |
iya | -0.025 |
peac | -0.025 |
Token | you |
Token ID | 345 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
brothers | +0.002 |
promises | +0.002 |
chambers | +0.002 |
mun | +0.002 |
friends | +0.002 |
Neg logit contributions | |
flake | -0.003 |
icol | -0.003 |
tha | -0.003 |
iya | -0.003 |
essa | -0.003 |
Token | go |
Token ID | 467 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
mun | +0.036 |
chambers | +0.031 |
importantly | +0.030 |
brothers | +0.030 |
ins | +0.030 |
Neg logit contributions | |
peac | -0.034 |
OW | -0.033 |
AR | -0.032 |
flake | -0.032 |
AP | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
of | +0.012 |
more | +0.012 |
brothers | +0.010 |
friends | +0.010 |
chambers | +0.009 |
Neg logit contributions | |
iya | -0.039 |
flake | -0.039 |
essa | -0.038 |
icol | -0.038 |
tha | -0.037 |
Token | my |
Token ID | 616 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
brothers | +0.008 |
chambers | +0.007 |
promises | +0.007 |
mun | +0.007 |
more | +0.007 |
Neg logit contributions | |
flake | -0.014 |
tha | -0.014 |
icol | -0.014 |
iya | -0.013 |
peac | -0.013 |
Token | d |
Token ID | 288 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
tha | +0.068 |
iya | +0.066 |
la | +0.065 |
flake | +0.064 |
icol | +0.064 |
Neg logit contributions | |
brothers | -0.035 |
friends | -0.032 |
promises | -0.028 |
of | -0.027 |
chambers | -0.026 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
tha | +0.014 |
flake | +0.013 |
icol | +0.013 |
iya | +0.013 |
peac | +0.013 |
Neg logit contributions | |
brothers | -0.011 |
chambers | -0.010 |
of | -0.009 |
mun | -0.009 |
ins | -0.009 |
Token | ings |
Token ID | 654 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
tha | +0.151 |
peac | +0.148 |
iya | +0.146 |
flake | +0.146 |
icol | +0.146 |
Neg logit contributions | |
brothers | -0.200 |
chambers | -0.184 |
mun | -0.183 |
promises | -0.182 |
friends | -0.179 |
Token | ," |
Token ID | 553 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
of | +0.002 |
more | +0.002 |
brothers | +0.002 |
mun | +0.002 |
cookies | +0.002 |
Neg logit contributions | |
icol | -0.003 |
tha | -0.003 |
iya | -0.003 |
flake | -0.003 |
peac | -0.003 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
tha | +0.021 |
flake | +0.021 |
icol | +0.020 |
peac | +0.020 |
iya | +0.020 |
Neg logit contributions | |
brothers | -0.013 |
chambers | -0.013 |
mun | -0.012 |
promises | -0.012 |
goals | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
chambers | +0.075 |
goals | +0.075 |
brothers | +0.071 |
chores | +0.069 |
mun | +0.069 |
Neg logit contributions | |
tha | -0.068 |
flake | -0.067 |
peac | -0.064 |
essa | -0.064 |
la | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
chambers | +0.020 |
brothers | +0.019 |
mun | +0.018 |
goals | +0.017 |
promises | +0.016 |
Neg logit contributions | |
tha | -0.029 |
flake | -0.028 |
essa | -0.028 |
icol | -0.027 |
iya | -0.026 |
Token | 's |
Token ID | 338 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
brothers | +0.008 |
chambers | +0.007 |
mun | +0.007 |
promises | +0.006 |
questions | +0.006 |
Neg logit contributions | |
flake | -0.017 |
tha | -0.017 |
peac | -0.016 |
icol | -0.016 |
essa | -0.016 |
Token | okay |
Token ID | 8788 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
brothers | +0.018 |
chambers | +0.017 |
mun | +0.016 |
promises | +0.016 |
more | +0.015 |
Neg logit contributions | |
tha | -0.033 |
flake | -0.033 |
icol | -0.031 |
iya | -0.031 |
peac | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
brothers | +0.036 |
chambers | +0.034 |
mun | +0.032 |
promises | +0.031 |
more | +0.029 |
Neg logit contributions | |
tha | -0.068 |
flake | -0.068 |
icol | -0.065 |
iya | -0.065 |
peac | -0.065 |
Token | my |
Token ID | 616 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
brothers | +0.009 |
promises | +0.007 |
chambers | +0.007 |
friends | +0.007 |
more | +0.007 |
Neg logit contributions | |
flake | -0.015 |
tha | -0.014 |
icol | -0.014 |
iya | -0.014 |
OW | -0.013 |
Token | d |
Token ID | 288 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
tha | +0.049 |
flake | +0.048 |
iya | +0.045 |
AR | +0.045 |
la | +0.045 |
Neg logit contributions | |
brothers | -0.030 |
friends | -0.026 |
questions | -0.026 |
promises | -0.026 |
chambers | -0.024 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
brothers | +0.001 |
chambers | +0.000 |
of | +0.000 |
ins | +0.000 |
questions | +0.000 |
Neg logit contributions | |
tha | -0.001 |
flake | -0.001 |
peac | -0.001 |
icol | -0.001 |
iya | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
tha | +0.147 |
flake | +0.142 |
peac | +0.140 |
icol | +0.139 |
iya | +0.137 |
Neg logit contributions | |
brothers | -0.207 |
chambers | -0.192 |
mun | -0.192 |
promises | -0.189 |
friends | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
brothers | +0.004 |
chambers | +0.003 |
mun | +0.003 |
more | +0.003 |
promises | +0.003 |
Neg logit contributions | |
tha | -0.012 |
flake | -0.012 |
icol | -0.012 |
iya | -0.012 |
peac | -0.012 |
Token | I |
Token ID | 314 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
tha | +0.005 |
flake | +0.005 |
iya | +0.005 |
peac | +0.005 |
icol | +0.005 |
Neg logit contributions | |
brothers | -0.005 |
chambers | -0.005 |
promises | -0.005 |
mun | -0.005 |
more | -0.005 |
Token | forgive |
Token ID | 20927 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
brothers | +0.004 |
chambers | +0.004 |
mun | +0.004 |
promises | +0.004 |
more | +0.004 |
Neg logit contributions | |
tha | -0.007 |
flake | -0.007 |
icol | -0.007 |
iya | -0.007 |
essa | -0.007 |
Token | you |
Token ID | 345 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
brothers | +0.004 |
more | +0.004 |
friends | +0.004 |
promises | +0.003 |
chambers | +0.003 |
Neg logit contributions | |
flake | -0.005 |
icol | -0.005 |
tha | -0.005 |
storm | -0.005 |
iya | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
flake | +0.010 |
icol | +0.009 |
tha | +0.009 |
AP | +0.008 |
ANG | +0.008 |
Neg logit contributions | |
brothers | -0.007 |
friends | -0.006 |
more | -0.006 |
promises | -0.006 |
mun | -0.006 |
Token | too |
Token ID | 1165 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
brothers | +0.003 |
more | +0.002 |
friends | +0.002 |
chambers | +0.002 |
sisters | +0.002 |
Neg logit contributions | |
icol | -0.006 |
flake | -0.006 |
tha | -0.006 |
iya | -0.006 |
peac | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
brothers | +0.025 |
chambers | +0.023 |
more | +0.022 |
friends | +0.021 |
mun | +0.020 |
Neg logit contributions | |
flake | -0.046 |
tha | -0.043 |
icol | -0.043 |
peac | -0.042 |
iya | -0.041 |
Token | my |
Token ID | 616 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
flake | +0.001 |
tha | +0.001 |
icol | +0.001 |
iya | +0.001 |
peac | +0.001 |
Neg logit contributions | |
brothers | -0.001 |
chambers | -0.001 |
mun | -0.001 |
promises | -0.001 |
more | -0.001 |
Token | d |
Token ID | 288 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
tha | +0.074 |
flake | +0.073 |
icol | +0.072 |
peac | +0.071 |
iya | +0.069 |
Neg logit contributions | |
brothers | -0.040 |
friends | -0.034 |
promises | -0.032 |
more | -0.031 |
mun | -0.030 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
tha | +0.018 |
flake | +0.017 |
icol | +0.017 |
peac | +0.017 |
iya | +0.017 |
Neg logit contributions | |
brothers | -0.011 |
of | -0.010 |
ins | -0.010 |
chambers | -0.009 |
mun | -0.009 |
Token | ings |
Token ID | 654 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
tha | +0.150 |
flake | +0.148 |
peac | +0.147 |
icol | +0.146 |
iya | +0.142 |
Neg logit contributions | |
brothers | -0.202 |
mun | -0.189 |
chambers | -0.186 |
promises | -0.185 |
friends | -0.179 |
Token | ," |
Token ID | 553 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
icol | +0.006 |
tha | +0.006 |
iya | +0.006 |
flake | +0.006 |
ich | +0.005 |
Neg logit contributions | |
of | -0.004 |
brothers | -0.004 |
more | -0.004 |
mun | -0.003 |
chambers | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
tha | +0.019 |
flake | +0.019 |
icol | +0.019 |
iya | +0.018 |
peac | +0.018 |
Neg logit contributions | |
brothers | -0.012 |
chambers | -0.011 |
mun | -0.010 |
promises | -0.010 |
more | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
chambers | +0.045 |
brothers | +0.044 |
mun | +0.042 |
promises | +0.040 |
goals | +0.040 |
Neg logit contributions | |
flake | -0.054 |
tha | -0.054 |
peac | -0.052 |
essa | -0.052 |
icol | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
chambers | +0.018 |
brothers | +0.017 |
mun | +0.016 |
goals | +0.015 |
promises | +0.015 |
Neg logit contributions | |
tha | -0.034 |
flake | -0.033 |
essa | -0.032 |
iya | -0.032 |
icol | -0.032 |
Token | What |
Token ID | 2061 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
tha | +0.014 |
flake | +0.014 |
icol | +0.014 |
iya | +0.013 |
peac | +0.013 |
Neg logit contributions | |
brothers | -0.010 |
chambers | -0.009 |
mun | -0.009 |
promises | -0.008 |
more | -0.008 |
Token | happened |
Token ID | 3022 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
flake | +0.012 |
peac | +0.012 |
essa | +0.012 |
OW | +0.012 |
work | +0.012 |
Neg logit contributions | |
chambers | -0.017 |
mun | -0.017 |
ang | -0.016 |
irms | -0.016 |
promises | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
brothers | +0.009 |
questions | +0.008 |
of | +0.008 |
more | +0.007 |
friends | +0.007 |
Neg logit contributions | |
flake | -0.022 |
tha | -0.022 |
la | -0.021 |
iya | -0.021 |
icol | -0.021 |
Token | my |
Token ID | 616 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
brothers | +0.003 |
chambers | +0.003 |
mun | +0.003 |
promises | +0.002 |
goals | +0.002 |
Neg logit contributions | |
tha | -0.005 |
flake | -0.005 |
icol | -0.005 |
iya | -0.005 |
peac | -0.005 |
Token | d |
Token ID | 288 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
flake | +0.063 |
peac | +0.062 |
AR | +0.062 |
iya | +0.061 |
nes | +0.060 |
Neg logit contributions | |
brothers | -0.029 |
friends | -0.025 |
twins | -0.021 |
promises | -0.021 |
toys | -0.021 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
tha | +0.017 |
flake | +0.017 |
icol | +0.016 |
iya | +0.016 |
peac | +0.016 |
Neg logit contributions | |
brothers | -0.011 |
of | -0.010 |
chambers | -0.010 |
ins | -0.010 |
mun | -0.009 |
Token | ings |
Token ID | 654 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
tha | +0.152 |
peac | +0.151 |
icol | +0.151 |
flake | +0.148 |
iya | +0.147 |
Neg logit contributions | |
brothers | -0.198 |
mun | -0.181 |
chambers | -0.180 |
promises | -0.177 |
friends | -0.175 |
Token | ? |
Token ID | 30 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
icol | +0.002 |
tha | +0.002 |
iya | +0.002 |
flake | +0.002 |
peac | +0.002 |
Neg logit contributions | |
brothers | -0.001 |
of | -0.001 |
chambers | -0.001 |
mun | -0.001 |
more | -0.001 |
Token | Why |
Token ID | 4162 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
tha | +0.086 |
flake | +0.085 |
iya | +0.083 |
icol | +0.083 |
essa | +0.082 |
Neg logit contributions | |
brothers | -0.048 |
chambers | -0.042 |
mun | -0.040 |
promises | -0.037 |
cabinets | -0.035 |
Token | are |
Token ID | 389 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
tha | +0.011 |
flake | +0.011 |
icol | +0.010 |
iya | +0.010 |
peac | +0.010 |
Neg logit contributions | |
brothers | -0.004 |
chambers | -0.004 |
mun | -0.003 |
promises | -0.003 |
more | -0.003 |
Token | you |
Token ID | 345 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
brothers | +0.015 |
chambers | +0.014 |
friends | +0.014 |
more | +0.013 |
promises | +0.013 |
Neg logit contributions | |
flake | -0.016 |
icol | -0.016 |
tha | -0.015 |
iya | -0.014 |
peac | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
brothers | +0.007 |
more | +0.006 |
mun | +0.005 |
promises | +0.005 |
friends | +0.004 |
Neg logit contributions | |
icol | -0.048 |
tha | -0.047 |
AR | -0.046 |
iya | -0.045 |
OW | -0.045 |
Token | good |
Token ID | 922 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
brothers | +0.021 |
chambers | +0.020 |
mun | +0.019 |
promises | +0.018 |
goals | +0.017 |
Neg logit contributions | |
tha | -0.033 |
flake | -0.032 |
icol | -0.031 |
iya | -0.031 |
peac | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
flake | +0.016 |
tha | +0.016 |
icol | +0.016 |
iya | +0.015 |
peac | +0.015 |
Neg logit contributions | |
brothers | -0.008 |
chambers | -0.007 |
mun | -0.006 |
friends | -0.006 |
more | -0.006 |
Token | my |
Token ID | 616 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
flake | +0.001 |
tha | +0.001 |
icol | +0.001 |
iya | +0.001 |
peac | +0.001 |
Neg logit contributions | |
brothers | -0.001 |
chambers | -0.001 |
promises | -0.001 |
more | -0.001 |
friends | -0.001 |
Token | d |
Token ID | 288 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
AR | +0.063 |
storm | +0.062 |
flake | +0.059 |
icol | +0.058 |
nes | +0.058 |
Neg logit contributions | |
brothers | -0.039 |
friends | -0.039 |
promises | -0.034 |
more | -0.032 |
sisters | -0.031 |
Token | arl |
Token ID | 7063 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
icol | +0.015 |
tha | +0.015 |
flake | +0.015 |
iya | +0.015 |
storm | +0.014 |
Neg logit contributions | |
of | -0.010 |
brothers | -0.009 |
ins | -0.009 |
chambers | -0.008 |
oll | -0.008 |
Token | ings |
Token ID | 654 |
Feature activation | +8.20e-04 |
Pos logit contributions | |
icol | +0.148 |
tha | +0.148 |
peac | +0.147 |
flake | +0.145 |
iya | +0.143 |
Neg logit contributions | |
brothers | -0.200 |
mun | -0.186 |
chambers | -0.184 |
promises | -0.183 |
friends | -0.177 |
Token | . |
Token ID | 13 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
tha | +0.000 |
icol | +0.000 |
flake | +0.000 |
iya | +0.000 |
peac | +0.000 |
Neg logit contributions | |
brothers | -0.000 |
chambers | -0.000 |
mun | -0.000 |
more | -0.000 |
of | -0.000 |
Token | I |
Token ID | 314 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
brothers | +0.002 |
chambers | +0.002 |
promises | +0.002 |
mun | +0.002 |
goals | +0.002 |
Neg logit contributions | |
flake | -0.003 |
tha | -0.003 |
iya | -0.003 |
essa | -0.003 |
la | -0.003 |
Token | 'm |
Token ID | 1101 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
brothers | +0.003 |
mun | +0.002 |
promises | +0.002 |
chambers | +0.002 |
more | +0.002 |
Neg logit contributions | |
tha | -0.005 |
icol | -0.004 |
flake | -0.004 |
iya | -0.004 |
essa | -0.004 |
Token | glad |
Token ID | 9675 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
flake | +0.075 |
icol | +0.073 |
tha | +0.071 |
storm | +0.070 |
iya | +0.069 |
Neg logit contributions | |
brothers | -0.024 |
more | -0.021 |
friends | -0.019 |
promises | -0.018 |
mun | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
brothers | +0.033 |
mun | +0.030 |
chambers | +0.028 |
promises | +0.025 |
of | +0.024 |
Neg logit contributions | |
tha | -0.090 |
flake | -0.090 |
icol | -0.090 |
peac | -0.087 |
iya | -0.087 |
Token | wrong |
Token ID | 2642 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
brothers | +0.063 |
chambers | +0.058 |
promises | +0.054 |
chores | +0.054 |
more | +0.054 |
Neg logit contributions | |
flake | -0.078 |
icol | -0.076 |
tha | -0.074 |
peac | -0.071 |
iya | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
flake | +0.013 |
peac | +0.012 |
OW | +0.012 |
tha | +0.012 |
icol | +0.012 |
Neg logit contributions | |
brothers | -0.008 |
friends | -0.007 |
of | -0.006 |
chambers | -0.006 |
more | -0.006 |
Token | rh |
Token ID | 9529 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
brothers | +0.025 |
friends | +0.021 |
more | +0.020 |
promises | +0.020 |
chambers | +0.020 |
Neg logit contributions | |
flake | -0.035 |
icol | -0.033 |
tha | -0.033 |
storm | -0.031 |
peac | -0.031 |
Token | in |
Token ID | 259 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
brothers | +0.018 |
chambers | +0.016 |
mun | +0.016 |
promises | +0.014 |
more | +0.014 |
Neg logit contributions | |
tha | -0.035 |
flake | -0.035 |
icol | -0.034 |
iya | -0.033 |
peac | -0.033 |
Token | oc |
Token ID | 420 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
icol | +0.007 |
tha | +0.007 |
flake | +0.007 |
essa | +0.006 |
iya | +0.006 |
Neg logit contributions | |
brothers | -0.006 |
mun | -0.005 |
chambers | -0.005 |
more | -0.005 |
promises | -0.005 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
brothers | +0.298 |
mun | +0.268 |
ins | +0.266 |
chambers | +0.260 |
friends | +0.257 |
Neg logit contributions | |
flake | -0.219 |
iya | -0.210 |
tha | -0.210 |
icol | -0.209 |
storm | -0.201 |
Token | ? |
Token ID | 30 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
icol | +0.016 |
tha | +0.015 |
flake | +0.015 |
iya | +0.015 |
essa | +0.015 |
Neg logit contributions | |
brothers | -0.014 |
friends | -0.012 |
mun | -0.011 |
chambers | -0.011 |
of | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
flake | +0.055 |
tha | +0.055 |
icol | +0.054 |
iya | +0.052 |
essa | +0.052 |
Neg logit contributions | |
brothers | -0.034 |
chambers | -0.029 |
mun | -0.028 |
of | -0.026 |
So | -0.026 |
Token | € |
Token ID | 26391 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
peac | +0.040 |
icol | +0.037 |
flake | +0.037 |
iya | +0.037 |
tha | +0.037 |
Neg logit contributions | |
brothers | -0.042 |
promises | -0.038 |
mun | -0.037 |
exercises | -0.035 |
chambers | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
brothers | +0.011 |
mun | +0.009 |
chambers | +0.008 |
friends | +0.008 |
es | +0.008 |
Neg logit contributions | |
flake | -0.022 |
tha | -0.022 |
essa | -0.022 |
peac | -0.021 |
work | -0.021 |
Token | give |
Token ID | 1577 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
brothers | +0.026 |
more | +0.025 |
chambers | +0.025 |
friends | +0.023 |
promises | +0.023 |
Neg logit contributions | |
icol | -0.063 |
tha | -0.062 |
flake | -0.061 |
iya | -0.060 |
essa | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
more | +0.026 |
brothers | +0.026 |
promises | +0.025 |
friends | +0.025 |
mun | +0.023 |
Neg logit contributions | |
icol | -0.045 |
flake | -0.045 |
storm | -0.044 |
tha | -0.044 |
iya | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
brothers | +0.004 |
chambers | +0.003 |
promises | +0.003 |
more | +0.003 |
friends | +0.003 |
Neg logit contributions | |
flake | -0.009 |
tha | -0.009 |
icol | -0.008 |
iya | -0.008 |
essa | -0.008 |
Token | rh |
Token ID | 9529 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
brothers | +0.012 |
friends | +0.010 |
chambers | +0.010 |
more | +0.010 |
promises | +0.009 |
Neg logit contributions | |
tha | -0.020 |
icol | -0.020 |
iya | -0.020 |
flake | -0.019 |
la | -0.019 |
Token | in |
Token ID | 259 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
brothers | +0.024 |
chambers | +0.023 |
mun | +0.022 |
promises | +0.021 |
more | +0.020 |
Neg logit contributions | |
flake | -0.043 |
tha | -0.042 |
peac | -0.040 |
iya | -0.040 |
icol | -0.040 |
Token | oc |
Token ID | 420 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
tha | +0.018 |
flake | +0.018 |
icol | +0.018 |
iya | +0.017 |
essa | +0.017 |
Neg logit contributions | |
brothers | -0.005 |
chambers | -0.004 |
mun | -0.004 |
promises | -0.003 |
more | -0.003 |
Token | eros |
Token ID | 27498 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
brothers | +0.311 |
promises | +0.284 |
mun | +0.278 |
chambers | +0.277 |
more | +0.268 |
Neg logit contributions | |
flake | -0.195 |
iya | -0.190 |
tha | -0.188 |
icol | -0.187 |
essa | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
brothers | +0.001 |
chambers | +0.001 |
more | +0.001 |
friends | +0.001 |
promises | +0.001 |
Neg logit contributions | |
tha | -0.002 |
icol | -0.002 |
flake | -0.002 |
iya | -0.002 |
essa | -0.002 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
brothers | +0.002 |
chambers | +0.002 |
So | +0.002 |
mun | +0.002 |
promises | +0.002 |
Neg logit contributions | |
flake | -0.007 |
tha | -0.007 |
iya | -0.007 |
essa | -0.007 |
peac | -0.007 |
Token | walked |
Token ID | 6807 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
brothers | +0.016 |
mun | +0.014 |
chambers | +0.014 |
promises | +0.013 |
more | +0.012 |
Neg logit contributions | |
tha | -0.037 |
flake | -0.036 |
peac | -0.035 |
icol | -0.035 |
iya | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
brothers | +0.033 |
more | +0.032 |
chambers | +0.031 |
questions | +0.029 |
friends | +0.029 |
Neg logit contributions | |
flake | -0.062 |
tha | -0.062 |
peac | -0.061 |
icol | -0.060 |
iya | -0.060 |
Token | it |
Token ID | 340 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
flake | +0.006 |
storm | +0.006 |
icol | +0.006 |
tha | +0.006 |
peac | +0.006 |
Neg logit contributions | |
brothers | -0.003 |
friends | -0.003 |
promises | -0.003 |
more | -0.003 |
mun | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
tha | +0.054 |
flake | +0.052 |
iya | +0.051 |
icol | +0.051 |
essa | +0.048 |
Neg logit contributions | |
more | -0.030 |
brothers | -0.030 |
friends | -0.029 |
promises | -0.028 |
chambers | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
brothers | +0.008 |
friends | +0.007 |
more | +0.007 |
promises | +0.006 |
other | +0.006 |
Neg logit contributions | |
flake | -0.019 |
icol | -0.019 |
tha | -0.018 |
ANG | -0.018 |
ich | -0.017 |
Token | rh |
Token ID | 9529 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
brothers | +0.025 |
more | +0.022 |
friends | +0.022 |
chambers | +0.020 |
other | +0.020 |
Neg logit contributions | |
tha | -0.039 |
icol | -0.037 |
flake | -0.037 |
enda | -0.037 |
da | -0.037 |
Token | in |
Token ID | 259 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
brothers | +0.021 |
chambers | +0.020 |
mun | +0.019 |
promises | +0.018 |
more | +0.017 |
Neg logit contributions | |
tha | -0.039 |
flake | -0.039 |
icol | -0.037 |
iya | -0.037 |
peac | -0.037 |
Token | oc |
Token ID | 420 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
tha | +0.001 |
flake | +0.001 |
icol | +0.001 |
iya | +0.001 |
essa | +0.001 |
Neg logit contributions | |
brothers | -0.000 |
chambers | -0.000 |
mun | -0.000 |
promises | -0.000 |
more | -0.000 |
Token | eros |
Token ID | 27498 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
brothers | +0.298 |
promises | +0.272 |
mun | +0.259 |
chambers | +0.259 |
friends | +0.253 |
Neg logit contributions | |
flake | -0.189 |
iya | -0.187 |
essa | -0.183 |
icol | -0.183 |
tha | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
brothers | +0.002 |
chambers | +0.002 |
mun | +0.002 |
promises | +0.002 |
more | +0.002 |
Neg logit contributions | |
tha | -0.007 |
icol | -0.006 |
flake | -0.006 |
iya | -0.006 |
essa | -0.006 |
Token | When |
Token ID | 1649 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
flake | +0.002 |
tha | +0.002 |
peac | +0.002 |
essa | +0.002 |
icol | +0.002 |
Neg logit contributions | |
brothers | -0.001 |
So | -0.001 |
chambers | -0.001 |
mun | -0.000 |
friends | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
flake | +0.011 |
icol | +0.011 |
tha | +0.011 |
OW | +0.011 |
essa | +0.011 |
Neg logit contributions | |
brothers | -0.004 |
more | -0.003 |
friends | -0.003 |
chambers | -0.003 |
cookies | -0.003 |
Token | tasted |
Token ID | 29187 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
brothers | +0.010 |
mun | +0.009 |
chambers | +0.008 |
more | +0.008 |
promises | +0.008 |
Neg logit contributions | |
tha | -0.022 |
flake | -0.022 |
icol | -0.022 |
essa | -0.021 |
iya | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
flake | +0.009 |
tha | +0.009 |
icol | +0.009 |
peac | +0.008 |
iya | +0.008 |
Neg logit contributions | |
brothers | -0.004 |
chambers | -0.004 |
mun | -0.004 |
promises | -0.003 |
more | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
flake | +0.025 |
tha | +0.024 |
icol | +0.024 |
peac | +0.023 |
iya | +0.023 |
Neg logit contributions | |
brothers | -0.017 |
chambers | -0.016 |
mun | -0.015 |
promises | -0.014 |
more | -0.014 |
Token | The |
Token ID | 464 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
tha | +0.045 |
icol | +0.045 |
flake | +0.044 |
iya | +0.042 |
peac | +0.042 |
Neg logit contributions | |
brothers | -0.030 |
mun | -0.029 |
chambers | -0.028 |
more | -0.027 |
promises | -0.026 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
flake | +0.024 |
tha | +0.024 |
iya | +0.023 |
icol | +0.023 |
enda | +0.023 |
Neg logit contributions | |
brothers | -0.017 |
friends | -0.015 |
chambers | -0.015 |
more | -0.015 |
questions | -0.015 |
Token | in |
Token ID | 259 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
brothers | +0.007 |
chambers | +0.006 |
mun | +0.006 |
promises | +0.005 |
more | +0.005 |
Neg logit contributions | |
icol | -0.013 |
tha | -0.013 |
flake | -0.012 |
iya | -0.012 |
essa | -0.012 |
Token | oc |
Token ID | 420 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
icol | +0.019 |
essa | +0.018 |
iya | +0.018 |
tha | +0.018 |
flake | +0.018 |
Neg logit contributions | |
brothers | -0.003 |
chambers | -0.002 |
promises | -0.002 |
friends | -0.002 |
more | -0.002 |
Token | eros |
Token ID | 27498 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
brothers | +0.287 |
promises | +0.261 |
mun | +0.254 |
chambers | +0.253 |
ins | +0.248 |
Neg logit contributions | |
icol | -0.186 |
iya | -0.186 |
flake | -0.182 |
storm | -0.178 |
essa | -0.177 |
Token | is |
Token ID | 318 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
brothers | +0.002 |
promises | +0.002 |
more | +0.002 |
chambers | +0.002 |
friends | +0.002 |
Neg logit contributions | |
icol | -0.006 |
iya | -0.006 |
essa | -0.006 |
flake | -0.006 |
tha | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
flake | +0.021 |
icol | +0.021 |
iya | +0.021 |
tha | +0.020 |
essa | +0.020 |
Neg logit contributions | |
more | -0.010 |
brothers | -0.010 |
friends | -0.008 |
of | -0.008 |
chambers | -0.007 |
Token | there |
Token ID | 612 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
brothers | +0.003 |
more | +0.003 |
chambers | +0.003 |
of | +0.003 |
friends | +0.003 |
Neg logit contributions | |
flake | -0.008 |
icol | -0.008 |
tha | -0.008 |
essa | -0.008 |
iya | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
more | +0.034 |
brothers | +0.034 |
of | +0.033 |
friends | +0.032 |
chambers | +0.030 |
Neg logit contributions | |
icol | -0.072 |
flake | -0.065 |
peac | -0.065 |
tha | -0.065 |
iya | -0.064 |
Token | 't |
Token ID | 470 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
more | +0.001 |
brothers | +0.000 |
of | +0.000 |
cookies | +0.000 |
friends | +0.000 |
Neg logit contributions | |
flake | -0.001 |
icol | -0.001 |
tha | -0.001 |
iya | -0.001 |
ich | -0.001 |
Token | know |
Token ID | 760 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
flake | +0.059 |
icol | +0.059 |
tha | +0.058 |
iya | +0.055 |
essa | +0.053 |
Neg logit contributions | |
brothers | -0.026 |
friends | -0.023 |
more | -0.022 |
chambers | -0.022 |
promises | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
brothers | +0.012 |
chambers | +0.011 |
more | +0.011 |
friends | +0.010 |
ways | +0.010 |
Neg logit contributions | |
flake | -0.028 |
icol | -0.028 |
tha | -0.028 |
iya | -0.027 |
peac | -0.026 |
Token | rh |
Token ID | 9529 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
tha | +0.013 |
icol | +0.013 |
iya | +0.012 |
flake | +0.012 |
enda | +0.012 |
Neg logit contributions | |
brothers | -0.008 |
more | -0.007 |
chambers | -0.007 |
friends | -0.007 |
questions | -0.007 |
Token | in |
Token ID | 259 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
brothers | +0.003 |
chambers | +0.003 |
mun | +0.003 |
promises | +0.002 |
more | +0.002 |
Neg logit contributions | |
tha | -0.006 |
icol | -0.006 |
flake | -0.006 |
iya | -0.005 |
peac | -0.005 |
Token | oc |
Token ID | 420 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
tha | +0.065 |
icol | +0.064 |
iya | +0.063 |
flake | +0.063 |
essa | +0.062 |
Neg logit contributions | |
brothers | -0.014 |
mun | -0.011 |
chambers | -0.010 |
promises | -0.010 |
more | -0.010 |
Token | eros |
Token ID | 27498 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
brothers | +0.288 |
promises | +0.265 |
mun | +0.263 |
chambers | +0.255 |
ins | +0.250 |
Neg logit contributions | |
flake | -0.181 |
iya | -0.180 |
icol | -0.177 |
tha | -0.175 |
essa | -0.170 |
Token | was |
Token ID | 373 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
icol | +0.053 |
flake | +0.051 |
tha | +0.051 |
iya | +0.050 |
essa | +0.049 |
Neg logit contributions | |
brothers | -0.019 |
chambers | -0.016 |
mun | -0.015 |
more | -0.015 |
friends | -0.015 |
Token | wild |
Token ID | 4295 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
flake | +0.016 |
icol | +0.016 |
tha | +0.016 |
iya | +0.016 |
essa | +0.016 |
Neg logit contributions | |
brothers | -0.009 |
more | -0.009 |
friends | -0.008 |
chambers | -0.007 |
of | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
brothers | +0.008 |
chambers | +0.007 |
mun | +0.007 |
promises | +0.006 |
more | +0.006 |
Neg logit contributions | |
tha | -0.017 |
flake | -0.017 |
iya | -0.017 |
icol | -0.016 |
peac | -0.016 |
Token | Can |
Token ID | 1680 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
flake | +0.007 |
tha | +0.007 |
icol | +0.006 |
essa | +0.006 |
iya | +0.006 |
Neg logit contributions | |
brothers | -0.002 |
So | -0.002 |
chambers | -0.002 |
of | -0.001 |
mun | -0.001 |
Token | mess |
Token ID | 2085 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
flake | +0.005 |
tha | +0.005 |
la | +0.005 |
essa | +0.005 |
OW | +0.005 |
Neg logit contributions | |
brothers | -0.003 |
more | -0.003 |
chambers | -0.002 |
promises | -0.002 |
friends | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
tha | +0.027 |
flake | +0.027 |
icol | +0.027 |
iya | +0.026 |
peac | +0.026 |
Neg logit contributions | |
brothers | -0.010 |
chambers | -0.009 |
mun | -0.009 |
more | -0.008 |
promises | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
brothers | +0.001 |
chambers | +0.001 |
mun | +0.001 |
promises | +0.001 |
ways | +0.001 |
Neg logit contributions | |
flake | -0.004 |
tha | -0.004 |
peac | -0.004 |
icol | -0.003 |
iya | -0.003 |
Token | rh |
Token ID | 9529 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
tha | +0.008 |
flake | +0.008 |
icol | +0.007 |
iya | +0.007 |
la | +0.007 |
Neg logit contributions | |
brothers | -0.005 |
chambers | -0.004 |
friends | -0.004 |
more | -0.004 |
mun | -0.004 |
Token | in |
Token ID | 259 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
brothers | +0.015 |
chambers | +0.014 |
mun | +0.013 |
promises | +0.013 |
more | +0.012 |
Neg logit contributions | |
flake | -0.026 |
tha | -0.026 |
peac | -0.024 |
iya | -0.024 |
icol | -0.024 |
Token | oc |
Token ID | 420 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
tha | +0.022 |
flake | +0.022 |
icol | +0.021 |
iya | +0.021 |
essa | +0.021 |
Neg logit contributions | |
brothers | -0.006 |
chambers | -0.005 |
mun | -0.004 |
promises | -0.004 |
more | -0.004 |
Token | eros |
Token ID | 27498 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
brothers | +0.292 |
chambers | +0.271 |
promises | +0.269 |
mun | +0.268 |
ins | +0.254 |
Neg logit contributions | |
flake | -0.166 |
iya | -0.165 |
icol | -0.160 |
tha | -0.160 |
OW | -0.155 |
Token | had |
Token ID | 550 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
brothers | +0.004 |
chambers | +0.004 |
mun | +0.004 |
more | +0.003 |
promises | +0.003 |
Neg logit contributions | |
tha | -0.010 |
icol | -0.010 |
flake | -0.010 |
iya | -0.010 |
essa | -0.010 |
Token | destroyed |
Token ID | 6572 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
brothers | +0.006 |
more | +0.006 |
chambers | +0.006 |
friends | +0.006 |
of | +0.005 |
Neg logit contributions | |
tha | -0.011 |
flake | -0.011 |
icol | -0.010 |
iya | -0.010 |
essa | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
flake | +0.083 |
tha | +0.082 |
iya | +0.081 |
peac | +0.080 |
icol | +0.080 |
Neg logit contributions | |
brothers | -0.029 |
more | -0.027 |
chambers | -0.027 |
ways | -0.025 |
friends | -0.024 |
Token | room |
Token ID | 2119 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
brothers | +0.030 |
chambers | +0.027 |
promises | +0.026 |
friends | +0.026 |
more | +0.026 |
Neg logit contributions | |
tha | -0.051 |
flake | -0.050 |
iya | -0.050 |
icol | -0.049 |
essa | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
icol | +0.015 |
flake | +0.015 |
AR | +0.014 |
tha | +0.014 |
iya | +0.014 |
Neg logit contributions | |
more | -0.004 |
of | -0.004 |
brothers | -0.003 |
friends | -0.003 |
questions | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
brothers | +0.006 |
questions | +0.005 |
of | +0.004 |
more | +0.004 |
friends | +0.003 |
Neg logit contributions | |
tha | -0.024 |
flake | -0.024 |
icol | -0.024 |
iya | -0.023 |
essa | -0.023 |
Token | The |
Token ID | 464 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
mun | +0.015 |
brothers | +0.015 |
promises | +0.013 |
more | +0.013 |
chambers | +0.013 |
Neg logit contributions | |
tha | -0.025 |
icol | -0.025 |
flake | -0.025 |
iya | -0.023 |
essa | -0.023 |
Token | rh |
Token ID | 9529 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
flake | +0.010 |
tha | +0.009 |
enda | +0.009 |
icol | +0.009 |
la | +0.009 |
Neg logit contributions | |
brothers | -0.008 |
friends | -0.007 |
more | -0.007 |
promises | -0.006 |
other | -0.006 |
Token | in |
Token ID | 259 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
brothers | +0.019 |
chambers | +0.017 |
mun | +0.017 |
promises | +0.016 |
more | +0.015 |
Neg logit contributions | |
tha | -0.036 |
flake | -0.036 |
icol | -0.035 |
iya | -0.034 |
peac | -0.034 |
Token | oc |
Token ID | 420 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
brothers | +0.000 |
mun | +0.000 |
promises | +0.000 |
chambers | +0.000 |
more | +0.000 |
Neg logit contributions | |
icol | -0.002 |
tha | -0.001 |
essa | -0.001 |
iya | -0.001 |
flake | -0.001 |
Token | eros |
Token ID | 27498 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
brothers | +0.283 |
promises | +0.257 |
mun | +0.256 |
chambers | +0.251 |
ins | +0.242 |
Neg logit contributions | |
iya | -0.183 |
flake | -0.179 |
icol | -0.179 |
essa | -0.173 |
Gina | -0.172 |
Token | made |
Token ID | 925 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
brothers | +0.007 |
chambers | +0.006 |
promises | +0.006 |
mun | +0.005 |
friends | +0.005 |
Neg logit contributions | |
icol | -0.017 |
flake | -0.016 |
tha | -0.016 |
iya | -0.016 |
essa | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
flake | +0.024 |
tha | +0.023 |
icol | +0.022 |
storm | +0.022 |
iya | +0.022 |
Neg logit contributions | |
brothers | -0.016 |
more | -0.015 |
friends | -0.015 |
promises | -0.014 |
of | -0.013 |
Token | big |
Token ID | 1263 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
brothers | +0.015 |
more | +0.013 |
chambers | +0.013 |
friends | +0.012 |
promises | +0.012 |
Neg logit contributions | |
tha | -0.032 |
flake | -0.031 |
essa | -0.030 |
la | -0.030 |
iya | -0.030 |
Token | mess |
Token ID | 2085 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
tha | +0.015 |
flake | +0.015 |
la | +0.015 |
essa | +0.015 |
iya | +0.015 |
Neg logit contributions | |
brothers | -0.009 |
more | -0.009 |
promises | -0.008 |
friends | -0.008 |
chambers | -0.008 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
mun | +0.056 |
chambers | +0.055 |
brothers | +0.051 |
ins | +0.049 |
goals | +0.049 |
Neg logit contributions | |
tha | -0.047 |
flake | -0.044 |
icol | -0.042 |
iya | -0.042 |
essa | -0.041 |
Token | said |
Token ID | 531 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
brothers | +0.063 |
mun | +0.053 |
chambers | +0.051 |
more | +0.050 |
promises | +0.050 |
Neg logit contributions | |
icol | -0.110 |
tha | -0.109 |
flake | -0.109 |
iya | -0.107 |
peac | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
more | +0.013 |
brothers | +0.013 |
of | +0.013 |
friends | +0.010 |
mun | +0.010 |
Neg logit contributions | |
icol | -0.048 |
iya | -0.048 |
peac | -0.048 |
flake | -0.047 |
AR | -0.047 |
Token | " |
Token ID | 366 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
brothers | +0.015 |
more | +0.012 |
mun | +0.011 |
questions | +0.010 |
of | +0.010 |
Neg logit contributions | |
icol | -0.055 |
flake | -0.055 |
tha | -0.055 |
iya | -0.054 |
peac | -0.054 |
Token | C |
Token ID | 34 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
brothers | +0.025 |
mun | +0.024 |
ins | +0.023 |
of | +0.022 |
more | +0.022 |
Neg logit contributions | |
tha | -0.043 |
icol | -0.043 |
essa | -0.039 |
iya | -0.039 |
peac | -0.038 |
Token | oc |
Token ID | 420 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
brothers | +0.066 |
chambers | +0.064 |
mun | +0.062 |
promises | +0.061 |
more | +0.058 |
Neg logit contributions | |
tha | -0.054 |
flake | -0.053 |
icol | -0.051 |
peac | -0.050 |
iya | -0.050 |
Token | oa |
Token ID | 12162 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
brothers | +0.248 |
ins | +0.227 |
mun | +0.227 |
promises | +0.221 |
chambers | +0.217 |
Neg logit contributions | |
iya | -0.202 |
icol | -0.201 |
peac | -0.199 |
tha | -0.193 |
flake | -0.191 |
Token | is |
Token ID | 318 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
brothers | +0.026 |
mun | +0.021 |
chambers | +0.021 |
ins | +0.020 |
more | +0.020 |
Neg logit contributions | |
icol | -0.044 |
peac | -0.042 |
AR | -0.042 |
tha | -0.041 |
flake | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
brothers | +0.009 |
more | +0.008 |
chambers | +0.007 |
friends | +0.007 |
y | +0.007 |
Neg logit contributions | |
icol | -0.018 |
flake | -0.018 |
tha | -0.018 |
peac | -0.018 |
iya | -0.018 |
Token | strong |
Token ID | 1913 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
y | +0.020 |
brothers | +0.019 |
more | +0.018 |
cookies | +0.016 |
sleepy | +0.015 |
Neg logit contributions | |
tha | -0.063 |
la | -0.062 |
essa | -0.061 |
oot | -0.059 |
iya | -0.059 |
Token | drink |
Token ID | 4144 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
brothers | +0.010 |
more | +0.009 |
of | +0.008 |
promises | +0.008 |
mun | +0.008 |
Neg logit contributions | |
tha | -0.021 |
la | -0.021 |
AR | -0.020 |
essa | -0.020 |
icol | -0.020 |
Token | She |
Token ID | 1375 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
tha | +0.025 |
flake | +0.024 |
iya | +0.024 |
icol | +0.024 |
peac | +0.023 |
Neg logit contributions | |
brothers | -0.009 |
chambers | -0.008 |
mun | -0.007 |
promises | -0.007 |
goals | -0.007 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
tha | +0.014 |
flake | +0.014 |
AR | +0.014 |
iya | +0.013 |
icol | +0.013 |
Neg logit contributions | |
brothers | -0.003 |
friends | -0.002 |
mun | -0.002 |
more | -0.002 |
happy | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
tha | +0.030 |
flake | +0.029 |
icol | +0.027 |
iya | +0.027 |
peac | +0.027 |
Neg logit contributions | |
brothers | -0.024 |
chambers | -0.022 |
mun | -0.021 |
more | -0.020 |
promises | -0.020 |
Token | eat |
Token ID | 4483 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
tha | +0.067 |
flake | +0.066 |
icol | +0.064 |
iya | +0.064 |
la | +0.063 |
Neg logit contributions | |
brothers | -0.027 |
chambers | -0.024 |
mun | -0.022 |
promises | -0.022 |
more | -0.021 |
Token | av |
Token ID | 1196 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
brothers | +0.018 |
chambers | +0.017 |
mun | +0.016 |
promises | +0.015 |
goals | +0.014 |
Neg logit contributions | |
flake | -0.031 |
tha | -0.030 |
essa | -0.030 |
iya | -0.030 |
peac | -0.030 |
Token | oc |
Token ID | 420 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
brothers | +0.050 |
chambers | +0.048 |
mun | +0.044 |
sisters | +0.044 |
questions | +0.043 |
Neg logit contributions | |
flake | -0.080 |
peac | -0.077 |
icol | -0.076 |
OW | -0.076 |
tha | -0.076 |
Token | ados |
Token ID | 22484 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
brothers | +0.201 |
chambers | +0.191 |
mun | +0.185 |
promises | +0.179 |
more | +0.170 |
Neg logit contributions | |
flake | -0.249 |
tha | -0.248 |
icol | -0.237 |
iya | -0.234 |
peac | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
flake | +0.027 |
tha | +0.027 |
iya | +0.025 |
peac | +0.025 |
essa | +0.025 |
Neg logit contributions | |
brothers | -0.017 |
chambers | -0.016 |
mun | -0.016 |
promises | -0.015 |
goals | -0.014 |
Token | One |
Token ID | 1881 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
brothers | +0.006 |
chambers | +0.005 |
mun | +0.005 |
promises | +0.005 |
more | +0.004 |
Neg logit contributions | |
tha | -0.012 |
flake | -0.012 |
icol | -0.011 |
iya | -0.011 |
peac | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
mun | +0.006 |
chambers | +0.006 |
goals | +0.006 |
brothers | +0.006 |
promises | +0.006 |
Neg logit contributions | |
flake | -0.004 |
tha | -0.004 |
iya | -0.004 |
storm | -0.004 |
peac | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
brothers | +0.030 |
chambers | +0.028 |
mun | +0.027 |
more | +0.025 |
promises | +0.025 |
Neg logit contributions | |
flake | -0.053 |
tha | -0.053 |
icol | -0.051 |
iya | -0.050 |
peac | -0.050 |
Token | 't |
Token ID | 470 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
brothers | +0.030 |
of | +0.028 |
mun | +0.028 |
chambers | +0.028 |
more | +0.028 |
Neg logit contributions | |
icol | -0.018 |
flake | -0.018 |
tha | -0.017 |
iya | -0.017 |
peac | -0.017 |
Token | touch |
Token ID | 3638 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
icol | +0.015 |
flake | +0.015 |
tha | +0.015 |
la | +0.014 |
iya | +0.014 |
Neg logit contributions | |
friends | -0.006 |
of | -0.006 |
more | -0.006 |
brothers | -0.006 |
promises | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
more | +0.008 |
brothers | +0.008 |
friends | +0.007 |
of | +0.007 |
ways | +0.007 |
Neg logit contributions | |
icol | -0.013 |
tha | -0.012 |
flake | -0.012 |
iya | -0.012 |
peac | -0.011 |
Token | rh |
Token ID | 9529 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
brothers | +0.008 |
more | +0.007 |
friends | +0.007 |
cookies | +0.007 |
chambers | +0.007 |
Neg logit contributions | |
tha | -0.013 |
icol | -0.012 |
iya | -0.012 |
enda | -0.012 |
da | -0.012 |
Token | in |
Token ID | 259 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
brothers | +0.012 |
chambers | +0.012 |
mun | +0.011 |
promises | +0.011 |
more | +0.010 |
Neg logit contributions | |
tha | -0.021 |
flake | -0.021 |
icol | -0.020 |
iya | -0.020 |
peac | -0.020 |
Token | oc |
Token ID | 420 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
tha | +0.040 |
icol | +0.039 |
iya | +0.038 |
essa | +0.038 |
flake | +0.038 |
Neg logit contributions | |
brothers | -0.008 |
chambers | -0.006 |
mun | -0.005 |
more | -0.005 |
promises | -0.005 |
Token | eros |
Token ID | 27498 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
brothers | +0.278 |
mun | +0.257 |
promises | +0.256 |
ins | +0.244 |
chambers | +0.243 |
Neg logit contributions | |
flake | -0.167 |
iya | -0.167 |
icol | -0.165 |
tha | -0.162 |
Gina | -0.161 |
Token | ! |
Token ID | 0 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
icol | +0.005 |
tha | +0.005 |
iya | +0.005 |
essa | +0.005 |
peac | +0.005 |
Neg logit contributions | |
brothers | -0.006 |
more | -0.006 |
chambers | -0.006 |
promises | -0.006 |
of | -0.006 |
Token | It |
Token ID | 632 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
tha | +0.036 |
flake | +0.035 |
icol | +0.035 |
iya | +0.034 |
peac | +0.034 |
Neg logit contributions | |
brothers | -0.021 |
So | -0.017 |
of | -0.017 |
chambers | -0.017 |
promises | -0.016 |
Token | might |
Token ID | 1244 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
brothers | +0.008 |
chambers | +0.007 |
mun | +0.007 |
promises | +0.007 |
more | +0.007 |
Neg logit contributions | |
tha | -0.021 |
flake | -0.020 |
iya | -0.020 |
icol | -0.020 |
essa | -0.020 |
Token | bite |
Token ID | 13197 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
more | +0.018 |
of | +0.016 |
chew | +0.014 |
y | +0.014 |
other | +0.014 |
Neg logit contributions | |
icol | -0.053 |
iya | -0.050 |
tha | -0.050 |
essa | -0.049 |
la | -0.049 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
flake | +0.027 |
tha | +0.026 |
icol | +0.026 |
iya | +0.025 |
OW | +0.025 |
Neg logit contributions | |
brothers | -0.013 |
more | -0.012 |
friends | -0.011 |
questions | -0.010 |
of | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
tha | +0.063 |
opter | +0.062 |
flake | +0.062 |
icol | +0.062 |
iya | +0.061 |
Neg logit contributions | |
more | -0.029 |
brothers | -0.026 |
friends | -0.025 |
of | -0.025 |
promises | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
brothers | +0.015 |
more | +0.013 |
promises | +0.013 |
chambers | +0.013 |
friends | +0.012 |
Neg logit contributions | |
flake | -0.035 |
icol | -0.033 |
tha | -0.033 |
iya | -0.033 |
storm | -0.032 |
Token | rh |
Token ID | 9529 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
brothers | +0.023 |
friends | +0.021 |
chambers | +0.020 |
more | +0.020 |
promises | +0.020 |
Neg logit contributions | |
tha | -0.025 |
flake | -0.025 |
icol | -0.025 |
iya | -0.024 |
la | -0.024 |
Token | in |
Token ID | 259 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
brothers | +0.023 |
chambers | +0.021 |
mun | +0.021 |
promises | +0.020 |
more | +0.018 |
Neg logit contributions | |
tha | -0.041 |
flake | -0.041 |
icol | -0.040 |
iya | -0.039 |
peac | -0.039 |
Token | oc |
Token ID | 420 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
flake | +0.013 |
tha | +0.013 |
peac | +0.013 |
iya | +0.013 |
icol | +0.013 |
Neg logit contributions | |
brothers | -0.005 |
chambers | -0.004 |
mun | -0.004 |
promises | -0.004 |
goals | -0.004 |
Token | eros |
Token ID | 27498 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
brothers | +0.262 |
promises | +0.250 |
mun | +0.237 |
chambers | +0.235 |
ins | +0.225 |
Neg logit contributions | |
iya | -0.172 |
icol | -0.169 |
Gina | -0.167 |
flake | -0.165 |
essa | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
brothers | +0.016 |
chambers | +0.015 |
mun | +0.015 |
promises | +0.013 |
goals | +0.012 |
Neg logit contributions | |
flake | -0.034 |
tha | -0.033 |
peac | -0.032 |
iya | -0.032 |
icol | -0.032 |
Token | They |
Token ID | 1119 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
brothers | +0.004 |
chambers | +0.004 |
So | +0.003 |
promises | +0.003 |
more | +0.003 |
Neg logit contributions | |
flake | -0.016 |
tha | -0.016 |
iya | -0.016 |
essa | -0.015 |
ich | -0.015 |
Token | say |
Token ID | 910 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
tha | +0.009 |
flake | +0.009 |
icol | +0.008 |
peac | +0.008 |
iya | +0.008 |
Neg logit contributions | |
brothers | -0.005 |
chambers | -0.005 |
mun | -0.005 |
promises | -0.004 |
ins | -0.004 |
Token | they |
Token ID | 484 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
flake | +0.020 |
tha | +0.020 |
icol | +0.019 |
iya | +0.019 |
OW | +0.019 |
Neg logit contributions | |
brothers | -0.011 |
more | -0.010 |
friends | -0.009 |
chambers | -0.009 |
questions | -0.009 |
Token | € |
Token ID | 26391 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
peac | +0.045 |
flake | +0.043 |
icol | +0.042 |
iya | +0.042 |
tha | +0.042 |
Neg logit contributions | |
brothers | -0.047 |
promises | -0.046 |
mun | -0.045 |
more | -0.041 |
chambers | -0.041 |
Token | replied |
Token ID | 8712 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
brothers | +0.010 |
mun | +0.009 |
promises | +0.009 |
friends | +0.008 |
chambers | +0.008 |
Neg logit contributions | |
flake | -0.016 |
tha | -0.015 |
essa | -0.015 |
peac | -0.015 |
work | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
flake | +0.004 |
tha | +0.004 |
storm | +0.004 |
peac | +0.003 |
iya | +0.003 |
Neg logit contributions | |
of | -0.001 |
brothers | -0.001 |
friends | -0.001 |
more | -0.001 |
his | -0.001 |
Token | rh |
Token ID | 9529 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
brothers | +0.022 |
friends | +0.018 |
more | +0.018 |
chambers | +0.018 |
goals | +0.017 |
Neg logit contributions | |
tha | -0.035 |
flake | -0.034 |
icol | -0.033 |
iya | -0.032 |
essa | -0.032 |
Token | in |
Token ID | 259 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
brothers | +0.015 |
chambers | +0.014 |
mun | +0.013 |
promises | +0.012 |
more | +0.012 |
Neg logit contributions | |
tha | -0.029 |
flake | -0.029 |
icol | -0.028 |
iya | -0.028 |
peac | -0.027 |
Token | oc |
Token ID | 420 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
tha | +0.030 |
icol | +0.029 |
iya | +0.029 |
essa | +0.029 |
flake | +0.028 |
Neg logit contributions | |
brothers | -0.005 |
chambers | -0.003 |
more | -0.003 |
mun | -0.003 |
promises | -0.003 |
Token | eros |
Token ID | 27498 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
brothers | +0.268 |
promises | +0.249 |
ins | +0.241 |
mun | +0.241 |
chambers | +0.238 |
Neg logit contributions | |
iya | -0.169 |
icol | -0.165 |
tha | -0.163 |
flake | -0.163 |
storm | -0.162 |
Token | sadly |
Token ID | 21098 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
brothers | +0.005 |
more | +0.004 |
friends | +0.004 |
promises | +0.004 |
chambers | +0.004 |
Neg logit contributions | |
icol | -0.011 |
tha | -0.010 |
iya | -0.010 |
flake | -0.010 |
essa | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
brothers | +0.012 |
more | +0.012 |
promises | +0.011 |
friends | +0.011 |
of | +0.010 |
Neg logit contributions | |
tha | -0.039 |
iya | -0.039 |
flake | -0.038 |
peac | -0.037 |
AR | -0.037 |
Token | It |
Token ID | 632 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
brothers | +0.014 |
So | +0.011 |
mun | +0.010 |
promises | +0.010 |
of | +0.010 |
Neg logit contributions | |
flake | -0.038 |
tha | -0.036 |
peac | -0.035 |
iya | -0.035 |
storm | -0.035 |
Token | had |
Token ID | 550 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
brothers | +0.017 |
mun | +0.015 |
chambers | +0.015 |
promises | +0.015 |
more | +0.014 |
Neg logit contributions | |
tha | -0.035 |
flake | -0.035 |
icol | -0.034 |
iya | -0.034 |
essa | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
more | +0.034 |
brothers | +0.031 |
promises | +0.030 |
friends | +0.029 |
y | +0.029 |
Neg logit contributions | |
flake | -0.046 |
tha | -0.045 |
iya | -0.043 |
ich | -0.042 |
peac | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
icol | +0.039 |
tha | +0.039 |
iya | +0.039 |
flake | +0.039 |
peac | +0.039 |
Neg logit contributions | |
brothers | -0.018 |
more | -0.017 |
promises | -0.015 |
chambers | -0.015 |
mun | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
brothers | +0.015 |
chambers | +0.012 |
mun | +0.012 |
friends | +0.012 |
more | +0.012 |
Neg logit contributions | |
flake | -0.035 |
tha | -0.035 |
icol | -0.034 |
iya | -0.034 |
OW | -0.034 |
Token | rh |
Token ID | 9529 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
brothers | +0.033 |
friends | +0.029 |
more | +0.028 |
chambers | +0.027 |
promises | +0.026 |
Neg logit contributions | |
tha | -0.037 |
flake | -0.037 |
icol | -0.036 |
iya | -0.035 |
enda | -0.035 |
Token | in |
Token ID | 259 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
brothers | +0.014 |
chambers | +0.013 |
mun | +0.012 |
promises | +0.012 |
more | +0.011 |
Neg logit contributions | |
tha | -0.027 |
flake | -0.026 |
icol | -0.026 |
iya | -0.025 |
peac | -0.025 |
Token | oc |
Token ID | 420 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
tha | +0.024 |
icol | +0.024 |
flake | +0.024 |
iya | +0.024 |
essa | +0.024 |
Neg logit contributions | |
brothers | -0.005 |
chambers | -0.003 |
mun | -0.003 |
promises | -0.003 |
more | -0.003 |
Token | eros |
Token ID | 27498 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
brothers | +0.275 |
promises | +0.254 |
mun | +0.247 |
chambers | +0.244 |
ins | +0.237 |
Neg logit contributions | |
flake | -0.170 |
iya | -0.170 |
icol | -0.163 |
essa | -0.162 |
tha | -0.161 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
brothers | +0.000 |
more | +0.000 |
mun | +0.000 |
friends | +0.000 |
chambers | +0.000 |
Neg logit contributions | |
icol | -0.001 |
tha | -0.001 |
flake | -0.001 |
iya | -0.001 |
essa | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
brothers | +0.009 |
chambers | +0.008 |
more | +0.008 |
promises | +0.008 |
mun | +0.008 |
Neg logit contributions | |
tha | -0.020 |
flake | -0.020 |
iya | -0.019 |
icol | -0.019 |
peac | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
brothers | +0.001 |
chambers | +0.001 |
So | +0.001 |
mun | +0.001 |
friends | +0.001 |
Neg logit contributions | |
flake | -0.003 |
tha | -0.003 |
peac | -0.003 |
iya | -0.003 |
storm | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
brothers | +0.005 |
more | +0.004 |
friends | +0.004 |
mun | +0.003 |
promises | +0.003 |
Neg logit contributions | |
tha | -0.014 |
flake | -0.014 |
AR | -0.013 |
storm | -0.013 |
essa | -0.013 |
Token | I |
Token ID | 40 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
brothers | +0.009 |
mun | +0.009 |
chambers | +0.008 |
promises | +0.008 |
more | +0.008 |
Neg logit contributions | |
tha | -0.013 |
flake | -0.013 |
icol | -0.013 |
iya | -0.012 |
peac | -0.012 |
Token | will |
Token ID | 481 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
brothers | +0.001 |
mun | +0.001 |
promises | +0.001 |
chambers | +0.001 |
more | +0.001 |
Neg logit contributions | |
tha | -0.001 |
flake | -0.001 |
icol | -0.001 |
iya | -0.001 |
peac | -0.001 |
Token | buy |
Token ID | 2822 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
flake | +0.095 |
icol | +0.092 |
la | +0.091 |
tha | +0.090 |
ert | +0.089 |
Neg logit contributions | |
brothers | -0.025 |
of | -0.023 |
friends | -0.022 |
more | -0.021 |
promises | -0.021 |
Token | more |
Token ID | 517 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
more | +0.023 |
brothers | +0.022 |
friends | +0.021 |
promises | +0.020 |
cookies | +0.020 |
Neg logit contributions | |
flake | -0.034 |
storm | -0.033 |
icol | -0.032 |
tha | -0.032 |
iya | -0.031 |
Token | av |
Token ID | 1196 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
brothers | +0.037 |
chambers | +0.034 |
mun | +0.033 |
promises | +0.030 |
more | +0.028 |
Neg logit contributions | |
tha | -0.085 |
flake | -0.084 |
icol | -0.082 |
peac | -0.081 |
iya | -0.081 |
Token | oc |
Token ID | 420 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
brothers | +0.061 |
chambers | +0.059 |
sisters | +0.055 |
cabinets | +0.053 |
mun | +0.053 |
Neg logit contributions | |
flake | -0.087 |
tha | -0.085 |
peac | -0.085 |
OW | -0.084 |
icol | -0.082 |
Token | ados |
Token ID | 22484 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
brothers | +0.187 |
chambers | +0.172 |
mun | +0.169 |
promises | +0.165 |
ins | +0.154 |
Neg logit contributions | |
flake | -0.265 |
tha | -0.258 |
icol | -0.249 |
iya | -0.248 |
peac | -0.245 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
tha | +0.013 |
icol | +0.013 |
flake | +0.013 |
peac | +0.012 |
iya | +0.012 |
Neg logit contributions | |
brothers | -0.006 |
chambers | -0.006 |
more | -0.006 |
mun | -0.005 |
promises | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
brothers | +0.028 |
more | +0.026 |
chambers | +0.025 |
of | +0.024 |
promises | +0.024 |
Neg logit contributions | |
peac | -0.060 |
icol | -0.058 |
tha | -0.058 |
flake | -0.058 |
iya | -0.055 |
Token | You |
Token ID | 921 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
brothers | +0.010 |
chambers | +0.009 |
mun | +0.009 |
promises | +0.009 |
more | +0.009 |
Neg logit contributions | |
flake | -0.012 |
tha | -0.012 |
iya | -0.012 |
icol | -0.011 |
peac | -0.011 |
Token | can |
Token ID | 460 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
brothers | +0.018 |
chambers | +0.016 |
promises | +0.015 |
more | +0.014 |
mun | +0.014 |
Neg logit contributions | |
icol | -0.049 |
tha | -0.048 |
flake | -0.048 |
iya | -0.047 |
essa | -0.046 |
Token | book |
Token ID | 1492 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
flake | +0.004 |
tha | +0.003 |
peac | +0.003 |
icol | +0.003 |
iya | +0.003 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
mun | -0.002 |
promises | -0.002 |
ins | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
flake | +0.001 |
tha | +0.001 |
icol | +0.001 |
peac | +0.001 |
iya | +0.001 |
Neg logit contributions | |
brothers | -0.000 |
chambers | -0.000 |
mun | -0.000 |
promises | -0.000 |
goals | -0.000 |
Token | The |
Token ID | 383 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
brothers | +0.005 |
chambers | +0.004 |
So | +0.004 |
mun | +0.004 |
promises | +0.004 |
Neg logit contributions | |
tha | -0.017 |
flake | -0.016 |
peac | -0.016 |
iya | -0.016 |
essa | -0.016 |
Token | rh |
Token ID | 9529 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
brothers | +0.003 |
chambers | +0.003 |
mun | +0.003 |
more | +0.003 |
promises | +0.003 |
Neg logit contributions | |
flake | -0.003 |
tha | -0.003 |
icol | -0.003 |
iya | -0.003 |
essa | -0.003 |
Token | in |
Token ID | 259 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
brothers | +0.028 |
chambers | +0.027 |
mun | +0.025 |
promises | +0.025 |
goals | +0.023 |
Neg logit contributions | |
flake | -0.045 |
tha | -0.045 |
peac | -0.043 |
iya | -0.042 |
essa | -0.041 |
Token | oc |
Token ID | 420 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
tha | +0.003 |
flake | +0.003 |
icol | +0.003 |
iya | +0.003 |
peac | +0.003 |
Neg logit contributions | |
brothers | -0.001 |
chambers | -0.001 |
mun | -0.001 |
promises | -0.001 |
more | -0.001 |
Token | eros |
Token ID | 27498 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
brothers | +0.279 |
promises | +0.262 |
chambers | +0.255 |
mun | +0.254 |
ins | +0.246 |
Neg logit contributions | |
iya | -0.160 |
flake | -0.154 |
icol | -0.152 |
tha | -0.150 |
storm | -0.148 |
Token | was |
Token ID | 373 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
brothers | +0.019 |
chambers | +0.017 |
mun | +0.016 |
promises | +0.016 |
more | +0.016 |
Neg logit contributions | |
tha | -0.039 |
flake | -0.038 |
icol | -0.038 |
iya | -0.037 |
essa | -0.037 |
Token | mesmer |
Token ID | 46814 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
brothers | +0.002 |
more | +0.002 |
chambers | +0.002 |
friends | +0.002 |
promises | +0.002 |
Neg logit contributions | |
flake | -0.005 |
tha | -0.005 |
icol | -0.005 |
iya | -0.005 |
essa | -0.005 |
Token | ized |
Token ID | 1143 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
flake | +0.023 |
tha | +0.022 |
icol | +0.022 |
peac | +0.022 |
storm | +0.021 |
Neg logit contributions | |
brothers | -0.022 |
chambers | -0.020 |
more | -0.020 |
promises | -0.019 |
mun | -0.019 |
Token | by |
Token ID | 416 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
flake | +0.004 |
tha | +0.004 |
icol | +0.004 |
peac | +0.004 |
iya | +0.004 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
mun | -0.002 |
promises | -0.002 |
goals | -0.002 |
Token | Unicorn |
Token ID | 39481 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
brothers | +0.024 |
friends | +0.021 |
promises | +0.020 |
more | +0.020 |
chambers | +0.019 |
Neg logit contributions | |
flake | -0.034 |
tha | -0.032 |
icol | -0.032 |
iya | -0.031 |
essa | -0.031 |
Token | !" |
Token ID | 2474 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
brothers | +0.004 |
friends | +0.003 |
mun | +0.003 |
of | +0.003 |
more | +0.003 |
Neg logit contributions | |
icol | -0.003 |
tha | -0.003 |
flake | -0.003 |
AR | -0.003 |
iya | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
flake | +0.057 |
tha | +0.055 |
ich | +0.054 |
icol | +0.054 |
OW | +0.053 |
Neg logit contributions | |
brothers | -0.022 |
friends | -0.018 |
chambers | -0.017 |
more | -0.017 |
mun | -0.016 |
Token | rh |
Token ID | 9529 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
tha | +0.023 |
flake | +0.023 |
icol | +0.023 |
OW | +0.022 |
storm | +0.022 |
Neg logit contributions | |
brothers | -0.013 |
friends | -0.012 |
more | -0.010 |
sisters | -0.010 |
other | -0.010 |
Token | in |
Token ID | 259 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
brothers | +0.009 |
chambers | +0.008 |
mun | +0.008 |
promises | +0.007 |
more | +0.007 |
Neg logit contributions | |
tha | -0.017 |
icol | -0.017 |
flake | -0.017 |
iya | -0.016 |
peac | -0.016 |
Token | oc |
Token ID | 420 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
tha | +0.035 |
flake | +0.035 |
icol | +0.035 |
iya | +0.034 |
essa | +0.034 |
Neg logit contributions | |
brothers | -0.010 |
mun | -0.007 |
chambers | -0.007 |
promises | -0.007 |
friends | -0.007 |
Token | eros |
Token ID | 27498 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
brothers | +0.267 |
promises | +0.249 |
mun | +0.246 |
ins | +0.240 |
chambers | +0.238 |
Neg logit contributions | |
iya | -0.170 |
icol | -0.168 |
flake | -0.166 |
storm | -0.164 |
Gina | -0.164 |
Token | said |
Token ID | 531 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
brothers | +0.003 |
chambers | +0.003 |
mun | +0.002 |
promises | +0.002 |
more | +0.002 |
Neg logit contributions | |
tha | -0.005 |
flake | -0.005 |
icol | -0.005 |
iya | -0.005 |
essa | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
brothers | +0.002 |
more | +0.002 |
friends | +0.002 |
of | +0.002 |
mun | +0.002 |
Neg logit contributions | |
tha | -0.008 |
icol | -0.008 |
flake | -0.008 |
iya | -0.008 |
peac | -0.008 |
Token | feeling |
Token ID | 4203 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
brothers | +0.012 |
more | +0.010 |
mun | +0.010 |
friends | +0.009 |
promises | +0.009 |
Neg logit contributions | |
tha | -0.025 |
flake | -0.025 |
la | -0.024 |
iya | -0.024 |
essa | -0.024 |
Token | much |
Token ID | 881 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
chambers | +0.020 |
brothers | +0.019 |
mun | +0.019 |
promises | +0.016 |
ins | +0.016 |
Neg logit contributions | |
flake | -0.038 |
peac | -0.037 |
tha | -0.037 |
icol | -0.037 |
iya | -0.036 |
Token | fence |
Token ID | 13990 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
brothers | +0.019 |
chambers | +0.017 |
more | +0.017 |
friends | +0.016 |
promises | +0.015 |
Neg logit contributions | |
tha | -0.027 |
flake | -0.027 |
iya | -0.026 |
icol | -0.026 |
essa | -0.026 |
Token | where |
Token ID | 810 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
brothers | +0.023 |
more | +0.022 |
of | +0.021 |
chambers | +0.021 |
promises | +0.019 |
Neg logit contributions | |
tha | -0.065 |
flake | -0.064 |
icol | -0.064 |
iya | -0.064 |
OW | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
brothers | +0.016 |
chambers | +0.015 |
mun | +0.014 |
promises | +0.013 |
more | +0.013 |
Neg logit contributions | |
flake | -0.030 |
tha | -0.029 |
icol | -0.029 |
iya | -0.028 |
peac | -0.028 |
Token | rh |
Token ID | 9529 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
brothers | +0.010 |
friends | +0.008 |
chambers | +0.008 |
more | +0.008 |
other | +0.008 |
Neg logit contributions | |
tha | -0.012 |
icol | -0.012 |
flake | -0.012 |
enda | -0.011 |
iya | -0.011 |
Token | in |
Token ID | 259 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
brothers | +0.009 |
chambers | +0.008 |
mun | +0.008 |
promises | +0.008 |
more | +0.007 |
Neg logit contributions | |
flake | -0.015 |
tha | -0.015 |
peac | -0.014 |
iya | -0.014 |
icol | -0.014 |
Token | oc |
Token ID | 420 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
flake | +0.039 |
tha | +0.039 |
icol | +0.037 |
peac | +0.037 |
iya | +0.037 |
Neg logit contributions | |
brothers | -0.012 |
chambers | -0.011 |
mun | -0.011 |
promises | -0.010 |
goals | -0.009 |
Token | eros |
Token ID | 27498 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
brothers | +0.277 |
promises | +0.252 |
chambers | +0.250 |
mun | +0.247 |
more | +0.239 |
Neg logit contributions | |
iya | -0.167 |
flake | -0.166 |
icol | -0.162 |
essa | -0.161 |
tha | -0.159 |
Token | was |
Token ID | 373 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
tha | +0.007 |
flake | +0.007 |
icol | +0.006 |
iya | +0.006 |
essa | +0.006 |
Neg logit contributions | |
brothers | -0.003 |
chambers | -0.003 |
mun | -0.003 |
promises | -0.002 |
more | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
tha | +0.018 |
icol | +0.018 |
flake | +0.018 |
iya | +0.018 |
essa | +0.018 |
Neg logit contributions | |
brothers | -0.008 |
more | -0.007 |
chambers | -0.007 |
friends | -0.006 |
of | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
flake | +0.004 |
tha | +0.004 |
peac | +0.004 |
iya | +0.004 |
icol | +0.004 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
mun | -0.001 |
promises | -0.001 |
more | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
brothers | +0.004 |
mun | +0.004 |
chambers | +0.004 |
more | +0.004 |
friends | +0.004 |
Neg logit contributions | |
flake | -0.011 |
icol | -0.010 |
tha | -0.010 |
essa | -0.010 |
storm | -0.010 |
Token | Did |
Token ID | 7731 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
flake | +0.018 |
tha | +0.017 |
iya | +0.017 |
essa | +0.016 |
icol | +0.016 |
Neg logit contributions | |
brothers | -0.015 |
chambers | -0.013 |
promises | -0.013 |
mun | -0.013 |
friends | -0.012 |
Token | you |
Token ID | 345 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
brothers | +0.069 |
friends | +0.062 |
more | +0.062 |
chambers | +0.062 |
promises | +0.062 |
Neg logit contributions | |
flake | -0.078 |
icol | -0.075 |
tha | -0.075 |
iya | -0.071 |
storm | -0.070 |
Token | know |
Token ID | 760 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
brothers | +0.007 |
of | +0.007 |
more | +0.007 |
friends | +0.006 |
promises | +0.005 |
Neg logit contributions | |
icol | -0.024 |
tha | -0.024 |
iya | -0.022 |
essa | -0.022 |
flake | -0.022 |
Token | that |
Token ID | 326 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
brothers | +0.022 |
more | +0.021 |
chambers | +0.019 |
friends | +0.018 |
ways | +0.017 |
Neg logit contributions | |
icol | -0.066 |
flake | -0.066 |
tha | -0.065 |
iya | -0.064 |
OW | -0.062 |
Token | av |
Token ID | 1196 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
tha | +0.008 |
icol | +0.008 |
flake | +0.008 |
iya | +0.008 |
essa | +0.008 |
Neg logit contributions | |
brothers | -0.007 |
more | -0.006 |
chambers | -0.006 |
friends | -0.006 |
promises | -0.006 |
Token | oc |
Token ID | 420 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
brothers | +0.046 |
chambers | +0.046 |
mun | +0.041 |
promises | +0.038 |
questions | +0.037 |
Neg logit contributions | |
flake | -0.102 |
tha | -0.098 |
peac | -0.098 |
OW | -0.096 |
icol | -0.095 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
brothers | +0.176 |
mun | +0.154 |
chambers | +0.152 |
promises | +0.151 |
ins | +0.144 |
Neg logit contributions | |
flake | -0.277 |
tha | -0.270 |
icol | -0.265 |
iya | -0.264 |
peac | -0.255 |
Token | are |
Token ID | 389 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
icol | +0.030 |
tha | +0.029 |
iya | +0.028 |
flake | +0.028 |
peac | +0.027 |
Neg logit contributions | |
brothers | -0.010 |
chambers | -0.008 |
of | -0.008 |
mun | -0.008 |
more | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
icol | +0.003 |
flake | +0.003 |
tha | +0.003 |
iya | +0.003 |
essa | +0.003 |
Neg logit contributions | |
brothers | -0.002 |
more | -0.002 |
chambers | -0.002 |
friends | -0.002 |
questions | -0.002 |
Token | healthy |
Token ID | 5448 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
brothers | +0.005 |
chambers | +0.004 |
more | +0.004 |
promises | +0.004 |
mun | +0.004 |
Neg logit contributions | |
flake | -0.010 |
tha | -0.010 |
icol | -0.010 |
iya | -0.009 |
peac | -0.009 |
Token | for |
Token ID | 329 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
brothers | +0.023 |
chambers | +0.021 |
more | +0.020 |
promises | +0.019 |
friends | +0.019 |
Neg logit contributions | |
tha | -0.039 |
icol | -0.038 |
flake | -0.037 |
peac | -0.037 |
iya | -0.037 |
Token | net |
Token ID | 2010 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
icol | +0.046 |
tha | +0.045 |
enda | +0.044 |
iya | +0.044 |
essa | +0.043 |
Neg logit contributions | |
brothers | -0.034 |
more | -0.031 |
friends | -0.030 |
promises | -0.029 |
chambers | -0.029 |
Token | on |
Token ID | 319 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
tha | +0.091 |
flake | +0.090 |
icol | +0.088 |
iya | +0.087 |
peac | +0.086 |
Neg logit contributions | |
brothers | -0.050 |
chambers | -0.047 |
mun | -0.044 |
promises | -0.043 |
more | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
more | +0.007 |
brothers | +0.006 |
other | +0.005 |
his | +0.004 |
chores | +0.004 |
Neg logit contributions | |
icol | -0.031 |
storm | -0.031 |
flake | -0.031 |
opter | -0.030 |
peac | -0.030 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
brothers | +0.003 |
more | +0.003 |
chambers | +0.003 |
other | +0.003 |
friends | +0.002 |
Neg logit contributions | |
tha | -0.005 |
la | -0.005 |
enda | -0.005 |
iya | -0.005 |
flake | -0.005 |
Token | in |
Token ID | 259 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
brothers | +0.006 |
chambers | +0.006 |
mun | +0.006 |
promises | +0.005 |
more | +0.005 |
Neg logit contributions | |
flake | -0.010 |
tha | -0.009 |
iya | -0.009 |
peac | -0.009 |
essa | -0.009 |
Token | oc |
Token ID | 420 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
flake | +0.031 |
tha | +0.030 |
peac | +0.029 |
iya | +0.029 |
icol | +0.029 |
Neg logit contributions | |
brothers | -0.012 |
chambers | -0.011 |
mun | -0.011 |
promises | -0.010 |
goals | -0.009 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
brothers | +0.274 |
promises | +0.257 |
chambers | +0.251 |
mun | +0.241 |
goals | +0.239 |
Neg logit contributions | |
flake | -0.162 |
iya | -0.159 |
essa | -0.156 |
la | -0.155 |
tha | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
flake | +0.002 |
tha | +0.002 |
peac | +0.002 |
iya | +0.002 |
icol | +0.001 |
Neg logit contributions | |
brothers | -0.001 |
mun | -0.001 |
chambers | -0.001 |
promises | -0.001 |
ins | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
flake | +0.003 |
tha | +0.003 |
essa | +0.003 |
iya | +0.003 |
peac | +0.003 |
Neg logit contributions | |
brothers | -0.001 |
chambers | -0.001 |
promises | -0.001 |
So | -0.001 |
of | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
tha | +0.024 |
flake | +0.024 |
icol | +0.023 |
iya | +0.023 |
essa | +0.023 |
Neg logit contributions | |
brothers | -0.013 |
chambers | -0.012 |
mun | -0.012 |
promises | -0.011 |
more | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
flake | +0.037 |
tha | +0.037 |
icol | +0.037 |
iya | +0.037 |
peac | +0.036 |
Neg logit contributions | |
brothers | -0.022 |
chambers | -0.020 |
promises | -0.020 |
more | -0.020 |
mun | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
tha | +0.029 |
flake | +0.029 |
icol | +0.028 |
iya | +0.028 |
peac | +0.028 |
Neg logit contributions | |
brothers | -0.015 |
chambers | -0.014 |
mun | -0.013 |
promises | -0.013 |
more | -0.012 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
tha | +0.012 |
flake | +0.012 |
AR | +0.012 |
icol | +0.012 |
chie | +0.012 |
Neg logit contributions | |
brothers | -0.002 |
friends | -0.002 |
mun | -0.002 |
more | -0.001 |
happy | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
tha | +0.027 |
flake | +0.027 |
icol | +0.025 |
iya | +0.025 |
peac | +0.025 |
Neg logit contributions | |
brothers | -0.024 |
chambers | -0.023 |
mun | -0.022 |
promises | -0.022 |
more | -0.021 |
Token | eat |
Token ID | 4483 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
tha | +0.064 |
flake | +0.062 |
icol | +0.060 |
iya | +0.060 |
la | +0.060 |
Neg logit contributions | |
brothers | -0.023 |
chambers | -0.021 |
mun | -0.018 |
promises | -0.018 |
more | -0.018 |
Token | av |
Token ID | 1196 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
brothers | +0.018 |
chambers | +0.018 |
mun | +0.016 |
promises | +0.016 |
goals | +0.015 |
Neg logit contributions | |
flake | -0.030 |
essa | -0.029 |
tha | -0.029 |
iya | -0.029 |
peac | -0.029 |
Token | oc |
Token ID | 420 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
brothers | +0.046 |
chambers | +0.043 |
mun | +0.041 |
sisters | +0.040 |
questions | +0.040 |
Neg logit contributions | |
flake | -0.072 |
peac | -0.069 |
icol | -0.069 |
tha | -0.068 |
OW | -0.068 |
Token | ados |
Token ID | 22484 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
brothers | +0.196 |
chambers | +0.187 |
mun | +0.181 |
promises | +0.175 |
more | +0.166 |
Neg logit contributions | |
flake | -0.239 |
tha | -0.239 |
icol | -0.227 |
iya | -0.225 |
peac | -0.224 |
Token | because |
Token ID | 780 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
flake | +0.029 |
tha | +0.029 |
essa | +0.027 |
iya | +0.027 |
peac | +0.027 |
Neg logit contributions | |
brothers | -0.020 |
chambers | -0.018 |
mun | -0.018 |
promises | -0.018 |
goals | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
brothers | +0.003 |
chambers | +0.003 |
mun | +0.003 |
promises | +0.003 |
goals | +0.002 |
Neg logit contributions | |
tha | -0.004 |
flake | -0.004 |
peac | -0.004 |
iya | -0.004 |
essa | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
tha | +0.038 |
flake | +0.038 |
peac | +0.036 |
iya | +0.036 |
icol | +0.036 |
Neg logit contributions | |
brothers | -0.019 |
chambers | -0.018 |
mun | -0.017 |
promises | -0.016 |
goals | -0.015 |
Token | y |
Token ID | 331 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
tha | +0.015 |
flake | +0.015 |
peac | +0.015 |
iya | +0.014 |
essa | +0.014 |
Neg logit contributions | |
chambers | -0.010 |
mun | -0.010 |
brothers | -0.010 |
promises | -0.010 |
goals | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
brothers | +0.002 |
chambers | +0.002 |
mun | +0.002 |
more | +0.002 |
promises | +0.002 |
Neg logit contributions | |
tha | -0.006 |
flake | -0.006 |
icol | -0.006 |
iya | -0.006 |
peac | -0.006 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
brothers | +0.011 |
chambers | +0.010 |
mun | +0.009 |
promises | +0.009 |
more | +0.008 |
Neg logit contributions | |
flake | -0.023 |
tha | -0.023 |
peac | -0.022 |
iya | -0.022 |
icol | -0.022 |
Token | Ben |
Token ID | 11696 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
brothers | +0.003 |
chambers | +0.003 |
promises | +0.003 |
mun | +0.003 |
questions | +0.002 |
Neg logit contributions | |
flake | -0.003 |
tha | -0.003 |
da | -0.003 |
iya | -0.003 |
icol | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
brothers | +0.000 |
chambers | +0.000 |
promises | +0.000 |
mun | +0.000 |
more | +0.000 |
Neg logit contributions | |
tha | -0.001 |
flake | -0.001 |
peac | -0.001 |
icol | -0.001 |
iya | -0.001 |
Token | Mia |
Token ID | 32189 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
brothers | +0.006 |
chambers | +0.005 |
friends | +0.005 |
promises | +0.005 |
mun | +0.005 |
Neg logit contributions | |
flake | -0.015 |
tha | -0.014 |
icol | -0.014 |
storm | -0.014 |
peac | -0.014 |
Token | like |
Token ID | 588 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
flake | +0.010 |
tha | +0.010 |
icol | +0.009 |
peac | +0.009 |
ich | +0.009 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
mun | -0.002 |
promises | -0.002 |
more | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
tha | +0.109 |
flake | +0.106 |
icol | +0.103 |
iya | +0.099 |
la | +0.098 |
Neg logit contributions | |
brothers | -0.081 |
chambers | -0.075 |
mun | -0.070 |
friends | -0.070 |
more | -0.069 |
Token | play |
Token ID | 711 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
tha | +0.045 |
flake | +0.045 |
icol | +0.043 |
iya | +0.043 |
peac | +0.042 |
Neg logit contributions | |
brothers | -0.018 |
chambers | -0.017 |
mun | -0.015 |
promises | -0.015 |
more | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
brothers | +0.014 |
chambers | +0.013 |
mun | +0.013 |
promises | +0.012 |
questions | +0.011 |
Neg logit contributions | |
flake | -0.019 |
tha | -0.018 |
icol | -0.017 |
peac | -0.017 |
iya | -0.017 |
Token | trains |
Token ID | 13404 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
tha | +0.016 |
flake | +0.016 |
iya | +0.015 |
peac | +0.015 |
icol | +0.015 |
Neg logit contributions | |
brothers | -0.009 |
chambers | -0.009 |
mun | -0.009 |
promises | -0.008 |
goals | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
flake | +0.053 |
tha | +0.052 |
peac | +0.051 |
icol | +0.050 |
iya | +0.050 |
Neg logit contributions | |
brothers | -0.024 |
chambers | -0.024 |
mun | -0.022 |
promises | -0.022 |
goals | -0.019 |
Token | rough |
Token ID | 5210 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
tha | +0.009 |
la | +0.008 |
iya | +0.008 |
icol | +0.008 |
essa | +0.008 |
Neg logit contributions | |
brothers | -0.004 |
more | -0.004 |
friends | -0.003 |
chambers | -0.003 |
y | -0.003 |
Token | paper |
Token ID | 3348 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
tha | +0.037 |
la | +0.035 |
iya | +0.034 |
nes | +0.032 |
icol | +0.032 |
Neg logit contributions | |
brothers | -0.016 |
more | -0.015 |
toys | -0.014 |
books | -0.014 |
chambers | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
tha | +0.055 |
iya | +0.053 |
icol | +0.053 |
OW | +0.053 |
flake | +0.052 |
Neg logit contributions | |
brothers | -0.024 |
chambers | -0.022 |
more | -0.020 |
friends | -0.019 |
promises | -0.019 |
Token | some |
Token ID | 617 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
brothers | +0.005 |
chambers | +0.004 |
mun | +0.004 |
promises | +0.004 |
more | +0.004 |
Neg logit contributions | |
tha | -0.007 |
flake | -0.007 |
icol | -0.007 |
peac | -0.007 |
iya | -0.007 |
Token | cr |
Token ID | 1067 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
brothers | +0.004 |
mun | +0.003 |
chambers | +0.003 |
promises | +0.003 |
ins | +0.003 |
Neg logit contributions | |
flake | -0.005 |
tha | -0.005 |
peac | -0.005 |
icol | -0.005 |
iya | -0.004 |
Token | ay |
Token ID | 323 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
tha | +0.009 |
flake | +0.008 |
iya | +0.008 |
peac | +0.008 |
icol | +0.008 |
Neg logit contributions | |
brothers | -0.008 |
chambers | -0.007 |
of | -0.007 |
ins | -0.006 |
more | -0.006 |
Token | ons |
Token ID | 684 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
tha | +0.122 |
flake | +0.122 |
icol | +0.118 |
iya | +0.117 |
peac | +0.116 |
Neg logit contributions | |
brothers | -0.052 |
chambers | -0.049 |
mun | -0.046 |
promises | -0.044 |
more | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
tha | +0.055 |
flake | +0.054 |
icol | +0.054 |
iya | +0.053 |
peac | +0.052 |
Neg logit contributions | |
brothers | -0.019 |
chambers | -0.016 |
more | -0.015 |
promises | -0.015 |
mun | -0.015 |
Token | They |
Token ID | 1119 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
brothers | +0.010 |
chambers | +0.010 |
mun | +0.010 |
promises | +0.009 |
more | +0.009 |
Neg logit contributions | |
tha | -0.016 |
flake | -0.016 |
icol | -0.016 |
iya | -0.015 |
essa | -0.015 |
Token | sit |
Token ID | 1650 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
brothers | +0.004 |
chambers | +0.004 |
mun | +0.004 |
promises | +0.003 |
more | +0.003 |
Neg logit contributions | |
tha | -0.006 |
flake | -0.006 |
icol | -0.006 |
iya | -0.006 |
peac | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
mun | +0.050 |
chambers | +0.049 |
brothers | +0.048 |
goals | +0.044 |
promises | +0.044 |
Neg logit contributions | |
tha | -0.078 |
flake | -0.077 |
ich | -0.071 |
iya | -0.068 |
la | -0.067 |
Token | ride |
Token ID | 6594 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
brothers | +0.005 |
chambers | +0.005 |
mun | +0.004 |
promises | +0.004 |
ins | +0.004 |
Neg logit contributions | |
flake | -0.006 |
tha | -0.006 |
peac | -0.006 |
icol | -0.006 |
iya | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
flake | +0.004 |
tha | +0.004 |
icol | +0.004 |
iya | +0.004 |
peac | +0.004 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
mun | -0.002 |
promises | -0.002 |
ins | -0.001 |
Token | waves |
Token ID | 9813 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
enda | +0.045 |
tha | +0.045 |
icol | +0.042 |
flake | +0.041 |
essa | +0.041 |
Neg logit contributions | |
brothers | -0.020 |
other | -0.018 |
friends | -0.017 |
more | -0.016 |
y | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
tha | +0.129 |
flake | +0.126 |
icol | +0.125 |
iya | +0.123 |
peac | +0.121 |
Neg logit contributions | |
brothers | -0.040 |
chambers | -0.033 |
more | -0.032 |
mun | -0.032 |
of | -0.029 |
Token | his |
Token ID | 465 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
brothers | +0.012 |
chambers | +0.011 |
mun | +0.011 |
promises | +0.010 |
more | +0.009 |
Neg logit contributions | |
tha | -0.025 |
flake | -0.025 |
icol | -0.024 |
iya | -0.024 |
peac | -0.024 |
Token | surf |
Token ID | 9053 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
brothers | +0.017 |
chambers | +0.015 |
friends | +0.015 |
promises | +0.014 |
more | +0.014 |
Neg logit contributions | |
flake | -0.022 |
tha | -0.021 |
icol | -0.020 |
peac | -0.020 |
storm | -0.020 |
Token | board |
Token ID | 3526 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
tha | +0.116 |
flake | +0.114 |
icol | +0.111 |
iya | +0.110 |
peac | +0.109 |
Neg logit contributions | |
brothers | -0.055 |
chambers | -0.051 |
mun | -0.049 |
promises | -0.046 |
more | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
tha | +0.007 |
flake | +0.007 |
icol | +0.007 |
iya | +0.007 |
peac | +0.007 |
Neg logit contributions | |
brothers | -0.003 |
chambers | -0.003 |
mun | -0.003 |
promises | -0.002 |
more | -0.002 |
Token | One |
Token ID | 1881 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
chambers | +0.012 |
brothers | +0.011 |
mun | +0.011 |
promises | +0.011 |
ins | +0.010 |
Neg logit contributions | |
flake | -0.015 |
tha | -0.015 |
icol | -0.015 |
storm | -0.014 |
peac | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
flake | +0.003 |
tha | +0.003 |
iya | +0.003 |
peac | +0.003 |
bye | +0.003 |
Neg logit contributions | |
chambers | -0.004 |
mun | -0.004 |
ins | -0.004 |
promises | -0.004 |
brothers | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
chambers | +0.038 |
brothers | +0.037 |
promises | +0.037 |
mun | +0.035 |
goals | +0.034 |
Neg logit contributions | |
tha | -0.031 |
flake | -0.030 |
icol | -0.030 |
peac | -0.029 |
storm | -0.028 |
Token | some |
Token ID | 617 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
flake | +0.045 |
tha | +0.045 |
iya | +0.044 |
icol | +0.043 |
storm | +0.043 |
Neg logit contributions | |
brothers | -0.014 |
more | -0.014 |
chambers | -0.012 |
promises | -0.012 |
friends | -0.011 |
Token | ac |
Token ID | 936 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
brothers | +0.019 |
chambers | +0.018 |
mun | +0.017 |
promises | +0.016 |
goals | +0.015 |
Neg logit contributions | |
flake | -0.035 |
tha | -0.035 |
peac | -0.035 |
icol | -0.034 |
iya | -0.033 |
Token | orns |
Token ID | 19942 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
flake | +0.023 |
tha | +0.023 |
peac | +0.022 |
icol | +0.022 |
iya | +0.021 |
Neg logit contributions | |
brothers | -0.014 |
chambers | -0.014 |
promises | -0.012 |
mun | -0.012 |
goals | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
brothers | +0.006 |
more | +0.006 |
chambers | +0.005 |
mun | +0.005 |
promises | +0.005 |
Neg logit contributions | |
icol | -0.013 |
tha | -0.013 |
flake | -0.012 |
iya | -0.012 |
peac | -0.012 |
Token | took |
Token ID | 1718 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
brothers | +0.007 |
chambers | +0.007 |
mun | +0.006 |
promises | +0.006 |
goals | +0.006 |
Neg logit contributions | |
tha | -0.011 |
flake | -0.011 |
icol | -0.011 |
peac | -0.011 |
iya | -0.011 |
Token | them |
Token ID | 606 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
flake | +0.025 |
tha | +0.025 |
ich | +0.024 |
iya | +0.023 |
storm | +0.023 |
Neg logit contributions | |
brothers | -0.016 |
more | -0.015 |
friends | -0.014 |
promises | -0.014 |
chambers | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
tha | +0.092 |
flake | +0.090 |
icol | +0.090 |
iya | +0.088 |
peac | +0.087 |
Neg logit contributions | |
brothers | -0.069 |
chambers | -0.066 |
more | -0.066 |
promises | -0.065 |
friends | -0.063 |
Token | his |
Token ID | 465 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
brothers | +0.002 |
more | +0.002 |
chambers | +0.002 |
promises | +0.002 |
friends | +0.002 |
Neg logit contributions | |
flake | -0.005 |
tha | -0.005 |
icol | -0.005 |
iya | -0.005 |
la | -0.005 |
Token | friends |
Token ID | 2460 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
mun | +0.028 |
brothers | +0.027 |
chambers | +0.026 |
ins | +0.026 |
promises | +0.024 |
Neg logit contributions | |
tha | -0.035 |
flake | -0.034 |
icol | -0.033 |
peac | -0.033 |
iya | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
tha | +0.004 |
flake | +0.004 |
icol | +0.004 |
peac | +0.004 |
iya | +0.004 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.001 |
mun | -0.001 |
promises | -0.001 |
more | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
tha | +0.004 |
flake | +0.004 |
icol | +0.004 |
peac | +0.004 |
iya | +0.004 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
mun | -0.002 |
promises | -0.002 |
more | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
flake | +0.082 |
tha | +0.081 |
iya | +0.078 |
peac | +0.078 |
icol | +0.078 |
Neg logit contributions | |
brothers | -0.037 |
chambers | -0.035 |
mun | -0.034 |
promises | -0.031 |
goals | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
flake | +0.001 |
icol | +0.001 |
tha | +0.001 |
storm | +0.001 |
OW | +0.001 |
Neg logit contributions | |
mun | -0.001 |
promises | -0.001 |
brothers | -0.001 |
chambers | -0.001 |
ins | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
tha | +0.010 |
flake | +0.009 |
icol | +0.009 |
iya | +0.009 |
essa | +0.009 |
Neg logit contributions | |
brothers | -0.005 |
chambers | -0.004 |
mun | -0.004 |
more | -0.004 |
promises | -0.004 |
Token | holding |
Token ID | 4769 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
tha | +0.026 |
flake | +0.026 |
icol | +0.025 |
peac | +0.025 |
iya | +0.025 |
Neg logit contributions | |
brothers | -0.029 |
chambers | -0.028 |
mun | -0.027 |
promises | -0.026 |
goals | -0.025 |
Token | his |
Token ID | 465 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
chambers | +0.003 |
mun | +0.003 |
brothers | +0.003 |
promises | +0.002 |
goals | +0.002 |
Neg logit contributions | |
tha | -0.007 |
flake | -0.007 |
icol | -0.007 |
iya | -0.007 |
essa | -0.007 |
Token | treasure |
Token ID | 14068 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
tha | +0.025 |
flake | +0.025 |
icol | +0.024 |
iya | +0.023 |
peac | +0.023 |
Neg logit contributions | |
brothers | -0.014 |
chambers | -0.012 |
promises | -0.012 |
mun | -0.012 |
friends | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
flake | +0.098 |
tha | +0.097 |
icol | +0.092 |
peac | +0.092 |
essa | +0.090 |
Neg logit contributions | |
brothers | -0.069 |
mun | -0.069 |
chambers | -0.064 |
promises | -0.060 |
ins | -0.059 |
Token | One |
Token ID | 1881 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
flake | +0.003 |
tha | +0.003 |
icol | +0.003 |
iya | +0.003 |
peac | +0.003 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
mun | -0.002 |
promises | -0.002 |
ins | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
flake | +0.015 |
tha | +0.014 |
peac | +0.014 |
iya | +0.014 |
storm | +0.013 |
Neg logit contributions | |
chambers | -0.018 |
mun | -0.018 |
ins | -0.017 |
brothers | -0.017 |
goals | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
chambers | +0.021 |
mun | +0.021 |
promises | +0.021 |
brothers | +0.020 |
ins | +0.020 |
Neg logit contributions | |
tha | -0.016 |
icol | -0.016 |
flake | -0.016 |
OW | -0.015 |
essa | -0.015 |
Token | while |
Token ID | 981 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
tha | +0.019 |
flake | +0.019 |
icol | +0.018 |
essa | +0.018 |
peac | +0.017 |
Neg logit contributions | |
chambers | -0.018 |
mun | -0.017 |
brothers | -0.017 |
promises | -0.016 |
ins | -0.016 |
Token | purple |
Token ID | 14032 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
tha | +0.046 |
la | +0.045 |
OW | +0.044 |
chie | +0.043 |
flake | +0.043 |
Neg logit contributions | |
friends | -0.020 |
more | -0.020 |
cookies | -0.018 |
brothers | -0.018 |
toys | -0.017 |
Token | balloon |
Token ID | 21190 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
tha | +0.019 |
OW | +0.017 |
la | +0.017 |
enda | +0.017 |
iya | +0.017 |
Neg logit contributions | |
more | -0.008 |
brothers | -0.008 |
friends | -0.008 |
chambers | -0.008 |
of | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.68e-03 |
Pos logit contributions | |
tha | +0.034 |
icol | +0.033 |
flake | +0.033 |
iya | +0.033 |
OW | +0.033 |
Neg logit contributions | |
brothers | -0.013 |
chambers | -0.012 |
more | -0.012 |
of | -0.011 |
mun | -0.011 |
Token | |
Token ID | 220 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
brothers | +0.000 |
chambers | +0.000 |
mun | +0.000 |
of | +0.000 |
friends | +0.000 |
Neg logit contributions | |
flake | -0.000 |
tha | -0.000 |
iya | -0.000 |
peac | -0.000 |
storm | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
brothers | +0.021 |
chambers | +0.020 |
mun | +0.019 |
promises | +0.018 |
more | +0.017 |
Neg logit contributions | |
tha | -0.033 |
flake | -0.033 |
iya | -0.031 |
icol | -0.031 |
essa | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
tha | +0.006 |
flake | +0.006 |
icol | +0.006 |
peac | +0.006 |
storm | +0.006 |
Neg logit contributions | |
brothers | -0.002 |
chambers | -0.002 |
mun | -0.002 |
of | -0.002 |
more | -0.001 |
Token | As |
Token ID | 1722 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
flake | +0.020 |
tha | +0.020 |
icol | +0.019 |
iya | +0.019 |
peac | +0.019 |
Neg logit contributions | |
brothers | -0.011 |
chambers | -0.011 |
mun | -0.010 |
more | -0.010 |
of | -0.010 |
Token | Sus |
Token ID | 8932 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
flake | +0.044 |
AR | +0.041 |
icol | +0.041 |
OW | +0.040 |
rus | +0.040 |
Neg logit contributions | |
brothers | -0.015 |
more | -0.015 |
of | -0.014 |
friends | -0.014 |
chambers | -0.012 |
Token | ie |
Token ID | 494 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
tha | +0.067 |
flake | +0.067 |
iya | +0.063 |
icol | +0.063 |
peac | +0.062 |
Neg logit contributions | |
brothers | -0.051 |
chambers | -0.049 |
mun | -0.047 |
promises | -0.045 |
goals | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
tha | +0.059 |
flake | +0.057 |
iya | +0.056 |
icol | +0.055 |
la | +0.054 |
Neg logit contributions | |
brothers | -0.035 |
chambers | -0.034 |
goals | -0.031 |
mun | -0.030 |
questions | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
tha | +0.034 |
flake | +0.034 |
icol | +0.032 |
peac | +0.032 |
iya | +0.032 |
Neg logit contributions | |
brothers | -0.014 |
chambers | -0.013 |
mun | -0.012 |
promises | -0.011 |
more | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
brothers | +0.020 |
more | +0.020 |
promises | +0.019 |
friends | +0.018 |
chambers | +0.018 |
Neg logit contributions | |
icol | -0.033 |
tha | -0.032 |
flake | -0.032 |
iya | -0.031 |
peac | -0.031 |
Token | get |
Token ID | 651 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
more | +0.027 |
promises | +0.025 |
brothers | +0.025 |
friends | +0.023 |
chores | +0.023 |
Neg logit contributions | |
flake | -0.069 |
icol | -0.068 |
la | -0.068 |
tha | -0.067 |
iya | -0.066 |
Token | better |
Token ID | 1365 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
more | +0.030 |
brothers | +0.028 |
promises | +0.027 |
friends | +0.027 |
of | +0.025 |
Neg logit contributions | |
flake | -0.049 |
icol | -0.048 |
iya | -0.048 |
tha | -0.047 |
storm | -0.047 |
Token | ." |
Token ID | 526 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
tha | +0.018 |
flake | +0.017 |
icol | +0.017 |
enda | +0.017 |
peac | +0.017 |
Neg logit contributions | |
more | -0.014 |
brothers | -0.014 |
promises | -0.013 |
friends | -0.013 |
chambers | -0.013 |
Token | Mia |
Token ID | 32189 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
tha | +0.025 |
flake | +0.025 |
icol | +0.024 |
iya | +0.024 |
da | +0.024 |
Neg logit contributions | |
brothers | -0.017 |
chambers | -0.016 |
mun | -0.016 |
promises | -0.015 |
chores | -0.015 |
Token | picked |
Token ID | 6497 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
brothers | +0.028 |
chambers | +0.026 |
mun | +0.025 |
promises | +0.024 |
more | +0.023 |
Neg logit contributions | |
tha | -0.058 |
flake | -0.058 |
icol | -0.056 |
peac | -0.055 |
iya | -0.055 |
Token | up |
Token ID | 510 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
chambers | +0.047 |
brothers | +0.046 |
mun | +0.044 |
goals | +0.040 |
promises | +0.040 |
Neg logit contributions | |
tha | -0.050 |
flake | -0.049 |
icol | -0.046 |
essa | -0.046 |
iya | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
chambers | +0.077 |
brothers | +0.074 |
mun | +0.074 |
ins | +0.068 |
goals | +0.065 |
Neg logit contributions | |
tha | -0.086 |
flake | -0.082 |
peac | -0.079 |
iya | -0.078 |
essa | -0.076 |
Token | arrow |
Token ID | 15452 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
brothers | +0.018 |
chambers | +0.017 |
promises | +0.016 |
mun | +0.016 |
more | +0.016 |
Neg logit contributions | |
tha | -0.012 |
flake | -0.012 |
icol | -0.012 |
iya | -0.012 |
essa | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
flake | +0.001 |
tha | +0.001 |
peac | +0.001 |
iya | +0.001 |
icol | +0.001 |
Neg logit contributions | |
brothers | -0.001 |
chambers | -0.001 |
mun | -0.001 |
ins | -0.001 |
promises | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
brothers | +0.027 |
chambers | +0.026 |
mun | +0.025 |
promises | +0.024 |
goals | +0.023 |
Neg logit contributions | |
tha | -0.041 |
flake | -0.041 |
icol | -0.039 |
iya | -0.039 |
peac | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
mun | +0.006 |
ins | +0.006 |
promises | +0.006 |
brothers | +0.005 |
chambers | +0.005 |
Neg logit contributions | |
flake | -0.009 |
icol | -0.009 |
tha | -0.009 |
storm | -0.009 |
peac | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
tha | +0.005 |
flake | +0.005 |
icol | +0.005 |
iya | +0.005 |
peac | +0.005 |
Neg logit contributions | |
brothers | -0.003 |
chambers | -0.002 |
mun | -0.002 |
more | -0.002 |
promises | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
tha | +0.021 |
peac | +0.021 |
flake | +0.020 |
ich | +0.019 |
iya | +0.019 |
Neg logit contributions | |
chambers | -0.016 |
mun | -0.016 |
ins | -0.015 |
brothers | -0.015 |
promises | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
tha | +0.032 |
flake | +0.032 |
icol | +0.031 |
peac | +0.031 |
iya | +0.030 |
Neg logit contributions | |
chambers | -0.026 |
mun | -0.026 |
brothers | -0.025 |
promises | -0.023 |
ins | -0.023 |
Token | strong |
Token ID | 1913 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
tha | +0.011 |
flake | +0.011 |
peac | +0.010 |
storm | +0.010 |
da | +0.010 |
Neg logit contributions | |
mun | -0.010 |
chambers | -0.010 |
ins | -0.010 |
promises | -0.009 |
ways | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
flake | +0.032 |
tha | +0.031 |
icol | +0.031 |
peac | +0.031 |
essa | +0.030 |
Neg logit contributions | |
mun | -0.020 |
chambers | -0.019 |
brothers | -0.018 |
promises | -0.018 |
ins | -0.017 |
Token | He |
Token ID | 679 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
flake | +0.030 |
tha | +0.030 |
icol | +0.029 |
iya | +0.029 |
peac | +0.029 |
Neg logit contributions | |
mun | -0.017 |
brothers | -0.017 |
promises | -0.016 |
chambers | -0.016 |
ins | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
brothers | +0.001 |
chambers | +0.000 |
mun | +0.000 |
more | +0.000 |
friends | +0.000 |
Neg logit contributions | |
tha | -0.001 |
flake | -0.001 |
icol | -0.001 |
iya | -0.001 |
essa | -0.001 |
Token | wearing |
Token ID | 5762 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
tha | +0.013 |
flake | +0.013 |
peac | +0.013 |
iya | +0.013 |
icol | +0.013 |
Neg logit contributions | |
chambers | -0.008 |
brothers | -0.008 |
mun | -0.008 |
promises | -0.007 |
goals | -0.007 |
Token | an |
Token ID | 281 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
brothers | +0.023 |
mun | +0.023 |
chambers | +0.022 |
promises | +0.021 |
ins | +0.020 |
Neg logit contributions | |
flake | -0.036 |
tha | -0.036 |
icol | -0.035 |
peac | -0.035 |
iya | -0.034 |
Token | orange |
Token ID | 10912 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
brothers | +0.006 |
chambers | +0.006 |
mun | +0.006 |
promises | +0.006 |
more | +0.005 |
Neg logit contributions | |
flake | -0.010 |
tha | -0.010 |
icol | -0.009 |
iya | -0.009 |
peac | -0.009 |
Token | ase |
Token ID | 589 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
tha | +0.017 |
iya | +0.016 |
icol | +0.016 |
Gab | +0.016 |
Gina | +0.016 |
Neg logit contributions | |
brothers | -0.011 |
of | -0.010 |
ins | -0.009 |
chambers | -0.009 |
mun | -0.009 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
iya | +0.008 |
icol | +0.007 |
tha | +0.007 |
essa | +0.007 |
flake | +0.007 |
Neg logit contributions | |
of | -0.011 |
brothers | -0.010 |
more | -0.010 |
chambers | -0.010 |
friends | -0.010 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
tha | +0.018 |
iya | +0.018 |
essa | +0.017 |
flake | +0.017 |
la | +0.017 |
Neg logit contributions | |
brothers | -0.016 |
chambers | -0.016 |
mun | -0.015 |
promises | -0.014 |
ins | -0.014 |
Token | says |
Token ID | 1139 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
brothers | +0.005 |
chambers | +0.005 |
mun | +0.005 |
promises | +0.005 |
chores | +0.004 |
Neg logit contributions | |
tha | -0.008 |
flake | -0.008 |
iya | -0.007 |
essa | -0.007 |
icol | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
chambers | +0.011 |
mun | +0.011 |
brothers | +0.011 |
promises | +0.010 |
goals | +0.009 |
Neg logit contributions | |
tha | -0.015 |
flake | -0.014 |
essa | -0.014 |
work | -0.013 |
icol | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
brothers | +0.016 |
chambers | +0.016 |
mun | +0.015 |
promises | +0.014 |
more | +0.013 |
Neg logit contributions | |
tha | -0.028 |
flake | -0.028 |
icol | -0.027 |
iya | -0.027 |
essa | -0.026 |
Token | Can |
Token ID | 6090 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
brothers | +0.005 |
chambers | +0.005 |
more | +0.005 |
mun | +0.005 |
goals | +0.005 |
Neg logit contributions | |
tha | -0.008 |
icol | -0.008 |
iya | -0.007 |
flake | -0.007 |
essa | -0.007 |
Token | we |
Token ID | 356 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
icol | +0.023 |
flake | +0.022 |
iya | +0.022 |
essa | +0.022 |
tha | +0.021 |
Neg logit contributions | |
more | -0.016 |
brothers | -0.016 |
of | -0.015 |
friends | -0.015 |
chambers | -0.014 |
Token | play |
Token ID | 711 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
brothers | +0.013 |
of | +0.013 |
more | +0.012 |
friends | +0.012 |
chambers | +0.011 |
Neg logit contributions | |
icol | -0.044 |
flake | -0.042 |
tha | -0.042 |
essa | -0.041 |
iya | -0.041 |
Token | with |
Token ID | 351 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
more | +0.034 |
brothers | +0.032 |
chambers | +0.028 |
friends | +0.028 |
of | +0.026 |
Neg logit contributions | |
tha | -0.095 |
iya | -0.092 |
icol | -0.091 |
essa | -0.089 |
la | -0.087 |
Token | it |
Token ID | 340 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
more | +0.016 |
other | +0.012 |
friends | +0.012 |
things | +0.012 |
of | +0.012 |
Neg logit contributions | |
icol | -0.037 |
storm | -0.034 |
flake | -0.033 |
ote | -0.032 |
sed | -0.032 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
tha | +0.025 |
flake | +0.025 |
icol | +0.024 |
peac | +0.024 |
AR | +0.024 |
Neg logit contributions | |
brothers | -0.009 |
promises | -0.008 |
chambers | -0.008 |
more | -0.008 |
friends | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
flake | +0.101 |
tha | +0.098 |
icol | +0.097 |
peac | +0.094 |
storm | +0.092 |
Neg logit contributions | |
brothers | -0.044 |
mun | -0.038 |
chambers | -0.036 |
friends | -0.035 |
promises | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
brothers | +0.010 |
chambers | +0.009 |
mun | +0.009 |
promises | +0.008 |
friends | +0.008 |
Neg logit contributions | |
flake | -0.025 |
tha | -0.025 |
icol | -0.024 |
peac | -0.024 |
storm | -0.024 |
Token | The |
Token ID | 464 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
brothers | +0.001 |
chambers | +0.001 |
mun | +0.001 |
promises | +0.001 |
friends | +0.001 |
Neg logit contributions | |
flake | -0.002 |
tha | -0.002 |
icol | -0.002 |
peac | -0.002 |
storm | -0.002 |
Token | tree |
Token ID | 5509 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
tha | +0.070 |
flake | +0.069 |
icol | +0.068 |
iya | +0.066 |
OW | +0.065 |
Neg logit contributions | |
brothers | -0.042 |
chambers | -0.037 |
mun | -0.035 |
more | -0.035 |
friends | -0.035 |
Token | smiled |
Token ID | 13541 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
brothers | +0.013 |
chambers | +0.012 |
mun | +0.011 |
promises | +0.011 |
more | +0.011 |
Neg logit contributions | |
tha | -0.023 |
icol | -0.023 |
flake | -0.023 |
iya | -0.023 |
essa | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
brothers | +0.001 |
chambers | +0.001 |
more | +0.001 |
promises | +0.001 |
friends | +0.001 |
Neg logit contributions | |
tha | -0.002 |
flake | -0.002 |
iya | -0.002 |
peac | -0.002 |
icol | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
brothers | +0.012 |
more | +0.011 |
friends | +0.010 |
promises | +0.010 |
mun | +0.010 |
Neg logit contributions | |
flake | -0.030 |
tha | -0.030 |
AR | -0.030 |
ich | -0.029 |
iya | -0.029 |
Token | kindly |
Token ID | 26820 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
tha | +0.062 |
iya | +0.061 |
flake | +0.060 |
icol | +0.060 |
ich | +0.060 |
Neg logit contributions | |
more | -0.018 |
of | -0.017 |
brothers | -0.017 |
friends | -0.015 |
es | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
tha | +0.026 |
flake | +0.025 |
peac | +0.025 |
icol | +0.025 |
iya | +0.025 |
Neg logit contributions | |
brothers | -0.009 |
chambers | -0.007 |
more | -0.007 |
questions | -0.007 |
promises | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
brothers | +0.003 |
more | +0.002 |
happy | +0.002 |
sleepy | +0.002 |
questions | +0.002 |
Neg logit contributions | |
flake | -0.013 |
tha | -0.012 |
opter | -0.012 |
iya | -0.012 |
OW | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
brothers | +0.004 |
more | +0.004 |
chambers | +0.003 |
mun | +0.003 |
promises | +0.003 |
Neg logit contributions | |
flake | -0.010 |
tha | -0.010 |
icol | -0.010 |
iya | -0.009 |
storm | -0.009 |
Token | sign |
Token ID | 1051 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
brothers | +0.004 |
more | +0.004 |
friends | +0.004 |
chambers | +0.004 |
mun | +0.004 |
Neg logit contributions | |
tha | -0.012 |
flake | -0.011 |
icol | -0.011 |
essa | -0.011 |
iya | -0.011 |
Token | that |
Token ID | 326 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
brothers | +0.006 |
more | +0.006 |
of | +0.006 |
chambers | +0.005 |
friends | +0.005 |
Neg logit contributions | |
tha | -0.012 |
flake | -0.012 |
icol | -0.012 |
iya | -0.012 |
OW | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
icol | +0.012 |
flake | +0.012 |
iya | +0.012 |
tha | +0.012 |
OW | +0.011 |
Neg logit contributions | |
brothers | -0.004 |
chambers | -0.004 |
more | -0.004 |
mun | -0.004 |
friends | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
icol | +0.016 |
flake | +0.015 |
iya | +0.015 |
tha | +0.015 |
OW | +0.015 |
Neg logit contributions | |
brothers | -0.005 |
of | -0.005 |
more | -0.005 |
questions | -0.005 |
friends | -0.005 |
Token | Safety |
Token ID | 45372 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
mun | +0.009 |
brothers | +0.009 |
of | +0.009 |
more | +0.009 |
ins | +0.008 |
Neg logit contributions | |
icol | -0.016 |
tha | -0.016 |
flake | -0.014 |
iya | -0.014 |
sed | -0.014 |
Token | First |
Token ID | 3274 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
brothers | +0.051 |
questions | +0.050 |
of | +0.049 |
more | +0.046 |
chores | +0.045 |
Neg logit contributions | |
icol | -0.071 |
peac | -0.062 |
iya | -0.059 |
flake | -0.058 |
storm | -0.056 |
Token | ". |
Token ID | 1911 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
brothers | +0.046 |
of | +0.043 |
friends | +0.039 |
more | +0.039 |
ways | +0.039 |
Neg logit contributions | |
icol | -0.101 |
peac | -0.098 |
flake | -0.095 |
AR | -0.091 |
tha | -0.088 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
flake | +0.006 |
tha | +0.006 |
icol | +0.006 |
essa | +0.005 |
peac | +0.005 |
Neg logit contributions | |
brothers | -0.004 |
chambers | -0.004 |
mun | -0.004 |
promises | -0.004 |
goals | -0.003 |
Token | remembered |
Token ID | 12086 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
brothers | +0.044 |
chambers | +0.040 |
mun | +0.039 |
promises | +0.038 |
more | +0.035 |
Neg logit contributions | |
flake | -0.086 |
tha | -0.085 |
icol | -0.083 |
peac | -0.082 |
iya | -0.081 |
Token | what |
Token ID | 644 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
more | +0.019 |
brothers | +0.018 |
questions | +0.017 |
friends | +0.017 |
promises | +0.017 |
Neg logit contributions | |
flake | -0.056 |
icol | -0.055 |
tha | -0.053 |
storm | -0.053 |
OW | -0.052 |
Token | will |
Token ID | 481 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
brothers | +0.004 |
chambers | +0.004 |
promises | +0.003 |
friends | +0.003 |
mun | +0.003 |
Neg logit contributions | |
icol | -0.015 |
tha | -0.015 |
flake | -0.014 |
ich | -0.014 |
iya | -0.014 |
Token | have |
Token ID | 423 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
icol | +0.089 |
rus | +0.087 |
flake | +0.086 |
tha | +0.085 |
ich | +0.084 |
Neg logit contributions | |
friends | -0.027 |
brothers | -0.026 |
more | -0.026 |
chores | -0.023 |
promises | -0.021 |
Token | dessert |
Token ID | 23084 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
more | +0.018 |
friends | +0.014 |
brothers | +0.014 |
cookies | +0.013 |
y | +0.013 |
Neg logit contributions | |
flake | -0.047 |
tha | -0.046 |
icol | -0.045 |
storm | -0.044 |
AR | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
brothers | +0.006 |
chambers | +0.006 |
more | +0.006 |
promises | +0.006 |
friends | +0.005 |
Neg logit contributions | |
tha | -0.010 |
icol | -0.010 |
flake | -0.010 |
peac | -0.010 |
iya | -0.010 |
Token | How |
Token ID | 1374 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
brothers | +0.007 |
chambers | +0.007 |
mun | +0.007 |
promises | +0.006 |
more | +0.006 |
Neg logit contributions | |
tha | -0.008 |
flake | -0.008 |
icol | -0.008 |
iya | -0.008 |
peac | -0.008 |
Token | does |
Token ID | 857 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
brothers | +0.012 |
mun | +0.012 |
chambers | +0.011 |
promises | +0.011 |
ins | +0.010 |
Neg logit contributions | |
flake | -0.024 |
tha | -0.024 |
iya | -0.023 |
essa | -0.023 |
peac | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
brothers | +0.068 |
more | +0.067 |
chores | +0.063 |
chambers | +0.062 |
of | +0.061 |
Neg logit contributions | |
flake | -0.088 |
icol | -0.087 |
tha | -0.084 |
OW | -0.081 |
ert | -0.079 |
Token | sound |
Token ID | 2128 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
more | +0.034 |
brothers | +0.033 |
of | +0.029 |
friends | +0.029 |
promises | +0.029 |
Neg logit contributions | |
icol | -0.054 |
tha | -0.054 |
flake | -0.051 |
iya | -0.051 |
la | -0.050 |
Token | ?" |
Token ID | 1701 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
brothers | +0.039 |
more | +0.037 |
chambers | +0.036 |
of | +0.035 |
questions | +0.035 |
Neg logit contributions | |
icol | -0.040 |
tha | -0.040 |
flake | -0.038 |
iya | -0.038 |
peac | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
tha | +0.050 |
flake | +0.050 |
icol | +0.048 |
iya | +0.048 |
peac | +0.048 |
Neg logit contributions | |
brothers | -0.026 |
chambers | -0.024 |
mun | -0.023 |
promises | -0.022 |
more | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
brothers | +0.030 |
chambers | +0.028 |
mun | +0.026 |
promises | +0.025 |
more | +0.024 |
Neg logit contributions | |
tha | -0.062 |
flake | -0.062 |
icol | -0.060 |
peac | -0.059 |
iya | -0.059 |
Token | Everything |
Token ID | 11391 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
brothers | +0.003 |
chambers | +0.003 |
promises | +0.003 |
mun | +0.003 |
more | +0.002 |
Neg logit contributions | |
flake | -0.003 |
tha | -0.003 |
iya | -0.003 |
icol | -0.003 |
peac | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
more | +0.018 |
promises | +0.017 |
brothers | +0.016 |
chambers | +0.016 |
goals | +0.015 |
Neg logit contributions | |
icol | -0.049 |
iya | -0.049 |
tha | -0.049 |
peac | -0.048 |
essa | -0.048 |
Token | going |
Token ID | 1016 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
iya | +0.012 |
flake | +0.012 |
icol | +0.012 |
tha | +0.012 |
essa | +0.012 |
Neg logit contributions | |
more | -0.005 |
brothers | -0.005 |
friends | -0.004 |
promises | -0.004 |
y | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
more | +0.023 |
too | +0.017 |
questions | +0.017 |
brothers | +0.017 |
of | +0.016 |
Neg logit contributions | |
iya | -0.064 |
flake | -0.063 |
icol | -0.062 |
tha | -0.062 |
essa | -0.061 |
Token | be |
Token ID | 307 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
more | +0.006 |
chores | +0.005 |
other | +0.005 |
brothers | +0.005 |
friends | +0.004 |
Neg logit contributions | |
icol | -0.013 |
la | -0.012 |
tha | -0.012 |
flake | -0.012 |
iya | -0.012 |
Token | okay |
Token ID | 8788 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
more | +0.021 |
brothers | +0.020 |
friends | +0.017 |
promises | +0.016 |
chambers | +0.016 |
Neg logit contributions | |
flake | -0.051 |
tha | -0.050 |
iya | -0.050 |
icol | -0.049 |
essa | -0.049 |
Token | ." |
Token ID | 526 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
brothers | +0.058 |
of | +0.053 |
friends | +0.053 |
more | +0.053 |
chambers | +0.049 |
Neg logit contributions | |
icol | -0.109 |
tha | -0.099 |
peac | -0.098 |
iya | -0.096 |
flake | -0.096 |
Token | |
Token ID | 220 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
flake | +0.030 |
tha | +0.029 |
peac | +0.029 |
icol | +0.028 |
storm | +0.028 |
Neg logit contributions | |
brothers | -0.010 |
mun | -0.008 |
chambers | -0.008 |
promises | -0.008 |
more | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
brothers | +0.040 |
mun | +0.031 |
chambers | +0.031 |
promises | +0.030 |
friends | +0.029 |
Neg logit contributions | |
flake | -0.114 |
tha | -0.112 |
peac | -0.112 |
icol | -0.112 |
storm | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
brothers | +0.011 |
mun | +0.008 |
friends | +0.008 |
more | +0.007 |
of | +0.007 |
Neg logit contributions | |
icol | -0.051 |
flake | -0.051 |
storm | -0.051 |
tha | -0.051 |
peac | -0.049 |
Token | The |
Token ID | 464 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
brothers | +0.007 |
mun | +0.006 |
chambers | +0.006 |
more | +0.006 |
promises | +0.006 |
Neg logit contributions | |
tha | -0.012 |
flake | -0.012 |
icol | -0.012 |
storm | -0.012 |
iya | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
brothers | +0.002 |
more | +0.001 |
of | +0.001 |
questions | +0.001 |
friends | +0.001 |
Neg logit contributions | |
tha | -0.008 |
iya | -0.008 |
flake | -0.008 |
icol | -0.008 |
AR | -0.007 |
Token | I |
Token ID | 40 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
mun | +0.003 |
brothers | +0.003 |
more | +0.003 |
ins | +0.003 |
of | +0.003 |
Neg logit contributions | |
tha | -0.008 |
icol | -0.007 |
sed | -0.007 |
flake | -0.007 |
iya | -0.007 |
Token | 'm |
Token ID | 1101 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
brothers | +0.009 |
promises | +0.008 |
more | +0.008 |
mun | +0.008 |
of | +0.008 |
Neg logit contributions | |
tha | -0.021 |
ich | -0.020 |
icol | -0.020 |
flake | -0.019 |
iya | -0.019 |
Token | here |
Token ID | 994 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
flake | +0.066 |
icol | +0.060 |
storm | +0.060 |
tha | +0.059 |
iya | +0.058 |
Neg logit contributions | |
brothers | -0.024 |
more | -0.020 |
friends | -0.019 |
sleepy | -0.018 |
of | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
flake | +0.044 |
icol | +0.044 |
tha | +0.044 |
storm | +0.043 |
iya | +0.043 |
Neg logit contributions | |
more | -0.019 |
of | -0.019 |
brothers | -0.018 |
friends | -0.017 |
questions | -0.015 |
Token | talk |
Token ID | 1561 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
brothers | +0.010 |
more | +0.009 |
friends | +0.009 |
of | +0.009 |
promises | +0.008 |
Neg logit contributions | |
tha | -0.033 |
flake | -0.032 |
la | -0.032 |
ich | -0.032 |
icol | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
more | +0.038 |
of | +0.036 |
questions | +0.032 |
brothers | +0.030 |
friends | +0.028 |
Neg logit contributions | |
tha | -0.090 |
icol | -0.084 |
iya | -0.083 |
flake | -0.082 |
ich | -0.081 |
Token | you |
Token ID | 345 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
more | +0.009 |
brothers | +0.009 |
friends | +0.009 |
of | +0.008 |
questions | +0.008 |
Neg logit contributions | |
icol | -0.016 |
flake | -0.016 |
tha | -0.015 |
storm | -0.015 |
ANG | -0.015 |
Token | about |
Token ID | 546 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
brothers | +0.009 |
more | +0.008 |
friends | +0.008 |
of | +0.007 |
chambers | +0.007 |
Neg logit contributions | |
icol | -0.017 |
tha | -0.017 |
flake | -0.016 |
iya | -0.015 |
peac | -0.015 |
Token | taking |
Token ID | 2263 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
brothers | +0.033 |
more | +0.031 |
friends | +0.030 |
promises | +0.028 |
ways | +0.028 |
Neg logit contributions | |
tha | -0.058 |
icol | -0.057 |
flake | -0.057 |
iya | -0.056 |
peac | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
more | +0.018 |
brothers | +0.018 |
friends | +0.017 |
promises | +0.017 |
questions | +0.016 |
Neg logit contributions | |
tha | -0.044 |
flake | -0.043 |
ich | -0.041 |
storm | -0.041 |
peac | -0.040 |
Token | learning |
Token ID | 4673 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
tha | +0.018 |
flake | +0.018 |
peac | +0.017 |
icol | +0.017 |
iya | +0.017 |
Neg logit contributions | |
brothers | -0.014 |
chambers | -0.014 |
mun | -0.013 |
promises | -0.013 |
goals | -0.012 |
Token | new |
Token ID | 649 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
tha | +0.021 |
flake | +0.021 |
peac | +0.021 |
essa | +0.021 |
icol | +0.021 |
Neg logit contributions | |
brothers | -0.012 |
mun | -0.011 |
chambers | -0.010 |
promises | -0.010 |
ins | -0.009 |
Token | things |
Token ID | 1243 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
icol | +0.017 |
peac | +0.017 |
flake | +0.017 |
tha | +0.017 |
essa | +0.017 |
Neg logit contributions | |
brothers | -0.007 |
mun | -0.007 |
chambers | -0.006 |
promises | -0.006 |
hes | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
flake | +0.074 |
tha | +0.074 |
icol | +0.071 |
peac | +0.071 |
iya | +0.071 |
Neg logit contributions | |
brothers | -0.033 |
chambers | -0.030 |
mun | -0.029 |
promises | -0.027 |
goals | -0.024 |
Token | One |
Token ID | 1881 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
brothers | +0.001 |
chambers | +0.001 |
mun | +0.001 |
promises | +0.001 |
more | +0.001 |
Neg logit contributions | |
flake | -0.003 |
tha | -0.003 |
icol | -0.003 |
peac | -0.003 |
iya | -0.003 |
Token | sunny |
Token ID | 27737 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
tha | +0.020 |
flake | +0.020 |
iya | +0.019 |
peac | +0.019 |
icol | +0.019 |
Neg logit contributions | |
brothers | -0.013 |
chambers | -0.013 |
mun | -0.012 |
promises | -0.012 |
goals | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
brothers | +0.042 |
chambers | +0.039 |
mun | +0.037 |
promises | +0.035 |
more | +0.034 |
Neg logit contributions | |
tha | -0.083 |
flake | -0.083 |
icol | -0.080 |
iya | -0.079 |
peac | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
brothers | +0.012 |
of | +0.011 |
more | +0.011 |
chambers | +0.011 |
friends | +0.011 |
Neg logit contributions | |
flake | -0.031 |
tha | -0.030 |
icol | -0.029 |
iya | -0.028 |
ich | -0.028 |
Token | she |
Token ID | 673 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
flake | +0.016 |
tha | +0.016 |
icol | +0.015 |
iya | +0.015 |
storm | +0.015 |
Neg logit contributions | |
brothers | -0.010 |
chambers | -0.009 |
more | -0.009 |
friends | -0.009 |
mun | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
brothers | +0.008 |
chambers | +0.008 |
friends | +0.007 |
mun | +0.007 |
of | +0.007 |
Neg logit contributions | |
tha | -0.022 |
flake | -0.022 |
icol | -0.021 |
AR | -0.021 |
ich | -0.021 |
Token | playing |
Token ID | 2712 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
flake | +0.024 |
tha | +0.024 |
icol | +0.023 |
peac | +0.023 |
iya | +0.023 |
Neg logit contributions | |
brothers | -0.010 |
chambers | -0.008 |
more | -0.008 |
friends | -0.008 |
mun | -0.008 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
brothers | +0.267 |
chambers | +0.249 |
mun | +0.239 |
friends | +0.238 |
promises | +0.235 |
Neg logit contributions | |
flake | -0.162 |
iya | -0.156 |
tha | -0.154 |
icol | -0.153 |
essa | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
tha | +0.019 |
icol | +0.018 |
flake | +0.018 |
iya | +0.018 |
essa | +0.018 |
Neg logit contributions | |
brothers | -0.008 |
chambers | -0.007 |
mun | -0.007 |
more | -0.006 |
friends | -0.006 |
Token | The |
Token ID | 383 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
flake | +0.033 |
tha | +0.033 |
icol | +0.031 |
iya | +0.031 |
essa | +0.031 |
Neg logit contributions | |
brothers | -0.015 |
chambers | -0.013 |
of | -0.011 |
mun | -0.011 |
friends | -0.010 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
icol | +0.022 |
flake | +0.022 |
tha | +0.021 |
iya | +0.020 |
enda | +0.020 |
Neg logit contributions | |
brothers | -0.022 |
friends | -0.020 |
chambers | -0.019 |
more | -0.019 |
promises | -0.018 |
Token | in |
Token ID | 259 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
brothers | +0.007 |
chambers | +0.007 |
mun | +0.007 |
promises | +0.006 |
more | +0.006 |
Neg logit contributions | |
tha | -0.014 |
flake | -0.014 |
icol | -0.013 |
iya | -0.013 |
peac | -0.013 |
Token | oc |
Token ID | 420 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
tha | +0.037 |
icol | +0.037 |
flake | +0.037 |
essa | +0.036 |
iya | +0.036 |
Neg logit contributions | |
brothers | -0.008 |
chambers | -0.006 |
mun | -0.006 |
promises | -0.005 |
friends | -0.004 |
Token | eros |
Token ID | 27498 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
brothers | +0.272 |
chambers | +0.250 |
mun | +0.246 |
promises | +0.243 |
friends | +0.240 |
Neg logit contributions | |
flake | -0.166 |
iya | -0.165 |
icol | -0.163 |
tha | -0.159 |
essa | -0.159 |
Token | was |
Token ID | 373 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
brothers | +0.000 |
chambers | +0.000 |
mun | +0.000 |
friends | +0.000 |
more | +0.000 |
Neg logit contributions | |
icol | -0.000 |
tha | -0.000 |
flake | -0.000 |
iya | -0.000 |
essa | -0.000 |
Token | very |
Token ID | 845 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
flake | +0.012 |
icol | +0.012 |
tha | +0.012 |
iya | +0.011 |
essa | +0.011 |
Neg logit contributions | |
brothers | -0.004 |
more | -0.003 |
friends | -0.003 |
chambers | -0.003 |
promises | -0.003 |
Token | big |
Token ID | 1263 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
flake | +0.034 |
tha | +0.033 |
icol | +0.033 |
iya | +0.032 |
essa | +0.032 |
Neg logit contributions | |
brothers | -0.011 |
chambers | -0.010 |
mun | -0.009 |
promises | -0.009 |
more | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
flake | +0.039 |
tha | +0.038 |
icol | +0.037 |
peac | +0.037 |
iya | +0.036 |
Neg logit contributions | |
brothers | -0.028 |
mun | -0.027 |
chambers | -0.027 |
promises | -0.025 |
ins | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
brothers | +0.044 |
chambers | +0.037 |
mun | +0.037 |
promises | +0.035 |
friends | +0.033 |
Neg logit contributions | |
flake | -0.111 |
tha | -0.110 |
icol | -0.109 |
peac | -0.108 |
iya | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
brothers | +0.017 |
mun | +0.014 |
of | +0.012 |
more | +0.012 |
friends | +0.012 |
Neg logit contributions | |
tha | -0.068 |
icol | -0.067 |
flake | -0.066 |
storm | -0.066 |
peac | -0.065 |
Token | The |
Token ID | 464 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
brothers | +0.016 |
mun | +0.015 |
chambers | +0.015 |
more | +0.014 |
promises | +0.014 |
Neg logit contributions | |
tha | -0.027 |
flake | -0.027 |
icol | -0.026 |
essa | -0.025 |
iya | -0.025 |
Token | rh |
Token ID | 9529 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
tha | +0.019 |
flake | +0.018 |
icol | +0.018 |
iya | +0.018 |
essa | +0.017 |
Neg logit contributions | |
brothers | -0.017 |
chambers | -0.016 |
mun | -0.015 |
promises | -0.015 |
more | -0.014 |
Token | in |
Token ID | 259 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
brothers | +0.012 |
chambers | +0.012 |
mun | +0.011 |
promises | +0.011 |
more | +0.010 |
Neg logit contributions | |
flake | -0.021 |
tha | -0.021 |
peac | -0.020 |
icol | -0.020 |
iya | -0.020 |
Token | oc |
Token ID | 420 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
tha | +0.029 |
flake | +0.028 |
icol | +0.028 |
iya | +0.027 |
peac | +0.027 |
Neg logit contributions | |
brothers | -0.008 |
chambers | -0.007 |
mun | -0.007 |
promises | -0.006 |
more | -0.006 |
Token | eros |
Token ID | 27498 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
brothers | +0.240 |
promises | +0.224 |
mun | +0.218 |
chambers | +0.217 |
friends | +0.211 |
Neg logit contributions | |
iya | -0.141 |
icol | -0.139 |
la | -0.134 |
tha | -0.132 |
flake | -0.132 |
Token | couldn |
Token ID | 3521 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
brothers | +0.012 |
more | +0.010 |
chambers | +0.010 |
mun | +0.010 |
promises | +0.010 |
Neg logit contributions | |
tha | -0.027 |
icol | -0.027 |
flake | -0.026 |
iya | -0.026 |
essa | -0.026 |
Token | 't |
Token ID | 470 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
brothers | +0.029 |
mun | +0.027 |
chambers | +0.027 |
more | +0.027 |
promises | +0.027 |
Neg logit contributions | |
tha | -0.016 |
icol | -0.016 |
flake | -0.015 |
peac | -0.015 |
iya | -0.015 |
Token | believe |
Token ID | 1975 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
icol | +0.009 |
tha | +0.009 |
ich | +0.009 |
flake | +0.009 |
la | +0.008 |
Neg logit contributions | |
more | -0.005 |
brothers | -0.005 |
chambers | -0.005 |
of | -0.005 |
questions | -0.005 |
Token | his |
Token ID | 465 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
flake | +0.014 |
tha | +0.014 |
icol | +0.014 |
iya | +0.014 |
peac | +0.014 |
Neg logit contributions | |
brothers | -0.007 |
chambers | -0.006 |
promises | -0.006 |
more | -0.006 |
mun | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
tha | +0.029 |
flake | +0.029 |
icol | +0.028 |
iya | +0.028 |
peac | +0.028 |
Neg logit contributions | |
brothers | -0.015 |
chambers | -0.014 |
mun | -0.013 |
promises | -0.013 |
more | -0.012 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
tha | +0.012 |
flake | +0.012 |
AR | +0.012 |
icol | +0.012 |
chie | +0.012 |
Neg logit contributions | |
brothers | -0.002 |
friends | -0.002 |
mun | -0.002 |
more | -0.001 |
happy | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
tha | +0.027 |
flake | +0.027 |
icol | +0.025 |
iya | +0.025 |
peac | +0.025 |
Neg logit contributions | |
brothers | -0.024 |
chambers | -0.023 |
mun | -0.022 |
promises | -0.022 |
more | -0.021 |
Token | eat |
Token ID | 4483 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
tha | +0.064 |
flake | +0.062 |
icol | +0.060 |
iya | +0.060 |
la | +0.060 |
Neg logit contributions | |
brothers | -0.023 |
chambers | -0.021 |
mun | -0.018 |
promises | -0.018 |
more | -0.018 |
Token | av |
Token ID | 1196 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
brothers | +0.018 |
chambers | +0.018 |
mun | +0.016 |
promises | +0.016 |
goals | +0.015 |
Neg logit contributions | |
flake | -0.030 |
essa | -0.029 |
tha | -0.029 |
iya | -0.029 |
peac | -0.029 |
Token | oc |
Token ID | 420 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
brothers | +0.046 |
chambers | +0.043 |
mun | +0.041 |
sisters | +0.040 |
questions | +0.040 |
Neg logit contributions | |
flake | -0.072 |
peac | -0.069 |
icol | -0.069 |
tha | -0.068 |
OW | -0.068 |
Token | ados |
Token ID | 22484 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
brothers | +0.196 |
chambers | +0.187 |
mun | +0.181 |
promises | +0.175 |
more | +0.166 |
Neg logit contributions | |
flake | -0.239 |
tha | -0.239 |
icol | -0.227 |
iya | -0.225 |
peac | -0.224 |
Token | because |
Token ID | 780 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
flake | +0.029 |
tha | +0.029 |
essa | +0.027 |
iya | +0.027 |
peac | +0.027 |
Neg logit contributions | |
brothers | -0.020 |
chambers | -0.018 |
mun | -0.018 |
promises | -0.018 |
goals | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
brothers | +0.003 |
chambers | +0.003 |
mun | +0.003 |
promises | +0.003 |
goals | +0.002 |
Neg logit contributions | |
tha | -0.004 |
flake | -0.004 |
peac | -0.004 |
iya | -0.004 |
essa | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
tha | +0.038 |
flake | +0.038 |
peac | +0.036 |
iya | +0.036 |
icol | +0.036 |
Neg logit contributions | |
brothers | -0.019 |
chambers | -0.018 |
mun | -0.017 |
promises | -0.016 |
goals | -0.015 |
Token | y |
Token ID | 331 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
tha | +0.015 |
flake | +0.015 |
peac | +0.015 |
iya | +0.014 |
essa | +0.014 |
Neg logit contributions | |
chambers | -0.010 |
mun | -0.010 |
brothers | -0.010 |
promises | -0.010 |
goals | -0.009 |
Token | net |
Token ID | 2010 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
icol | +0.046 |
tha | +0.045 |
enda | +0.044 |
iya | +0.044 |
essa | +0.043 |
Neg logit contributions | |
brothers | -0.034 |
more | -0.031 |
friends | -0.030 |
promises | -0.029 |
chambers | -0.029 |
Token | on |
Token ID | 319 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
tha | +0.091 |
flake | +0.090 |
icol | +0.088 |
iya | +0.087 |
peac | +0.086 |
Neg logit contributions | |
brothers | -0.050 |
chambers | -0.047 |
mun | -0.044 |
promises | -0.043 |
more | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
more | +0.007 |
brothers | +0.006 |
other | +0.005 |
his | +0.004 |
chores | +0.004 |
Neg logit contributions | |
icol | -0.031 |
storm | -0.031 |
flake | -0.031 |
opter | -0.030 |
peac | -0.030 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
brothers | +0.003 |
more | +0.003 |
chambers | +0.003 |
other | +0.003 |
friends | +0.002 |
Neg logit contributions | |
tha | -0.005 |
la | -0.005 |
enda | -0.005 |
iya | -0.005 |
flake | -0.005 |
Token | in |
Token ID | 259 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
brothers | +0.006 |
chambers | +0.006 |
mun | +0.006 |
promises | +0.005 |
more | +0.005 |
Neg logit contributions | |
flake | -0.010 |
tha | -0.009 |
iya | -0.009 |
peac | -0.009 |
essa | -0.009 |
Token | oc |
Token ID | 420 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
flake | +0.031 |
tha | +0.030 |
peac | +0.029 |
iya | +0.029 |
icol | +0.029 |
Neg logit contributions | |
brothers | -0.012 |
chambers | -0.011 |
mun | -0.011 |
promises | -0.010 |
goals | -0.009 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
brothers | +0.274 |
promises | +0.257 |
chambers | +0.251 |
mun | +0.241 |
goals | +0.239 |
Neg logit contributions | |
flake | -0.162 |
iya | -0.159 |
essa | -0.156 |
la | -0.155 |
tha | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
flake | +0.002 |
tha | +0.002 |
peac | +0.002 |
iya | +0.002 |
icol | +0.001 |
Neg logit contributions | |
brothers | -0.001 |
mun | -0.001 |
chambers | -0.001 |
promises | -0.001 |
ins | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
flake | +0.003 |
tha | +0.003 |
essa | +0.003 |
iya | +0.003 |
peac | +0.003 |
Neg logit contributions | |
brothers | -0.001 |
chambers | -0.001 |
promises | -0.001 |
So | -0.001 |
of | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
tha | +0.024 |
flake | +0.024 |
icol | +0.023 |
iya | +0.023 |
essa | +0.023 |
Neg logit contributions | |
brothers | -0.013 |
chambers | -0.012 |
mun | -0.012 |
promises | -0.011 |
more | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
flake | +0.037 |
tha | +0.037 |
icol | +0.037 |
iya | +0.037 |
peac | +0.036 |
Neg logit contributions | |
brothers | -0.022 |
chambers | -0.020 |
promises | -0.020 |
more | -0.020 |
mun | -0.019 |
Token | shaking |
Token ID | 17275 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
more | +0.009 |
brothers | +0.008 |
friends | +0.007 |
of | +0.007 |
ways | +0.007 |
Neg logit contributions | |
tha | -0.017 |
iya | -0.017 |
flake | -0.017 |
essa | -0.017 |
peac | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
more | +0.029 |
brothers | +0.026 |
of | +0.023 |
ways | +0.021 |
goals | +0.020 |
Neg logit contributions | |
tha | -0.097 |
iya | -0.097 |
flake | -0.094 |
ich | -0.093 |
essa | -0.093 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
brothers | +0.003 |
chambers | +0.002 |
mun | +0.002 |
promises | +0.002 |
more | +0.002 |
Neg logit contributions | |
flake | -0.008 |
tha | -0.008 |
peac | -0.008 |
iya | -0.007 |
ich | -0.007 |
Token | watched |
Token ID | 7342 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
brothers | +0.045 |
mun | +0.037 |
more | +0.035 |
of | +0.035 |
friends | +0.034 |
Neg logit contributions | |
icol | -0.096 |
flake | -0.094 |
tha | -0.094 |
essa | -0.093 |
iya | -0.093 |
Token | in |
Token ID | 287 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
of | +0.022 |
more | +0.022 |
brothers | +0.022 |
promises | +0.018 |
questions | +0.018 |
Neg logit contributions | |
flake | -0.063 |
peac | -0.061 |
tha | -0.060 |
ich | -0.060 |
iya | -0.060 |
Token | amaz |
Token ID | 40642 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
brothers | +0.017 |
chambers | +0.016 |
mun | +0.015 |
promises | +0.014 |
more | +0.013 |
Neg logit contributions | |
tha | -0.032 |
flake | -0.032 |
icol | -0.031 |
iya | -0.031 |
peac | -0.031 |
Token | ement |
Token ID | 972 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
brothers | +0.122 |
chambers | +0.115 |
mun | +0.108 |
promises | +0.106 |
more | +0.105 |
Neg logit contributions | |
flake | -0.251 |
tha | -0.244 |
peac | -0.241 |
icol | -0.237 |
iya | -0.234 |
Token | from |
Token ID | 422 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
brothers | +0.042 |
more | +0.038 |
of | +0.036 |
friends | +0.036 |
chambers | +0.034 |
Neg logit contributions | |
flake | -0.122 |
tha | -0.119 |
peac | -0.117 |
icol | -0.116 |
iya | -0.115 |
Token | a |
Token ID | 257 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
more | +0.029 |
brothers | +0.025 |
ways | +0.024 |
promises | +0.023 |
chambers | +0.022 |
Neg logit contributions | |
flake | -0.099 |
opter | -0.095 |
iya | -0.095 |
enda | -0.095 |
peac | -0.094 |
Token | distance |
Token ID | 5253 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
brothers | +0.034 |
more | +0.033 |
chambers | +0.031 |
mun | +0.030 |
promises | +0.029 |
Neg logit contributions | |
tha | -0.061 |
flake | -0.061 |
essa | -0.059 |
icol | -0.058 |
iya | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
more | +0.024 |
of | +0.023 |
brothers | +0.021 |
ways | +0.020 |
friends | +0.019 |
Neg logit contributions | |
flake | -0.070 |
icol | -0.066 |
AR | -0.066 |
peac | -0.065 |
tha | -0.065 |