Token | this |
Token ID | 428 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
aids | +0.134 |
jokes | +0.115 |
song | +0.115 |
hair | +0.112 |
ggie | +0.112 |
Neg logit contributions | |
arp | -0.127 |
unst | -0.123 |
sorts | -0.122 |
Joey | -0.121 |
aved | -0.120 |
Token | power |
Token ID | 1176 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
sorts | +0.077 |
Joey | +0.077 |
arp | +0.077 |
unst | +0.076 |
Mill | +0.075 |
Neg logit contributions | |
aids | -0.104 |
jokes | -0.090 |
song | -0.090 |
wig | -0.090 |
hair | -0.089 |
Token | would |
Token ID | 561 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
arp | +0.157 |
unst | +0.150 |
Joey | +0.149 |
aved | +0.147 |
sorts | +0.145 |
Neg logit contributions | |
aids | -0.187 |
song | -0.165 |
jokes | -0.163 |
hair | -0.160 |
poems | -0.156 |
Token | come |
Token ID | 1282 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
arp | +0.137 |
unst | +0.129 |
aved | +0.129 |
rolley | +0.128 |
sorts | +0.127 |
Neg logit contributions | |
aids | -0.101 |
song | -0.089 |
jokes | -0.086 |
hair | -0.081 |
ggie | -0.080 |
Token | in |
Token ID | 287 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
arp | +0.050 |
sorts | +0.049 |
rolley | +0.047 |
aved | +0.047 |
erek | +0.046 |
Neg logit contributions | |
aids | -0.055 |
song | -0.049 |
hair | -0.048 |
jokes | -0.047 |
poems | -0.045 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
aids | +0.033 |
hair | +0.029 |
song | +0.028 |
jokes | +0.028 |
poems | +0.026 |
Neg logit contributions | |
arp | -0.049 |
aved | -0.046 |
ucer | -0.046 |
rolley | -0.045 |
erek | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
arp | +0.824 |
unst | +0.810 |
Joey | +0.806 |
sorts | +0.803 |
aved | +0.787 |
Neg logit contributions | |
aids | -0.925 |
song | -0.794 |
jokes | -0.794 |
hair | -0.779 |
wig | -0.778 |
Token | |
Token ID | 220 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
arp | +0.040 |
unst | +0.039 |
aved | +0.038 |
sorts | +0.038 |
extingu | +0.037 |
Neg logit contributions | |
aids | -0.034 |
jokes | -0.027 |
Dancing | -0.027 |
hair | -0.027 |
song | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
aids | +0.021 |
Dancing | +0.017 |
ggie | +0.016 |
hair | +0.016 |
jokes | +0.016 |
Neg logit contributions | |
arp | -0.028 |
sorts | -0.027 |
unst | -0.026 |
aved | -0.026 |
extingu | -0.026 |
Token | He |
Token ID | 1544 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
arp | +0.057 |
unst | +0.056 |
aved | +0.055 |
extingu | +0.054 |
sorts | +0.054 |
Neg logit contributions | |
aids | -0.052 |
ggie | -0.043 |
jokes | -0.043 |
song | -0.043 |
Dancing | -0.043 |
Token | was |
Token ID | 373 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
arp | +0.026 |
unst | +0.026 |
Joey | +0.025 |
sorts | +0.025 |
aved | +0.025 |
Neg logit contributions | |
aids | -0.031 |
song | -0.027 |
jokes | -0.027 |
hair | -0.026 |
ggie | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
aids | +0.009 |
jokes | +0.008 |
song | +0.008 |
poems | +0.008 |
Dancing | +0.008 |
Neg logit contributions | |
arp | -0.008 |
sorts | -0.008 |
unst | -0.008 |
Joey | -0.008 |
Mill | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
unst | +0.037 |
sorts | +0.036 |
Joey | +0.035 |
Mill | +0.034 |
aved | +0.032 |
Neg logit contributions | |
aids | -0.053 |
cheeks | -0.048 |
wig | -0.048 |
jokes | -0.048 |
poems | -0.048 |
Token | happy |
Token ID | 3772 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
aids | +0.044 |
poems | +0.038 |
wig | +0.037 |
jokes | +0.037 |
cheeks | +0.036 |
Neg logit contributions | |
unst | -0.041 |
sorts | -0.040 |
Joey | -0.040 |
Mill | -0.038 |
aved | -0.037 |
Token | because |
Token ID | 780 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
aids | +0.067 |
wig | +0.056 |
ggie | +0.056 |
jokes | +0.055 |
song | +0.055 |
Neg logit contributions | |
Joey | -0.053 |
sorts | -0.053 |
arp | -0.051 |
Mill | -0.051 |
unst | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
aids | +0.128 |
song | +0.111 |
poems | +0.109 |
jokes | +0.107 |
hair | +0.107 |
Neg logit contributions | |
arp | -0.232 |
aved | -0.229 |
unst | -0.222 |
extingu | -0.218 |
ucer | -0.213 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
arp | +0.059 |
aved | +0.056 |
Joey | +0.056 |
sorts | +0.056 |
ucer | +0.054 |
Neg logit contributions | |
aids | -0.046 |
song | -0.041 |
hair | -0.040 |
jokes | -0.040 |
poems | -0.039 |
Token | man |
Token ID | 582 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
arp | +0.897 |
unst | +0.882 |
Joey | +0.877 |
sorts | +0.875 |
aved | +0.860 |
Neg logit contributions | |
aids | -0.795 |
jokes | -0.669 |
song | -0.669 |
hair | -0.655 |
wig | -0.653 |
Token | had |
Token ID | 550 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
arp | +0.093 |
unst | +0.091 |
Joey | +0.091 |
sorts | +0.090 |
aved | +0.089 |
Neg logit contributions | |
aids | -0.105 |
song | -0.091 |
jokes | -0.090 |
hair | -0.089 |
ggie | -0.089 |
Token | helped |
Token ID | 4193 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
aids | +0.087 |
jokes | +0.077 |
song | +0.076 |
hair | +0.076 |
poems | +0.075 |
Neg logit contributions | |
arp | -0.080 |
aved | -0.073 |
unst | -0.073 |
Joey | -0.073 |
sorts | -0.072 |
Token | her |
Token ID | 607 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
arp | +0.200 |
aved | +0.192 |
unst | +0.191 |
sorts | +0.191 |
Joey | +0.188 |
Neg logit contributions | |
aids | -0.266 |
song | -0.233 |
jokes | -0.233 |
hair | -0.229 |
ggie | -0.228 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
aids | +0.046 |
song | +0.041 |
jokes | +0.040 |
hair | +0.040 |
ggie | +0.039 |
Neg logit contributions | |
arp | -0.036 |
Joey | -0.034 |
aved | -0.034 |
sorts | -0.034 |
unst | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
arp | +0.112 |
unst | +0.111 |
sorts | +0.111 |
Joey | +0.110 |
aved | +0.107 |
Neg logit contributions | |
aids | -0.135 |
jokes | -0.115 |
song | -0.115 |
wig | -0.114 |
ggie | -0.113 |
Token | The |
Token ID | 383 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
arp | +0.012 |
Joey | +0.012 |
unst | +0.012 |
sorts | +0.011 |
Mill | +0.011 |
Neg logit contributions | |
aids | -0.012 |
song | -0.011 |
jokes | -0.010 |
wig | -0.010 |
ggie | -0.010 |
Token | cart |
Token ID | 6383 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
aids | +0.096 |
ggie | +0.081 |
song | +0.080 |
jokes | +0.080 |
wig | +0.078 |
Neg logit contributions | |
unst | -0.085 |
arp | -0.084 |
Joey | -0.083 |
sorts | -0.081 |
aved | -0.080 |
Token | came |
Token ID | 1625 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
arp | +0.099 |
unst | +0.096 |
Joey | +0.096 |
sorts | +0.095 |
aved | +0.094 |
Neg logit contributions | |
aids | -0.115 |
song | -0.100 |
jokes | -0.100 |
hair | -0.098 |
ggie | -0.098 |
Token | in |
Token ID | 287 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
aids | +0.042 |
song | +0.039 |
hair | +0.039 |
jokes | +0.038 |
ggie | +0.037 |
Neg logit contributions | |
arp | -0.034 |
sorts | -0.032 |
rolley | -0.031 |
Joey | -0.030 |
extingu | -0.030 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
aids | +0.066 |
song | +0.064 |
hair | +0.063 |
jokes | +0.062 |
songs | +0.057 |
Neg logit contributions | |
arp | -0.107 |
aved | -0.103 |
ucer | -0.102 |
pling | -0.098 |
ylan | -0.097 |
Token | to |
Token ID | 284 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
sorts | +0.705 |
Joey | +0.696 |
arp | +0.695 |
unst | +0.694 |
wood | +0.681 |
Neg logit contributions | |
aids | -0.967 |
Dancing | -0.839 |
jokes | -0.819 |
wig | -0.819 |
poems | -0.798 |
Token | carry |
Token ID | 3283 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
aids | +0.051 |
song | +0.048 |
jokes | +0.047 |
hair | +0.046 |
wig | +0.044 |
Neg logit contributions | |
arp | -0.057 |
aved | -0.055 |
ucer | -0.054 |
rolley | -0.054 |
erek | -0.053 |
Token | all |
Token ID | 477 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
aved | +0.239 |
ucer | +0.239 |
haven | +0.237 |
stack | +0.236 |
arp | +0.234 |
Neg logit contributions | |
hair | -0.138 |
aids | -0.117 |
jokes | -0.110 |
songs | -0.107 |
poems | -0.101 |
Token | of |
Token ID | 286 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
aved | +0.203 |
arp | +0.199 |
unst | +0.194 |
scaven | +0.192 |
erek | +0.191 |
Neg logit contributions | |
aids | -0.171 |
song | -0.150 |
hair | -0.150 |
jokes | -0.143 |
poems | -0.137 |
Token | the |
Token ID | 262 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
aved | +0.041 |
arp | +0.041 |
rolley | +0.041 |
ucer | +0.040 |
erek | +0.038 |
Neg logit contributions | |
hair | -0.022 |
jokes | -0.021 |
aids | -0.019 |
yoga | -0.019 |
song | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
Joey | +0.190 |
sorts | +0.188 |
unst | +0.186 |
arp | +0.182 |
Mill | +0.180 |
Neg logit contributions | |
aids | -0.321 |
cheeks | -0.277 |
wig | -0.272 |
jokes | -0.270 |
song | -0.269 |
Token | time |
Token ID | 640 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
scaven | +0.069 |
sorts | +0.067 |
Joey | +0.066 |
arp | +0.066 |
unst | +0.065 |
Neg logit contributions | |
aids | -0.059 |
wig | -0.048 |
cheeks | -0.047 |
jokes | -0.046 |
song | -0.046 |
Token | there |
Token ID | 612 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
aids | +0.251 |
hair | +0.213 |
ggie | +0.213 |
song | +0.212 |
jokes | +0.211 |
Neg logit contributions | |
arp | -0.343 |
sorts | -0.332 |
unst | -0.325 |
rolley | -0.325 |
aved | -0.324 |
Token | was |
Token ID | 373 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
arp | +0.039 |
unst | +0.037 |
sorts | +0.036 |
extingu | +0.036 |
wood | +0.036 |
Neg logit contributions | |
aids | -0.028 |
ggie | -0.026 |
hair | -0.025 |
Dancing | -0.025 |
song | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
Joey | +0.047 |
arp | +0.047 |
unst | +0.047 |
sorts | +0.047 |
aved | +0.046 |
Neg logit contributions | |
aids | -0.059 |
song | -0.050 |
jokes | -0.050 |
wig | -0.050 |
ggie | -0.049 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
arp | +0.046 |
Joey | +0.045 |
unst | +0.044 |
scaven | +0.043 |
Mill | +0.043 |
Neg logit contributions | |
aids | -0.052 |
jokes | -0.042 |
cheeks | -0.040 |
poems | -0.040 |
hair | -0.039 |
Token | man |
Token ID | 582 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
arp | +0.764 |
Joey | +0.749 |
sorts | +0.747 |
Mill | +0.740 |
extingu | +0.733 |
Neg logit contributions | |
aids | -0.927 |
jokes | -0.793 |
Dancing | -0.784 |
hair | -0.778 |
wig | -0.767 |
Token | who |
Token ID | 508 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
sorts | +0.085 |
Joey | +0.084 |
arp | +0.081 |
Mill | +0.080 |
extingu | +0.077 |
Neg logit contributions | |
aids | -0.121 |
jokes | -0.105 |
cheeks | -0.104 |
song | -0.102 |
uren | -0.101 |
Token | had |
Token ID | 550 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
aids | +0.093 |
ggie | +0.082 |
hair | +0.080 |
song | +0.080 |
jokes | +0.077 |
Neg logit contributions | |
arp | -0.117 |
unst | -0.114 |
Joey | -0.113 |
hed | -0.111 |
Mill | -0.109 |
Token | a |
Token ID | 257 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
aids | +0.103 |
jokes | +0.088 |
song | +0.088 |
Dancing | +0.087 |
wig | +0.087 |
Neg logit contributions | |
unst | -0.070 |
Joey | -0.070 |
arp | -0.069 |
sorts | -0.069 |
Mill | -0.068 |
Token | fancy |
Token ID | 14996 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
arp | +0.036 |
unst | +0.035 |
Joey | +0.035 |
sorts | +0.035 |
aved | +0.034 |
Neg logit contributions | |
aids | -0.038 |
jokes | -0.032 |
song | -0.032 |
hair | -0.032 |
ggie | -0.032 |
Token | is |
Token ID | 318 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
aids | +0.377 |
jokes | +0.314 |
song | +0.310 |
Dancing | +0.299 |
ggie | +0.298 |
Neg logit contributions | |
arp | -0.435 |
unst | -0.435 |
aved | -0.431 |
Joey | -0.424 |
afloat | -0.416 |
Token | that |
Token ID | 326 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
arp | +0.059 |
unst | +0.058 |
aved | +0.057 |
sorts | +0.057 |
Joey | +0.056 |
Neg logit contributions | |
aids | -0.046 |
jokes | -0.039 |
song | -0.039 |
ggie | -0.038 |
hair | -0.037 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
aids | +0.129 |
jokes | +0.120 |
song | +0.119 |
poems | +0.113 |
hair | +0.113 |
Neg logit contributions | |
arp | -0.117 |
aved | -0.115 |
rolley | -0.109 |
extingu | -0.108 |
unst | -0.107 |
Token | come |
Token ID | 1282 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
aids | +0.143 |
song | +0.132 |
jokes | +0.132 |
hair | +0.130 |
Dancing | +0.126 |
Neg logit contributions | |
arp | -0.110 |
extingu | -0.105 |
rolley | -0.104 |
hed | -0.103 |
Suz | -0.103 |
Token | in |
Token ID | 287 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
sorts | +0.003 |
arp | +0.003 |
aved | +0.003 |
hed | +0.003 |
Joey | +0.003 |
Neg logit contributions | |
aids | -0.002 |
hair | -0.002 |
song | -0.002 |
ggie | -0.002 |
Dancing | -0.002 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
aids | +0.082 |
song | +0.075 |
hair | +0.073 |
poems | +0.072 |
jokes | +0.072 |
Neg logit contributions | |
arp | -0.103 |
aved | -0.101 |
ucer | -0.095 |
rolley | -0.093 |
erek | -0.093 |
Token | in |
Token ID | 287 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
arp | +0.771 |
unst | +0.764 |
Joey | +0.759 |
sorts | +0.759 |
aved | +0.738 |
Neg logit contributions | |
aids | -0.899 |
song | -0.770 |
jokes | -0.769 |
wig | -0.761 |
hair | -0.755 |
Token | times |
Token ID | 1661 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
aids | +0.094 |
hair | +0.083 |
song | +0.082 |
jokes | +0.081 |
poems | +0.078 |
Neg logit contributions | |
arp | -0.085 |
aved | -0.083 |
erek | -0.080 |
ucer | -0.079 |
Joey | -0.079 |
Token | of |
Token ID | 286 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
aids | +0.057 |
hair | +0.049 |
jokes | +0.047 |
song | +0.047 |
Dancing | +0.046 |
Neg logit contributions | |
arp | -0.086 |
extingu | -0.084 |
aved | -0.081 |
unst | -0.080 |
sorts | -0.079 |
Token | need |
Token ID | 761 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
arp | +0.026 |
aved | +0.025 |
erek | +0.024 |
rolley | +0.024 |
ucer | +0.024 |
Neg logit contributions | |
aids | -0.027 |
jokes | -0.024 |
song | -0.024 |
hair | -0.024 |
poems | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
arp | +0.258 |
aved | +0.244 |
erek | +0.241 |
rolley | +0.236 |
ucer | +0.236 |
Neg logit contributions | |
aids | -0.218 |
jokes | -0.196 |
hair | -0.193 |
song | -0.192 |
poems | -0.185 |
Token | Maybe |
Token ID | 6674 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
aids | +0.073 |
song | +0.062 |
jokes | +0.061 |
hair | +0.060 |
wig | +0.060 |
Neg logit contributions | |
arp | -0.078 |
unst | -0.076 |
Joey | -0.076 |
sorts | -0.076 |
aved | -0.075 |
Token | it |
Token ID | 340 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
arp | +0.233 |
aved | +0.228 |
sorts | +0.225 |
unst | +0.225 |
Joey | +0.219 |
Neg logit contributions | |
aids | -0.245 |
song | -0.216 |
jokes | -0.215 |
hair | -0.214 |
wig | -0.211 |
Token | will |
Token ID | 481 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
arp | +0.095 |
Joey | +0.094 |
Mill | +0.090 |
sorts | +0.089 |
unst | +0.088 |
Neg logit contributions | |
aids | -0.107 |
hair | -0.093 |
jokes | -0.093 |
song | -0.092 |
ggie | -0.090 |
Token | come |
Token ID | 1282 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
arp | +0.480 |
rolley | +0.465 |
erek | +0.444 |
sorts | +0.441 |
aved | +0.440 |
Neg logit contributions | |
aids | -0.323 |
song | -0.293 |
jokes | -0.277 |
hair | -0.269 |
ggie | -0.253 |
Token | in |
Token ID | 287 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
sorts | +0.007 |
arp | +0.007 |
erek | +0.007 |
ylan | +0.007 |
hed | +0.007 |
Neg logit contributions | |
aids | -0.006 |
song | -0.006 |
hair | -0.006 |
songs | -0.005 |
poems | -0.005 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
aids | +0.076 |
song | +0.074 |
hair | +0.071 |
poems | +0.070 |
yoga | +0.067 |
Neg logit contributions | |
aved | -0.103 |
arp | -0.100 |
erek | -0.098 |
ucer | -0.096 |
ylan | -0.093 |
Token | one |
Token ID | 530 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
arp | +0.568 |
sorts | +0.561 |
unst | +0.560 |
Joey | +0.557 |
Mill | +0.534 |
Neg logit contributions | |
aids | -1.096 |
jokes | -0.964 |
Dancing | -0.958 |
song | -0.955 |
wig | -0.953 |
Token | day |
Token ID | 1110 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
aids | +0.215 |
song | +0.190 |
jokes | +0.187 |
hair | +0.185 |
ggie | +0.183 |
Neg logit contributions | |
arp | -0.173 |
unst | -0.171 |
Joey | -0.170 |
aved | -0.168 |
sorts | -0.167 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
aids | +0.096 |
song | +0.088 |
hair | +0.086 |
jokes | +0.085 |
poems | +0.084 |
Neg logit contributions | |
arp | -0.075 |
unst | -0.074 |
aved | -0.073 |
sorts | -0.070 |
Joey | -0.070 |
Token | |
Token ID | 220 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
arp | +0.232 |
unst | +0.229 |
Joey | +0.229 |
sorts | +0.226 |
Mill | +0.223 |
Neg logit contributions | |
aids | -0.272 |
jokes | -0.233 |
song | -0.233 |
ggie | -0.229 |
wig | -0.229 |
Token |
|
Token ID | 198 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
aids | +0.034 |
ggie | +0.028 |
Dancing | +0.028 |
Her | +0.027 |
hair | +0.027 |
Neg logit contributions | |
arp | -0.059 |
sorts | -0.058 |
extingu | -0.057 |
aved | -0.057 |
unst | -0.056 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
aids | +0.004 |
Dancing | +0.003 |
Her | +0.003 |
hair | +0.003 |
uren | +0.003 |
Neg logit contributions | |
arp | -0.006 |
aved | -0.006 |
unst | -0.006 |
afloat | -0.006 |
deeper | -0.006 |
Token | Grand |
Token ID | 23581 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
aids | +0.022 |
Dancing | +0.021 |
hair | +0.020 |
song | +0.019 |
ggie | +0.019 |
Neg logit contributions | |
unst | -0.017 |
arp | -0.016 |
extingu | -0.015 |
sorts | -0.015 |
aved | -0.015 |
Token | pa |
Token ID | 8957 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
arp | +0.046 |
Joey | +0.045 |
sorts | +0.045 |
unst | +0.045 |
Mill | +0.044 |
Neg logit contributions | |
aids | -0.072 |
song | -0.063 |
jokes | -0.063 |
ggie | -0.062 |
hair | -0.062 |
Token | was |
Token ID | 373 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
arp | +0.066 |
unst | +0.064 |
aved | +0.061 |
afloat | +0.061 |
ucer | +0.060 |
Neg logit contributions | |
aids | -0.046 |
jokes | -0.042 |
hair | -0.042 |
wig | -0.039 |
ggie | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Joey | +0.020 |
unst | +0.020 |
Mill | +0.020 |
sorts | +0.019 |
neath | +0.019 |
Neg logit contributions | |
aids | -0.025 |
jokes | -0.023 |
cheeks | -0.022 |
song | -0.022 |
wig | -0.022 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
Joey | +0.028 |
Mill | +0.027 |
sorts | +0.027 |
unst | +0.027 |
arp | +0.027 |
Neg logit contributions | |
aids | -0.033 |
jokes | -0.028 |
poems | -0.027 |
ggie | -0.027 |
wig | -0.026 |
Token | man |
Token ID | 582 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
arp | +0.755 |
Joey | +0.753 |
sorts | +0.751 |
Mill | +0.738 |
extingu | +0.723 |
Neg logit contributions | |
aids | -0.895 |
jokes | -0.769 |
Dancing | -0.758 |
hair | -0.756 |
wig | -0.751 |
Token | and |
Token ID | 290 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Joey | +0.070 |
sorts | +0.070 |
Mill | +0.068 |
arp | +0.068 |
unst | +0.066 |
Neg logit contributions | |
aids | -0.093 |
jokes | -0.081 |
song | -0.079 |
wig | -0.079 |
poems | -0.079 |
Token | he |
Token ID | 339 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
arp | +0.017 |
unst | +0.017 |
Joey | +0.016 |
aved | +0.016 |
sorts | +0.016 |
Neg logit contributions | |
aids | -0.016 |
jokes | -0.014 |
song | -0.014 |
hair | -0.013 |
wig | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
aids | +0.040 |
song | +0.035 |
jokes | +0.035 |
hair | +0.034 |
ggie | +0.034 |
Neg logit contributions | |
arp | -0.036 |
unst | -0.035 |
Joey | -0.035 |
sorts | -0.034 |
aved | -0.034 |
Token | lots |
Token ID | 6041 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
aids | +0.111 |
song | +0.096 |
jokes | +0.095 |
wig | +0.094 |
ggie | +0.093 |
Neg logit contributions | |
Joey | -0.087 |
sorts | -0.087 |
unst | -0.087 |
arp | -0.087 |
Mill | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
aids | +0.014 |
song | +0.012 |
hair | +0.012 |
ggie | +0.012 |
jokes | +0.011 |
Neg logit contributions | |
arp | -0.017 |
Joey | -0.017 |
sorts | -0.017 |
aved | -0.017 |
unst | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
aids | +0.010 |
jokes | +0.008 |
hair | +0.008 |
song | +0.008 |
Dancing | +0.008 |
Neg logit contributions | |
arp | -0.013 |
unst | -0.012 |
aved | -0.012 |
sorts | -0.012 |
Joey | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
arp | +0.024 |
unst | +0.024 |
sorts | +0.023 |
aved | +0.023 |
Joey | +0.023 |
Neg logit contributions | |
aids | -0.023 |
song | -0.019 |
ggie | -0.019 |
jokes | -0.019 |
Dancing | -0.019 |
Token | Then |
Token ID | 6423 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
arp | +0.022 |
sorts | +0.022 |
unst | +0.022 |
Joey | +0.022 |
aved | +0.021 |
Neg logit contributions | |
aids | -0.025 |
hair | -0.022 |
jokes | -0.022 |
cheeks | -0.022 |
wig | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
aids | +0.179 |
jokes | +0.155 |
hair | +0.155 |
song | +0.155 |
ggie | +0.151 |
Neg logit contributions | |
arp | -0.193 |
unst | -0.185 |
sorts | -0.184 |
aved | -0.183 |
Joey | -0.179 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
arp | +0.037 |
unst | +0.037 |
Joey | +0.037 |
sorts | +0.037 |
aved | +0.036 |
Neg logit contributions | |
aids | -0.039 |
jokes | -0.034 |
song | -0.033 |
wig | -0.033 |
hair | -0.033 |
Token | man |
Token ID | 582 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
arp | +0.838 |
unst | +0.820 |
Joey | +0.815 |
sorts | +0.814 |
Mill | +0.801 |
Neg logit contributions | |
aids | -0.818 |
jokes | -0.698 |
song | -0.684 |
wig | -0.683 |
hair | -0.682 |
Token | drove |
Token ID | 10357 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
arp | +0.087 |
sorts | +0.084 |
unst | +0.083 |
Joey | +0.083 |
hed | +0.083 |
Neg logit contributions | |
aids | -0.080 |
song | -0.069 |
ggie | -0.069 |
jokes | -0.068 |
hair | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
arp | +0.060 |
sorts | +0.057 |
aved | +0.056 |
unst | +0.056 |
Joey | +0.056 |
Neg logit contributions | |
aids | -0.090 |
song | -0.080 |
hair | -0.080 |
jokes | -0.079 |
ggie | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
aids | +0.057 |
jokes | +0.050 |
hair | +0.050 |
song | +0.050 |
haircut | +0.049 |
Neg logit contributions | |
arp | -0.095 |
aved | -0.093 |
ucer | -0.085 |
pling | -0.084 |
rol | -0.083 |
Token | young |
Token ID | 1862 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Joey | +0.038 |
aved | +0.038 |
sorts | +0.037 |
arp | +0.037 |
Suz | +0.036 |
Neg logit contributions | |
aids | -0.040 |
song | -0.037 |
hair | -0.037 |
jokes | -0.035 |
poems | -0.034 |
Token | compassionate |
Token ID | 32533 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
aids | +0.188 |
wig | +0.154 |
ggie | +0.152 |
song | +0.151 |
jokes | +0.149 |
Neg logit contributions | |
Joey | -0.213 |
arp | -0.211 |
unst | -0.209 |
sorts | -0.208 |
Mill | -0.204 |
Token | act |
Token ID | 719 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
aids | +0.040 |
song | +0.034 |
jokes | +0.034 |
hair | +0.033 |
ggie | +0.033 |
Neg logit contributions | |
arp | -0.047 |
unst | -0.046 |
Joey | -0.046 |
sorts | -0.046 |
aved | -0.045 |
Token | would |
Token ID | 561 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
aids | +0.023 |
song | +0.020 |
jokes | +0.019 |
hair | +0.019 |
ggie | +0.019 |
Neg logit contributions | |
arp | -0.021 |
Joey | -0.020 |
sorts | -0.020 |
unst | -0.020 |
hed | -0.019 |
Token | come |
Token ID | 1282 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
arp | +0.075 |
unst | +0.071 |
aved | +0.070 |
sorts | +0.069 |
rolley | +0.069 |
Neg logit contributions | |
aids | -0.061 |
song | -0.054 |
jokes | -0.053 |
hair | -0.051 |
ggie | -0.050 |
Token | in |
Token ID | 287 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
aids | +0.003 |
song | +0.003 |
hair | +0.003 |
jokes | +0.003 |
Dancing | +0.003 |
Neg logit contributions | |
arp | -0.004 |
sorts | -0.004 |
hed | -0.003 |
aved | -0.003 |
rolley | -0.003 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
aids | +0.086 |
song | +0.076 |
hair | +0.075 |
jokes | +0.074 |
poems | +0.073 |
Neg logit contributions | |
arp | -0.110 |
aved | -0.106 |
ucer | -0.102 |
erek | -0.100 |
unst | -0.099 |
Token | a |
Token ID | 257 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
arp | +0.716 |
sorts | +0.715 |
unst | +0.715 |
Joey | +0.712 |
Mill | +0.699 |
Neg logit contributions | |
aids | -0.916 |
Dancing | -0.789 |
jokes | -0.786 |
wig | -0.782 |
song | -0.769 |
Token | few |
Token ID | 1178 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
arp | +0.036 |
aved | +0.036 |
unst | +0.034 |
Joey | +0.034 |
neath | +0.034 |
Neg logit contributions | |
aids | -0.042 |
song | -0.039 |
jokes | -0.036 |
wig | -0.036 |
hair | -0.036 |
Token | days |
Token ID | 1528 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
aids | +0.126 |
wig | +0.106 |
Dancing | +0.106 |
ggie | +0.105 |
song | +0.105 |
Neg logit contributions | |
sorts | -0.133 |
arp | -0.133 |
unst | -0.132 |
Joey | -0.130 |
aved | -0.127 |
Token | later |
Token ID | 1568 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
aids | +0.065 |
hair | +0.056 |
song | +0.056 |
jokes | +0.055 |
ggie | +0.054 |
Neg logit contributions | |
arp | -0.076 |
unst | -0.072 |
Joey | -0.072 |
sorts | -0.072 |
aved | -0.071 |
Token | when |
Token ID | 618 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
arp | +0.078 |
unst | +0.076 |
sorts | +0.075 |
Joey | +0.075 |
aved | +0.074 |
Neg logit contributions | |
aids | -0.078 |
song | -0.067 |
jokes | -0.066 |
hair | -0.066 |
ggie | -0.065 |
Token | it |
Token ID | 340 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
aids | +0.190 |
jokes | +0.168 |
song | +0.166 |
hair | +0.163 |
poems | +0.163 |
Neg logit contributions | |
aved | -0.195 |
arp | -0.190 |
unst | -0.189 |
extingu | -0.186 |
afloat | -0.178 |
Token | 's |
Token ID | 338 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
arp | +0.117 |
unst | +0.112 |
aved | +0.111 |
Joey | +0.110 |
extingu | +0.108 |
Neg logit contributions | |
aids | -0.087 |
jokes | -0.075 |
song | -0.074 |
hair | -0.071 |
ggie | -0.070 |
Token | important |
Token ID | 1593 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
aids | +0.206 |
jokes | +0.179 |
song | +0.177 |
hair | +0.175 |
ggie | +0.172 |
Neg logit contributions | |
arp | -0.224 |
aved | -0.212 |
unst | -0.209 |
sorts | -0.205 |
Joey | -0.204 |
Token | to |
Token ID | 284 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
arp | +0.092 |
unst | +0.090 |
Joey | +0.089 |
sorts | +0.088 |
aved | +0.088 |
Neg logit contributions | |
aids | -0.090 |
song | -0.077 |
jokes | -0.077 |
hair | -0.076 |
ggie | -0.075 |
Token | keep |
Token ID | 1394 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
aids | +0.062 |
jokes | +0.054 |
song | +0.053 |
hair | +0.052 |
ggie | +0.051 |
Neg logit contributions | |
arp | -0.075 |
unst | -0.074 |
aved | -0.072 |
sorts | -0.072 |
rolley | -0.070 |
Token | hed |
Token ID | 16418 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
arp | +0.152 |
aved | +0.148 |
extingu | +0.143 |
erek | +0.141 |
sorts | +0.141 |
Neg logit contributions | |
aids | -0.167 |
hair | -0.152 |
jokes | -0.149 |
poems | -0.147 |
song | -0.147 |
Token | ges |
Token ID | 3212 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
sorts | +0.717 |
arp | +0.690 |
Joey | +0.684 |
unst | +0.684 |
hed | +0.682 |
Neg logit contributions | |
aids | -0.875 |
Dancing | -0.768 |
ggie | -0.740 |
wig | -0.739 |
song | -0.733 |
Token | neat |
Token ID | 15049 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
aved | +0.065 |
erek | +0.064 |
arp | +0.064 |
unst | +0.063 |
extingu | +0.062 |
Neg logit contributions | |
aids | -0.059 |
poems | -0.052 |
hair | -0.051 |
song | -0.051 |
jokes | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
arp | +0.387 |
aved | +0.382 |
unst | +0.378 |
neath | +0.376 |
Joey | +0.374 |
Neg logit contributions | |
aids | -0.369 |
hair | -0.337 |
jokes | -0.325 |
song | -0.324 |
poems | -0.322 |
Token | tidy |
Token ID | 43044 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
arp | +0.031 |
aved | +0.030 |
extingu | +0.029 |
neath | +0.029 |
rolley | +0.029 |
Neg logit contributions | |
aids | -0.031 |
song | -0.029 |
jokes | -0.029 |
hair | -0.028 |
poems | -0.027 |
Token | " |
Token ID | 1 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
aved | +0.234 |
arp | +0.233 |
unst | +0.224 |
neath | +0.223 |
sorts | +0.220 |
Neg logit contributions | |
aids | -0.293 |
hair | -0.270 |
jokes | -0.263 |
song | -0.261 |
poems | -0.258 |
Token | stood |
Token ID | 6204 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
aids | +0.066 |
song | +0.057 |
jokes | +0.057 |
hair | +0.056 |
wig | +0.056 |
Neg logit contributions | |
arp | -0.054 |
Joey | -0.053 |
unst | -0.053 |
sorts | -0.053 |
aved | -0.052 |
Token | back |
Token ID | 736 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
aids | +0.124 |
song | +0.109 |
jokes | +0.109 |
ggie | +0.107 |
wig | +0.107 |
Neg logit contributions | |
arp | -0.073 |
unst | -0.071 |
Joey | -0.071 |
sorts | -0.070 |
aved | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
aids | +0.048 |
hair | +0.043 |
song | +0.042 |
jokes | +0.041 |
cheeks | +0.040 |
Neg logit contributions | |
arp | -0.048 |
unst | -0.045 |
Joey | -0.045 |
sorts | -0.045 |
aved | -0.045 |
Token | admired |
Token ID | 29382 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
arp | +0.037 |
unst | +0.035 |
sorts | +0.035 |
Joey | +0.034 |
aved | +0.034 |
Neg logit contributions | |
aids | -0.031 |
hair | -0.027 |
song | -0.027 |
jokes | -0.027 |
wig | -0.026 |
Token | their |
Token ID | 511 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
arp | +0.081 |
unst | +0.078 |
sorts | +0.076 |
aved | +0.076 |
Joey | +0.076 |
Neg logit contributions | |
aids | -0.093 |
jokes | -0.082 |
hair | -0.081 |
song | -0.081 |
poems | -0.079 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
arp | +0.007 |
unst | +0.007 |
sorts | +0.007 |
Joey | +0.007 |
aved | +0.006 |
Neg logit contributions | |
aids | -0.014 |
song | -0.012 |
jokes | -0.012 |
ggie | -0.012 |
wig | -0.012 |
Token | work |
Token ID | 670 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
arp | +0.747 |
sorts | +0.744 |
unst | +0.741 |
Joey | +0.720 |
wood | +0.719 |
Neg logit contributions | |
aids | -0.862 |
Dancing | -0.742 |
wig | -0.732 |
jokes | -0.732 |
hair | -0.717 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
arp | +0.290 |
unst | +0.285 |
Joey | +0.284 |
sorts | +0.283 |
aved | +0.278 |
Neg logit contributions | |
aids | -0.319 |
song | -0.274 |
jokes | -0.274 |
hair | -0.269 |
wig | -0.268 |
Token | The |
Token ID | 383 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
arp | +0.000 |
unst | +0.000 |
aved | +0.000 |
Joey | +0.000 |
sorts | +0.000 |
Neg logit contributions | |
aids | -0.000 |
hair | -0.000 |
jokes | -0.000 |
Dancing | -0.000 |
song | -0.000 |
Token | screw |
Token ID | 9580 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
aids | +0.107 |
song | +0.094 |
jokes | +0.093 |
hair | +0.093 |
poems | +0.091 |
Neg logit contributions | |
arp | -0.091 |
Joey | -0.090 |
unst | -0.089 |
sorts | -0.088 |
aved | -0.088 |
Token | was |
Token ID | 373 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
arp | +0.307 |
unst | +0.301 |
Joey | +0.300 |
sorts | +0.298 |
aved | +0.292 |
Neg logit contributions | |
aids | -0.378 |
song | -0.328 |
jokes | -0.327 |
hair | -0.322 |
ggie | -0.321 |
Token | stepped |
Token ID | 10764 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
aids | +0.004 |
song | +0.003 |
jokes | +0.003 |
hair | +0.003 |
ggie | +0.003 |
Neg logit contributions | |
arp | -0.004 |
unst | -0.004 |
Joey | -0.004 |
sorts | -0.004 |
aved | -0.004 |
Token | back |
Token ID | 736 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
sorts | +0.020 |
arp | +0.019 |
Mill | +0.018 |
Joey | +0.018 |
hed | +0.018 |
Neg logit contributions | |
aids | -0.020 |
hair | -0.020 |
wig | -0.019 |
song | -0.018 |
Dancing | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
aids | +0.044 |
hair | +0.042 |
song | +0.039 |
jokes | +0.038 |
wig | +0.038 |
Neg logit contributions | |
arp | -0.054 |
unst | -0.051 |
aved | -0.051 |
sorts | -0.050 |
Joey | -0.050 |
Token | admire |
Token ID | 21099 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
aids | +0.078 |
jokes | +0.070 |
song | +0.070 |
hair | +0.068 |
wig | +0.066 |
Neg logit contributions | |
arp | -0.084 |
aved | -0.079 |
unst | -0.078 |
ucer | -0.075 |
rolley | -0.075 |
Token | his |
Token ID | 465 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
arp | +0.099 |
unst | +0.097 |
sorts | +0.095 |
aved | +0.095 |
Joey | +0.094 |
Neg logit contributions | |
aids | -0.123 |
jokes | -0.108 |
song | -0.107 |
hair | -0.106 |
ggie | -0.105 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
aids | +0.131 |
Dancing | +0.111 |
wig | +0.110 |
ggie | +0.109 |
jokes | +0.108 |
Neg logit contributions | |
unst | -0.090 |
sorts | -0.090 |
arp | -0.088 |
Joey | -0.087 |
Mill | -0.085 |
Token | work |
Token ID | 670 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
sorts | +0.773 |
arp | +0.769 |
unst | +0.755 |
Mill | +0.749 |
Joey | +0.749 |
Neg logit contributions | |
aids | -0.834 |
Dancing | -0.717 |
jokes | -0.708 |
wig | -0.688 |
hair | -0.682 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
arp | +0.286 |
unst | +0.281 |
Joey | +0.280 |
sorts | +0.279 |
aved | +0.274 |
Neg logit contributions | |
aids | -0.316 |
song | -0.271 |
jokes | -0.271 |
hair | -0.266 |
wig | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
aids | +0.010 |
Dancing | +0.008 |
jokes | +0.008 |
hair | +0.008 |
song | +0.008 |
Neg logit contributions | |
arp | -0.012 |
unst | -0.012 |
aved | -0.011 |
sorts | -0.011 |
Joey | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
arp | +0.027 |
unst | +0.027 |
extingu | +0.026 |
aved | +0.026 |
sorts | +0.026 |
Neg logit contributions | |
aids | -0.020 |
ggie | -0.017 |
Dancing | -0.017 |
song | -0.016 |
jokes | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
arp | +0.024 |
unst | +0.023 |
Joey | +0.023 |
sorts | +0.023 |
aved | +0.023 |
Neg logit contributions | |
aids | -0.022 |
song | -0.018 |
jokes | -0.018 |
ggie | -0.018 |
wig | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
aids | +0.083 |
song | +0.071 |
jokes | +0.071 |
hair | +0.070 |
wig | +0.070 |
Neg logit contributions | |
arp | -0.067 |
unst | -0.065 |
Joey | -0.065 |
sorts | -0.065 |
aved | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
aids | +0.030 |
song | +0.025 |
jokes | +0.025 |
hair | +0.025 |
wig | +0.024 |
Neg logit contributions | |
arp | -0.030 |
unst | -0.030 |
sorts | -0.029 |
aved | -0.029 |
Joey | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
arp | +0.007 |
unst | +0.007 |
aved | +0.007 |
sorts | +0.007 |
Joey | +0.007 |
Neg logit contributions | |
aids | -0.006 |
ggie | -0.005 |
song | -0.005 |
jokes | -0.005 |
Dancing | -0.005 |
Token | So |
Token ID | 2396 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
arp | +0.007 |
unst | +0.007 |
sorts | +0.007 |
Joey | +0.007 |
aved | +0.007 |
Neg logit contributions | |
aids | -0.007 |
jokes | -0.006 |
song | -0.006 |
hair | -0.006 |
wig | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
arp | +0.114 |
unst | +0.111 |
sorts | +0.110 |
aved | +0.109 |
Joey | +0.109 |
Neg logit contributions | |
aids | -0.125 |
song | -0.108 |
jokes | -0.108 |
hair | -0.107 |
ggie | -0.106 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
arp | +0.030 |
unst | +0.030 |
Joey | +0.030 |
sorts | +0.030 |
aved | +0.029 |
Neg logit contributions | |
aids | -0.026 |
song | -0.022 |
jokes | -0.022 |
hair | -0.022 |
ggie | -0.022 |
Token | man |
Token ID | 582 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
arp | +0.788 |
sorts | +0.766 |
unst | +0.766 |
Joey | +0.766 |
Mill | +0.757 |
Neg logit contributions | |
aids | -0.837 |
jokes | -0.718 |
Dancing | -0.707 |
hair | -0.703 |
wig | -0.702 |
Token | went |
Token ID | 1816 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
arp | +0.069 |
unst | +0.067 |
Joey | +0.067 |
hed | +0.067 |
sorts | +0.066 |
Neg logit contributions | |
aids | -0.070 |
ggie | -0.061 |
song | -0.061 |
hair | -0.060 |
jokes | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
arp | +0.064 |
Joey | +0.062 |
unst | +0.062 |
sorts | +0.062 |
aved | +0.061 |
Neg logit contributions | |
aids | -0.064 |
song | -0.055 |
jokes | -0.054 |
hair | -0.054 |
wig | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
aids | +0.069 |
jokes | +0.060 |
hair | +0.059 |
haircut | +0.059 |
song | +0.059 |
Neg logit contributions | |
arp | -0.113 |
aved | -0.108 |
ucer | -0.100 |
rol | -0.098 |
rolley | -0.097 |
Token | teach |
Token ID | 4545 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
arp | +0.026 |
Joey | +0.026 |
aved | +0.026 |
sorts | +0.026 |
unst | +0.025 |
Neg logit contributions | |
aids | -0.032 |
song | -0.029 |
hair | -0.029 |
jokes | -0.028 |
ggie | -0.027 |
Token | they |
Token ID | 484 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
arp | +0.008 |
unst | +0.008 |
aved | +0.008 |
sorts | +0.008 |
Joey | +0.008 |
Neg logit contributions | |
aids | -0.009 |
jokes | -0.008 |
song | -0.008 |
hair | -0.008 |
poems | -0.008 |
Token | would |
Token ID | 561 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
aids | +0.043 |
jokes | +0.038 |
song | +0.038 |
hair | +0.037 |
poems | +0.037 |
Neg logit contributions | |
arp | -0.042 |
unst | -0.041 |
Joey | -0.040 |
sorts | -0.040 |
hed | -0.039 |
Token | knock |
Token ID | 10643 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
arp | +0.066 |
unst | +0.064 |
Joey | +0.061 |
sorts | +0.061 |
aved | +0.061 |
Neg logit contributions | |
aids | -0.062 |
song | -0.054 |
jokes | -0.054 |
hair | -0.052 |
ggie | -0.050 |
Token | on |
Token ID | 319 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
aids | +0.262 |
hair | +0.248 |
jokes | +0.235 |
poems | +0.230 |
song | +0.229 |
Neg logit contributions | |
arp | -0.270 |
sorts | -0.263 |
aved | -0.261 |
hed | -0.258 |
unst | -0.257 |
Token | the |
Token ID | 262 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
aids | +0.200 |
hair | +0.183 |
jokes | +0.175 |
poems | +0.169 |
song | +0.160 |
Neg logit contributions | |
aved | -0.246 |
arp | -0.241 |
unst | -0.239 |
ucer | -0.236 |
sorts | -0.228 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
arp | +0.028 |
unst | +0.028 |
Joey | +0.027 |
sorts | +0.027 |
aved | +0.027 |
Neg logit contributions | |
aids | -0.039 |
song | -0.034 |
jokes | -0.034 |
ggie | -0.033 |
wig | -0.033 |
Token | man |
Token ID | 582 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
arp | +0.717 |
sorts | +0.688 |
unst | +0.688 |
wood | +0.684 |
extingu | +0.681 |
Neg logit contributions | |
aids | -0.900 |
jokes | -0.793 |
Dancing | -0.787 |
ggie | -0.775 |
wig | -0.775 |
Token | 's |
Token ID | 338 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
arp | +0.089 |
unst | +0.089 |
Joey | +0.088 |
sorts | +0.088 |
aved | +0.086 |
Neg logit contributions | |
aids | -0.065 |
song | -0.054 |
jokes | -0.053 |
ggie | -0.052 |
wig | -0.052 |
Token | door |
Token ID | 3420 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
aids | +0.267 |
ggie | +0.239 |
song | +0.235 |
jokes | +0.234 |
Dancing | +0.232 |
Neg logit contributions | |
arp | -0.174 |
unst | -0.173 |
Joey | -0.168 |
sorts | -0.166 |
Mill | -0.164 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
arp | +0.203 |
Joey | +0.198 |
unst | +0.197 |
aved | +0.195 |
sorts | +0.194 |
Neg logit contributions | |
aids | -0.187 |
song | -0.160 |
jokes | -0.157 |
hair | -0.157 |
poems | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
aids | +0.013 |
song | +0.011 |
jokes | +0.011 |
wig | +0.011 |
ggie | +0.011 |
Neg logit contributions | |
Joey | -0.015 |
arp | -0.014 |
sorts | -0.014 |
unst | -0.014 |
Mill | -0.014 |
Token | work |
Token ID | 670 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
aids | +0.070 |
jokes | +0.066 |
hair | +0.066 |
song | +0.063 |
blond | +0.062 |
Neg logit contributions | |
arp | -0.093 |
ucer | -0.088 |
rolley | -0.086 |
aved | -0.082 |
erek | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
arp | +0.338 |
aved | +0.310 |
Joey | +0.310 |
sorts | +0.306 |
unst | +0.305 |
Neg logit contributions | |
aids | -0.274 |
hair | -0.239 |
jokes | -0.236 |
song | -0.232 |
poems | -0.230 |
Token | They |
Token ID | 1119 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
aids | +0.016 |
hair | +0.013 |
jokes | +0.013 |
Dancing | +0.013 |
cheeks | +0.012 |
Neg logit contributions | |
arp | -0.019 |
unst | -0.018 |
aved | -0.018 |
sorts | -0.018 |
ucer | -0.017 |
Token | trimmed |
Token ID | 40325 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
arp | +0.043 |
unst | +0.040 |
wood | +0.039 |
extingu | +0.038 |
ucer | +0.038 |
Neg logit contributions | |
aids | -0.028 |
hair | -0.027 |
jokes | -0.025 |
cheeks | -0.025 |
curly | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
aids | +0.018 |
hair | +0.018 |
jokes | +0.017 |
cheeks | +0.017 |
song | +0.016 |
Neg logit contributions | |
arp | -0.022 |
aved | -0.021 |
scaven | -0.021 |
unst | -0.021 |
sorts | -0.021 |
Token | hed |
Token ID | 16418 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
sorts | +0.016 |
Joey | +0.016 |
arp | +0.015 |
aved | +0.015 |
unst | +0.015 |
Neg logit contributions | |
hair | -0.022 |
aids | -0.021 |
cheeks | -0.020 |
song | -0.020 |
jokes | -0.019 |
Token | ges |
Token ID | 3212 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
unst | +0.681 |
arp | +0.672 |
sorts | +0.667 |
Joey | +0.658 |
scaven | +0.650 |
Neg logit contributions | |
aids | -0.899 |
Dancing | -0.801 |
wig | -0.787 |
ggie | -0.762 |
hair | -0.753 |
Token | and |
Token ID | 290 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
arp | +0.058 |
ucer | +0.056 |
unst | +0.056 |
aved | +0.056 |
erek | +0.055 |
Neg logit contributions | |
aids | -0.050 |
hair | -0.045 |
jokes | -0.045 |
song | -0.043 |
poems | -0.042 |
Token | cut |
Token ID | 2005 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
arp | +0.008 |
aved | +0.007 |
unst | +0.007 |
rolley | +0.007 |
Joey | +0.007 |
Neg logit contributions | |
aids | -0.008 |
jokes | -0.007 |
hair | -0.007 |
song | -0.007 |
cheeks | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
arp | +0.079 |
sorts | +0.077 |
aved | +0.076 |
rolley | +0.075 |
scaven | +0.075 |
Neg logit contributions | |
aids | -0.080 |
hair | -0.076 |
jokes | -0.071 |
cheeks | -0.067 |
song | -0.067 |
Token | grass |
Token ID | 8701 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
sorts | +0.020 |
Joey | +0.020 |
arp | +0.019 |
erek | +0.019 |
neath | +0.019 |
Neg logit contributions | |
hair | -0.025 |
aids | -0.024 |
cheeks | -0.023 |
song | -0.023 |
jokes | -0.022 |
Token | for |
Token ID | 329 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
aids | +0.238 |
song | +0.220 |
jokes | +0.210 |
hair | +0.208 |
ggie | +0.207 |
Neg logit contributions | |
arp | -0.211 |
aved | -0.210 |
unst | -0.204 |
Joey | -0.202 |
erek | -0.200 |
Token | my |
Token ID | 616 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
arp | +0.176 |
unst | +0.171 |
sorts | +0.170 |
Joey | +0.169 |
aved | +0.167 |
Neg logit contributions | |
aids | -0.241 |
song | -0.211 |
jokes | -0.211 |
hair | -0.208 |
ggie | -0.207 |
Token | son |
Token ID | 3367 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
aids | +0.103 |
song | +0.088 |
jokes | +0.087 |
hair | +0.086 |
ggie | +0.085 |
Neg logit contributions | |
arp | -0.104 |
unst | -0.102 |
Joey | -0.102 |
sorts | -0.101 |
aved | -0.100 |
Token | ." |
Token ID | 526 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
arp | +0.133 |
unst | +0.131 |
Joey | +0.130 |
sorts | +0.130 |
aved | +0.127 |
Neg logit contributions | |
aids | -0.171 |
song | -0.149 |
jokes | -0.148 |
hair | -0.146 |
wig | -0.146 |
Token | The |
Token ID | 383 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
arp | +0.057 |
Joey | +0.057 |
unst | +0.057 |
sorts | +0.056 |
Mill | +0.056 |
Neg logit contributions | |
aids | -0.053 |
song | -0.045 |
jokes | -0.045 |
ggie | -0.044 |
wig | -0.044 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
aids | +0.112 |
jokes | +0.093 |
song | +0.093 |
wig | +0.091 |
ggie | +0.091 |
Neg logit contributions | |
arp | -0.127 |
unst | -0.125 |
Joey | -0.124 |
sorts | -0.124 |
Mill | -0.121 |
Token | man |
Token ID | 582 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
arp | +0.746 |
Joey | +0.729 |
sorts | +0.723 |
Mill | +0.722 |
unst | +0.720 |
Neg logit contributions | |
aids | -0.858 |
jokes | -0.743 |
Dancing | -0.740 |
hair | -0.729 |
wig | -0.729 |
Token | said |
Token ID | 531 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
Joey | +0.056 |
sorts | +0.055 |
Mill | +0.054 |
unst | +0.054 |
arp | +0.054 |
Neg logit contributions | |
aids | -0.074 |
Dancing | -0.066 |
poems | -0.064 |
wig | -0.064 |
song | -0.064 |
Token | he |
Token ID | 339 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
Joey | +0.004 |
unst | +0.004 |
Mill | +0.004 |
Bobby | +0.004 |
Suz | +0.004 |
Neg logit contributions | |
aids | -0.007 |
Dancing | -0.006 |
wig | -0.006 |
poems | -0.006 |
song | -0.006 |
Token | could |
Token ID | 714 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
aids | +0.060 |
jokes | +0.052 |
song | +0.052 |
ggie | +0.052 |
hair | +0.051 |
Neg logit contributions | |
arp | -0.049 |
unst | -0.047 |
Joey | -0.047 |
sorts | -0.047 |
aved | -0.045 |
Token | help |
Token ID | 1037 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
arp | +0.091 |
sorts | +0.087 |
hed | +0.086 |
Joey | +0.085 |
aved | +0.085 |
Neg logit contributions | |
aids | -0.096 |
hair | -0.086 |
song | -0.085 |
ggie | -0.084 |
jokes | -0.084 |
Token | of |
Token ID | 286 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
arp | +0.226 |
extingu | +0.225 |
aved | +0.217 |
sorts | +0.211 |
hed | +0.211 |
Neg logit contributions | |
aids | -0.197 |
song | -0.169 |
ggie | -0.167 |
jokes | -0.166 |
cheeks | -0.165 |
Token | salt |
Token ID | 8268 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
hair | +0.004 |
aids | +0.004 |
jokes | +0.004 |
wig | +0.004 |
poems | +0.004 |
Neg logit contributions | |
aved | -0.004 |
unst | -0.004 |
Mill | -0.003 |
neath | -0.003 |
arp | -0.003 |
Token | could |
Token ID | 714 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
arp | +0.245 |
aved | +0.237 |
sorts | +0.230 |
unst | +0.230 |
rolley | +0.224 |
Neg logit contributions | |
aids | -0.303 |
jokes | -0.278 |
hair | -0.272 |
song | -0.271 |
poems | -0.268 |
Token | come |
Token ID | 1282 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
sorts | +0.107 |
arp | +0.104 |
rolley | +0.103 |
aved | +0.102 |
erek | +0.102 |
Neg logit contributions | |
aids | -0.078 |
song | -0.069 |
hair | -0.068 |
ggie | -0.067 |
jokes | -0.067 |
Token | in |
Token ID | 287 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
aids | +0.018 |
song | +0.018 |
hair | +0.017 |
ggie | +0.016 |
songs | +0.015 |
Neg logit contributions | |
sorts | -0.020 |
erek | -0.019 |
hed | -0.019 |
aved | -0.018 |
ylan | -0.018 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
aids | +0.095 |
song | +0.090 |
hair | +0.089 |
poems | +0.083 |
yoga | +0.082 |
Neg logit contributions | |
aved | -0.127 |
ucer | -0.119 |
erek | -0.118 |
arp | -0.117 |
vell | -0.110 |
Token | ," |
Token ID | 553 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
arp | +0.612 |
unst | +0.595 |
Joey | +0.589 |
sorts | +0.586 |
aved | +0.581 |
Neg logit contributions | |
aids | -1.010 |
song | -0.897 |
jokes | -0.891 |
ggie | -0.881 |
hair | -0.881 |
Token | so |
Token ID | 523 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Joey | +0.171 |
arp | +0.171 |
unst | +0.168 |
sorts | +0.166 |
Mill | +0.166 |
Neg logit contributions | |
aids | -0.185 |
song | -0.157 |
jokes | -0.156 |
wig | -0.154 |
ggie | -0.153 |
Token | he |
Token ID | 339 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
aids | +0.089 |
song | +0.076 |
jokes | +0.076 |
hair | +0.074 |
wig | +0.074 |
Neg logit contributions | |
arp | -0.091 |
unst | -0.090 |
Joey | -0.089 |
sorts | -0.089 |
aved | -0.087 |
Token | scoop |
Token ID | 23529 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
aids | +0.058 |
Dancing | +0.051 |
song | +0.049 |
jokes | +0.048 |
poems | +0.048 |
Neg logit contributions | |
Joey | -0.046 |
unst | -0.046 |
arp | -0.045 |
Mill | -0.044 |
scaven | -0.044 |
Token | ed |
Token ID | 276 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
sorts | +0.087 |
hed | +0.084 |
scaven | +0.084 |
haven | +0.084 |
shed | +0.083 |
Neg logit contributions | |
aids | -0.055 |
hair | -0.055 |
ggie | -0.049 |
jokes | -0.046 |
cheeks | -0.045 |
Token | Mr |
Token ID | 1770 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
aids | +0.033 |
jokes | +0.029 |
hair | +0.029 |
song | +0.028 |
poems | +0.028 |
Neg logit contributions | |
arp | -0.034 |
Joey | -0.033 |
unst | -0.033 |
sorts | -0.033 |
aved | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
arp | +0.366 |
unst | +0.356 |
Joey | +0.355 |
sorts | +0.352 |
aved | +0.348 |
Neg logit contributions | |
aids | -0.385 |
song | -0.326 |
jokes | -0.326 |
wig | -0.320 |
hair | -0.319 |
Token | Lee |
Token ID | 5741 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
aids | +0.060 |
jokes | +0.052 |
song | +0.052 |
hair | +0.051 |
wig | +0.051 |
Neg logit contributions | |
arp | -0.048 |
unst | -0.047 |
sorts | -0.047 |
aved | -0.047 |
Joey | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
aids | +0.104 |
song | +0.091 |
ggie | +0.089 |
wig | +0.088 |
jokes | +0.088 |
Neg logit contributions | |
unst | -0.087 |
Joey | -0.084 |
sorts | -0.084 |
aved | -0.084 |
arp | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
aids | +0.008 |
jokes | +0.007 |
song | +0.007 |
hair | +0.007 |
wig | +0.007 |
Neg logit contributions | |
arp | -0.008 |
unst | -0.008 |
sorts | -0.008 |
Joey | -0.008 |
aved | -0.008 |
Token | handy |
Token ID | 15728 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
arp | +0.013 |
unst | +0.013 |
sorts | +0.013 |
Joey | +0.013 |
aved | +0.013 |
Neg logit contributions | |
aids | -0.013 |
jokes | -0.011 |
ggie | -0.010 |
song | -0.010 |
hair | -0.010 |
Token | man |
Token ID | 805 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
arp | +0.737 |
extingu | +0.714 |
sorts | +0.711 |
Joey | +0.701 |
unst | +0.700 |
Neg logit contributions | |
aids | -0.850 |
jokes | -0.736 |
Dancing | -0.728 |
wig | -0.716 |
poems | -0.715 |
Token | . |
Token ID | 13 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
aids | +0.060 |
song | +0.052 |
jokes | +0.051 |
poems | +0.050 |
ggie | +0.050 |
Neg logit contributions | |
unst | -0.050 |
Joey | -0.050 |
arp | -0.050 |
sorts | -0.049 |
aved | -0.048 |
Token | He |
Token ID | 679 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
aids | +0.053 |
song | +0.045 |
jokes | +0.045 |
ggie | +0.044 |
hair | +0.044 |
Neg logit contributions | |
arp | -0.053 |
unst | -0.052 |
Joey | -0.052 |
sorts | -0.052 |
aved | -0.051 |
Token | is |
Token ID | 318 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
aids | +0.034 |
jokes | +0.029 |
song | +0.029 |
hair | +0.029 |
wig | +0.029 |
Neg logit contributions | |
arp | -0.031 |
unst | -0.030 |
Joey | -0.030 |
sorts | -0.030 |
aved | -0.029 |
Token | fixing |
Token ID | 18682 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
unst | +0.014 |
Joey | +0.013 |
handy | +0.013 |
Mill | +0.013 |
deeper | +0.013 |
Neg logit contributions | |
aids | -0.014 |
cheeks | -0.012 |
song | -0.012 |
jokes | -0.012 |
uren | -0.012 |
Token | excitement |
Token ID | 14067 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
aids | +0.087 |
poems | +0.071 |
uren | +0.070 |
wig | +0.070 |
ggie | +0.069 |
Neg logit contributions | |
Joey | -0.095 |
unst | -0.092 |
arp | -0.091 |
afloat | -0.089 |
aved | -0.088 |
Token | growing |
Token ID | 3957 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
aids | +0.019 |
jokes | +0.016 |
song | +0.016 |
wig | +0.016 |
ggie | +0.016 |
Neg logit contributions | |
arp | -0.015 |
unst | -0.015 |
Joey | -0.015 |
sorts | -0.015 |
aved | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
arp | +0.214 |
sorts | +0.207 |
Joey | +0.206 |
Mill | +0.206 |
unst | +0.202 |
Neg logit contributions | |
aids | -0.238 |
song | -0.211 |
hair | -0.206 |
jokes | -0.206 |
ggie | -0.202 |
Token | He |
Token ID | 679 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Joey | +0.011 |
arp | +0.010 |
unst | +0.010 |
sorts | +0.010 |
Mill | +0.010 |
Neg logit contributions | |
aids | -0.010 |
song | -0.009 |
jokes | -0.009 |
wig | -0.009 |
poems | -0.009 |
Token | quickly |
Token ID | 2952 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
arp | +0.017 |
Joey | +0.017 |
unst | +0.016 |
sorts | +0.016 |
aved | +0.016 |
Neg logit contributions | |
aids | -0.020 |
song | -0.017 |
jokes | -0.017 |
wig | -0.017 |
hair | -0.017 |
Token | shed |
Token ID | 14999 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
arp | +0.357 |
unst | +0.350 |
Joey | +0.348 |
sorts | +0.347 |
aved | +0.340 |
Neg logit contributions | |
aids | -0.379 |
song | -0.326 |
jokes | -0.326 |
hair | -0.320 |
ggie | -0.318 |
Token | his |
Token ID | 465 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
sorts | +0.755 |
arp | +0.749 |
Joey | +0.715 |
aved | +0.698 |
Mill | +0.697 |
Neg logit contributions | |
aids | -0.727 |
hair | -0.652 |
ggie | -0.630 |
cheeks | -0.625 |
song | -0.618 |
Token | clothes |
Token ID | 8242 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
aids | +0.081 |
song | +0.065 |
Dancing | +0.065 |
ggie | +0.065 |
jokes | +0.065 |
Neg logit contributions | |
arp | -0.096 |
Joey | -0.096 |
unst | -0.095 |
sorts | -0.092 |
Mill | -0.091 |
Token | and |
Token ID | 290 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
hair | +0.030 |
aids | +0.030 |
cheeks | +0.029 |
song | +0.027 |
wig | +0.026 |
Neg logit contributions | |
sorts | -0.048 |
arp | -0.047 |
Joey | -0.044 |
hed | -0.044 |
Mill | -0.044 |
Token | plunged |
Token ID | 31460 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
arp | +0.041 |
aved | +0.039 |
sorts | +0.038 |
unst | +0.038 |
neath | +0.037 |
Neg logit contributions | |
aids | -0.030 |
hair | -0.029 |
cheeks | -0.028 |
jokes | -0.027 |
wig | -0.027 |
Token | into |
Token ID | 656 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
sorts | +0.236 |
arp | +0.234 |
rolley | +0.228 |
ucer | +0.216 |
pling | +0.214 |
Neg logit contributions | |
hair | -0.175 |
aids | -0.149 |
curly | -0.149 |
blond | -0.143 |
cheeks | -0.139 |
Token | he |
Token ID | 339 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
aids | +0.078 |
Dancing | +0.069 |
wig | +0.068 |
poems | +0.067 |
song | +0.066 |
Neg logit contributions | |
Joey | -0.051 |
Mill | -0.048 |
Bobby | -0.045 |
sorts | -0.045 |
unst | -0.044 |
Token | went |
Token ID | 1816 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
aids | +0.030 |
Dancing | +0.025 |
song | +0.025 |
jokes | +0.025 |
hair | +0.025 |
Neg logit contributions | |
Joey | -0.023 |
unst | -0.022 |
arp | -0.022 |
aved | -0.022 |
sorts | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
arp | +0.079 |
sorts | +0.076 |
aved | +0.074 |
Joey | +0.074 |
unst | +0.074 |
Neg logit contributions | |
aids | -0.098 |
hair | -0.087 |
jokes | -0.087 |
song | -0.086 |
wig | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
aids | +0.053 |
jokes | +0.047 |
song | +0.045 |
hair | +0.045 |
haircut | +0.044 |
Neg logit contributions | |
arp | -0.063 |
aved | -0.058 |
ucer | -0.056 |
rolley | -0.056 |
pling | -0.053 |
Token | garden |
Token ID | 11376 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
arp | +0.048 |
unst | +0.047 |
Joey | +0.047 |
sorts | +0.047 |
hed | +0.046 |
Neg logit contributions | |
aids | -0.054 |
jokes | -0.044 |
cheeks | -0.044 |
poems | -0.044 |
Dancing | -0.044 |
Token | shed |
Token ID | 14999 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
arp | +0.250 |
aved | +0.242 |
unst | +0.240 |
Joey | +0.236 |
neath | +0.234 |
Neg logit contributions | |
aids | -0.173 |
song | -0.149 |
hair | -0.148 |
jokes | -0.146 |
poems | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
arp | +0.886 |
aved | +0.850 |
Joey | +0.839 |
sorts | +0.828 |
neath | +0.826 |
Neg logit contributions | |
aids | -0.582 |
hair | -0.506 |
song | -0.495 |
jokes | -0.472 |
cheeks | -0.466 |
Token | found |
Token ID | 1043 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
arp | +0.040 |
aved | +0.035 |
sorts | +0.034 |
rolley | +0.034 |
unst | +0.034 |
Neg logit contributions | |
aids | -0.027 |
hair | -0.025 |
cheeks | -0.023 |
wig | -0.023 |
song | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
arp | +0.454 |
rying | +0.433 |
aved | +0.428 |
haven | +0.423 |
keeping | +0.421 |
Neg logit contributions | |
hair | -0.135 |
aids | -0.135 |
jokes | -0.118 |
His | -0.115 |
ggie | -0.111 |
Token | stick |
Token ID | 4859 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
arp | +0.042 |
aved | +0.041 |
neath | +0.040 |
Joey | +0.039 |
unst | +0.039 |
Neg logit contributions | |
aids | -0.043 |
song | -0.041 |
wig | -0.040 |
hair | -0.039 |
ggie | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
arp | +0.132 |
Joey | +0.127 |
sorts | +0.127 |
unst | +0.126 |
Mill | +0.126 |
Neg logit contributions | |
aids | -0.116 |
song | -0.100 |
hair | -0.099 |
jokes | -0.098 |
ggie | -0.097 |
Token | a |
Token ID | 257 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
arp | +0.014 |
unst | +0.014 |
Joey | +0.014 |
sorts | +0.014 |
aved | +0.013 |
Neg logit contributions | |
aids | -0.015 |
jokes | -0.013 |
song | -0.013 |
hair | -0.013 |
ggie | -0.013 |
Token | little |
Token ID | 1310 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
arp | +0.016 |
Joey | +0.016 |
unst | +0.016 |
Mill | +0.015 |
sorts | +0.015 |
Neg logit contributions | |
aids | -0.017 |
jokes | -0.014 |
cheeks | -0.014 |
poems | -0.014 |
hair | -0.014 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
aids | +0.081 |
song | +0.075 |
hair | +0.073 |
wig | +0.072 |
jokes | +0.071 |
Neg logit contributions | |
unst | -0.096 |
aved | -0.093 |
arp | -0.093 |
sorts | -0.093 |
Joey | -0.091 |
Token | named |
Token ID | 3706 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
arp | +0.010 |
sorts | +0.010 |
Mill | +0.010 |
Joey | +0.009 |
Suz | +0.009 |
Neg logit contributions | |
aids | -0.014 |
jokes | -0.012 |
cheeks | -0.012 |
poems | -0.012 |
uren | -0.012 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
aids | +0.112 |
jokes | +0.095 |
wig | +0.094 |
song | +0.093 |
ggie | +0.093 |
Neg logit contributions | |
Mill | -0.103 |
unst | -0.101 |
Joey | -0.100 |
arp | -0.099 |
sorts | -0.098 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
arp | +0.093 |
Mill | +0.092 |
sorts | +0.090 |
Joey | +0.089 |
aved | +0.087 |
Neg logit contributions | |
aids | -0.137 |
jokes | -0.122 |
poems | -0.116 |
wig | -0.115 |
Dancing | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
aids | +0.771 |
jokes | +0.657 |
song | +0.648 |
wig | +0.640 |
poems | +0.639 |
Neg logit contributions | |
arp | -0.712 |
unst | -0.702 |
Joey | -0.695 |
sorts | -0.692 |
aved | -0.687 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
aids | +0.027 |
song | +0.023 |
jokes | +0.023 |
hair | +0.023 |
Dancing | +0.023 |
Neg logit contributions | |
arp | -0.028 |
unst | -0.028 |
Joey | -0.028 |
sorts | -0.027 |
aved | -0.027 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
arp | +0.146 |
sorts | +0.143 |
Mill | +0.143 |
Joey | +0.142 |
aved | +0.140 |
Neg logit contributions | |
aids | -0.087 |
jokes | -0.071 |
wig | -0.069 |
poems | -0.067 |
song | -0.066 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
aids | +0.746 |
hair | +0.652 |
song | +0.650 |
jokes | +0.640 |
ggie | +0.636 |
Neg logit contributions | |
arp | -0.713 |
unst | -0.703 |
Joey | -0.694 |
sorts | -0.684 |
aved | -0.668 |
Token | in |
Token ID | 287 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
arp | +0.113 |
Joey | +0.110 |
unst | +0.110 |
sorts | +0.109 |
aved | +0.107 |
Neg logit contributions | |
aids | -0.115 |
song | -0.100 |
jokes | -0.099 |
hair | -0.099 |
ggie | -0.097 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
aids | +0.315 |
song | +0.264 |
jokes | +0.264 |
wig | +0.264 |
Dancing | +0.262 |
Neg logit contributions | |
arp | -0.267 |
sorts | -0.263 |
unst | -0.260 |
Joey | -0.260 |
aved | -0.256 |
Token | or |
Token ID | 393 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Joey | +0.007 |
unst | +0.007 |
arp | +0.007 |
sorts | +0.007 |
Mill | +0.007 |
Neg logit contributions | |
aids | -0.009 |
ggie | -0.007 |
song | -0.007 |
jokes | -0.007 |
wig | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
aids | +0.115 |
ggie | +0.102 |
wig | +0.099 |
uren | +0.099 |
song | +0.098 |
Neg logit contributions | |
Joey | -0.073 |
sorts | -0.070 |
Mill | -0.070 |
unst | -0.070 |
deeper | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
aids | +0.119 |
hair | +0.104 |
song | +0.103 |
jokes | +0.103 |
poems | +0.101 |
Neg logit contributions | |
arp | -0.112 |
unst | -0.108 |
Joey | -0.108 |
aved | -0.107 |
Mill | -0.104 |
Token | sav |
Token ID | 6799 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
arp | +0.023 |
unst | +0.022 |
Joey | +0.022 |
sorts | +0.022 |
aved | +0.022 |
Neg logit contributions | |
aids | -0.029 |
song | -0.025 |
jokes | -0.025 |
hair | -0.025 |
wig | -0.025 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
arp | +0.222 |
unst | +0.219 |
rying | +0.207 |
ylan | +0.206 |
aved | +0.206 |
Neg logit contributions | |
aids | -0.281 |
song | -0.250 |
jokes | -0.249 |
ggie | -0.242 |
Dancing | -0.239 |
Token | with |
Token ID | 351 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
aids | +0.777 |
jokes | +0.663 |
song | +0.658 |
ggie | +0.656 |
wig | +0.655 |
Neg logit contributions | |
arp | -0.690 |
unst | -0.684 |
Joey | -0.678 |
sorts | -0.672 |
aved | -0.666 |
Token | the |
Token ID | 262 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
aids | +0.069 |
song | +0.059 |
jokes | +0.059 |
hair | +0.058 |
wig | +0.058 |
Neg logit contributions | |
arp | -0.057 |
unst | -0.056 |
Joey | -0.055 |
sorts | -0.055 |
aved | -0.054 |
Token | lion |
Token ID | 18744 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
arp | +0.028 |
unst | +0.027 |
Joey | +0.027 |
sorts | +0.027 |
aved | +0.026 |
Neg logit contributions | |
aids | -0.028 |
ggie | -0.023 |
jokes | -0.023 |
song | -0.023 |
wig | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
aids | +0.190 |
wig | +0.162 |
ggie | +0.161 |
Dancing | +0.160 |
uren | +0.159 |
Neg logit contributions | |
Joey | -0.150 |
arp | -0.150 |
sorts | -0.149 |
Mill | -0.146 |
unst | -0.145 |
Token | or |
Token ID | 393 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Joey | +0.012 |
unst | +0.012 |
sorts | +0.012 |
arp | +0.012 |
Mill | +0.011 |
Neg logit contributions | |
aids | -0.014 |
ggie | -0.012 |
song | -0.012 |
jokes | -0.012 |
wig | -0.012 |
Token | little |
Token ID | 1310 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Joey | +0.002 |
arp | +0.002 |
unst | +0.002 |
sorts | +0.002 |
deeper | +0.002 |
Neg logit contributions | |
aids | -0.003 |
ggie | -0.003 |
hair | -0.003 |
poems | -0.003 |
uren | -0.003 |
Token | fish |
Token ID | 5916 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
aids | +0.123 |
song | +0.107 |
jokes | +0.107 |
ggie | +0.106 |
hair | +0.106 |
Neg logit contributions | |
arp | -0.080 |
Joey | -0.079 |
unst | -0.078 |
sorts | -0.078 |
aved | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
aids | +0.040 |
poems | +0.034 |
uren | +0.034 |
wig | +0.034 |
hair | +0.033 |
Neg logit contributions | |
Joey | -0.029 |
sorts | -0.028 |
arp | -0.028 |
unst | -0.027 |
aved | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
aids | +0.030 |
song | +0.025 |
poems | +0.025 |
wig | +0.025 |
ggie | +0.025 |
Neg logit contributions | |
Joey | -0.028 |
Mill | -0.026 |
Bobby | -0.024 |
unst | -0.024 |
Suz | -0.024 |
Token | W |
Token ID | 54 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
aids | +0.064 |
cheeks | +0.057 |
hair | +0.056 |
poems | +0.056 |
jokes | +0.055 |
Neg logit contributions | |
arp | -0.039 |
Joey | -0.038 |
sorts | -0.037 |
unst | -0.037 |
aved | -0.036 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
aids | +0.008 |
jokes | +0.007 |
ggie | +0.007 |
song | +0.007 |
hair | +0.007 |
Neg logit contributions | |
arp | -0.011 |
unst | -0.011 |
neath | -0.011 |
extingu | -0.011 |
aved | -0.011 |
Token | play |
Token ID | 711 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
aids | +0.729 |
jokes | +0.666 |
song | +0.662 |
hair | +0.659 |
Dancing | +0.639 |
Neg logit contributions | |
arp | -0.726 |
extingu | -0.680 |
unst | -0.675 |
rolley | -0.672 |
neath | -0.671 |
Token | with |
Token ID | 351 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
aids | +0.167 |
jokes | +0.153 |
song | +0.152 |
ggie | +0.144 |
poems | +0.143 |
Neg logit contributions | |
arp | -0.185 |
Mill | -0.179 |
unst | -0.179 |
aved | -0.179 |
extingu | -0.177 |
Token | me |
Token ID | 502 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
aids | +0.054 |
jokes | +0.052 |
song | +0.046 |
hair | +0.046 |
poems | +0.044 |
Neg logit contributions | |
arp | -0.089 |
aved | -0.088 |
rolley | -0.087 |
extingu | -0.086 |
ucer | -0.086 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
aids | +0.188 |
song | +0.169 |
jokes | +0.168 |
hair | +0.166 |
ggie | +0.165 |
Neg logit contributions | |
arp | -0.119 |
unst | -0.115 |
Joey | -0.114 |
sorts | -0.112 |
aved | -0.112 |
Token | Bob |
Token ID | 5811 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
aids | +0.274 |
poems | +0.240 |
wig | +0.235 |
song | +0.234 |
ggie | +0.228 |
Neg logit contributions | |
Joey | -0.150 |
Mill | -0.133 |
Bobby | -0.123 |
Suz | -0.120 |
Wil | -0.119 |
Token | named |
Token ID | 3706 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
arp | +0.010 |
sorts | +0.010 |
Mill | +0.010 |
Joey | +0.009 |
Suz | +0.009 |
Neg logit contributions | |
aids | -0.014 |
jokes | -0.012 |
cheeks | -0.012 |
poems | -0.012 |
uren | -0.012 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
aids | +0.112 |
jokes | +0.095 |
wig | +0.094 |
song | +0.093 |
ggie | +0.093 |
Neg logit contributions | |
Mill | -0.103 |
unst | -0.101 |
Joey | -0.100 |
arp | -0.099 |
sorts | -0.098 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
arp | +0.093 |
Mill | +0.092 |
sorts | +0.090 |
Joey | +0.089 |
aved | +0.087 |
Neg logit contributions | |
aids | -0.137 |
jokes | -0.122 |
poems | -0.116 |
wig | -0.115 |
Dancing | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
aids | +0.771 |
jokes | +0.657 |
song | +0.648 |
wig | +0.640 |
poems | +0.639 |
Neg logit contributions | |
arp | -0.712 |
unst | -0.702 |
Joey | -0.695 |
sorts | -0.692 |
aved | -0.687 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
aids | +0.027 |
song | +0.023 |
jokes | +0.023 |
hair | +0.023 |
Dancing | +0.023 |
Neg logit contributions | |
arp | -0.028 |
unst | -0.028 |
Joey | -0.028 |
sorts | -0.027 |
aved | -0.027 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
arp | +0.146 |
sorts | +0.143 |
Mill | +0.143 |
Joey | +0.142 |
aved | +0.140 |
Neg logit contributions | |
aids | -0.087 |
jokes | -0.071 |
wig | -0.069 |
poems | -0.067 |
song | -0.066 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
aids | +0.746 |
hair | +0.652 |
song | +0.650 |
jokes | +0.640 |
ggie | +0.636 |
Neg logit contributions | |
arp | -0.713 |
unst | -0.703 |
Joey | -0.694 |
sorts | -0.684 |
aved | -0.668 |
Token | in |
Token ID | 287 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
arp | +0.113 |
Joey | +0.110 |
unst | +0.110 |
sorts | +0.109 |
aved | +0.107 |
Neg logit contributions | |
aids | -0.115 |
song | -0.100 |
jokes | -0.099 |
hair | -0.099 |
ggie | -0.097 |
Token | a |
Token ID | 257 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
aids | +0.118 |
song | +0.102 |
jokes | +0.101 |
hair | +0.100 |
ggie | +0.099 |
Neg logit contributions | |
arp | -0.110 |
unst | -0.108 |
Joey | -0.107 |
sorts | -0.106 |
aved | -0.105 |
Token | village |
Token ID | 7404 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
arp | +0.016 |
unst | +0.015 |
Joey | +0.015 |
sorts | +0.015 |
aved | +0.015 |
Neg logit contributions | |
aids | -0.017 |
song | -0.014 |
jokes | -0.014 |
hair | -0.014 |
wig | -0.014 |
Token | near |
Token ID | 1474 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
sorts | +0.160 |
arp | +0.158 |
Joey | +0.153 |
unst | +0.152 |
Mill | +0.150 |
Neg logit contributions | |
aids | -0.188 |
jokes | -0.162 |
wig | -0.158 |
poems | -0.157 |
song | -0.156 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
aids | +0.360 |
cheeks | +0.309 |
uren | +0.303 |
Dancing | +0.290 |
ggie | +0.287 |
Neg logit contributions | |
unst | -0.279 |
sorts | -0.262 |
Joey | -0.259 |
arp | -0.249 |
deeper | -0.246 |
Token | . |
Token ID | 13 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
aids | +0.215 |
cheeks | +0.183 |
uren | +0.183 |
wig | +0.180 |
jokes | +0.180 |
Neg logit contributions | |
arp | -0.141 |
unst | -0.140 |
sorts | -0.136 |
Joey | -0.132 |
aved | -0.128 |
Token | But |
Token ID | 887 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
aids | +0.074 |
poems | +0.065 |
ggie | +0.065 |
wig | +0.064 |
song | +0.063 |
Neg logit contributions | |
Joey | -0.053 |
unst | -0.051 |
arp | -0.051 |
Mill | -0.050 |
sorts | -0.049 |
Token | no |
Token ID | 645 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
aids | +0.123 |
song | +0.104 |
jokes | +0.104 |
ggie | +0.103 |
hair | +0.103 |
Neg logit contributions | |
arp | -0.111 |
unst | -0.110 |
Joey | -0.110 |
sorts | -0.108 |
Mill | -0.106 |
Token | more |
Token ID | 517 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
sorts | +0.055 |
hed | +0.053 |
Joey | +0.053 |
deeper | +0.053 |
unst | +0.050 |
Neg logit contributions | |
aids | -0.076 |
uren | -0.064 |
ggie | -0.062 |
agged | -0.060 |
blond | -0.060 |
Token | jokes |
Token ID | 14532 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
aids | +0.217 |
uren | +0.194 |
ggie | +0.185 |
wig | +0.178 |
cheeks | +0.174 |
Neg logit contributions | |
hed | -0.188 |
Joey | -0.183 |
sorts | -0.182 |
unst | -0.171 |
deeper | -0.170 |
Token | . |
Token ID | 13 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
aids | +0.902 |
song | +0.794 |
jokes | +0.793 |
hair | +0.782 |
ggie | +0.779 |
Neg logit contributions | |
arp | -0.562 |
unst | -0.549 |
Joey | -0.546 |
sorts | -0.543 |
aved | -0.531 |
Token | And |
Token ID | 843 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
aids | +0.073 |
ggie | +0.071 |
wig | +0.068 |
poems | +0.068 |
haircut | +0.067 |
Neg logit contributions | |
Joey | -0.046 |
arp | -0.043 |
Mill | -0.042 |
extingu | -0.042 |
unst | -0.042 |
Token | no |
Token ID | 645 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
Joey | +0.093 |
unst | +0.091 |
sorts | +0.088 |
Mill | +0.088 |
hed | +0.085 |
Neg logit contributions | |
aids | -0.145 |
ggie | -0.124 |
wig | -0.124 |
song | -0.122 |
poems | -0.121 |
Token | more |
Token ID | 517 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
sorts | +0.056 |
deeper | +0.054 |
hed | +0.053 |
Joey | +0.052 |
unst | +0.051 |
Neg logit contributions | |
aids | -0.076 |
uren | -0.067 |
ggie | -0.064 |
Dancing | -0.061 |
blond | -0.061 |
Token | slides |
Token ID | 19392 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
aids | +0.189 |
uren | +0.171 |
ggie | +0.166 |
wig | +0.160 |
blond | +0.153 |
Neg logit contributions | |
Joey | -0.201 |
hed | -0.199 |
sorts | -0.198 |
unst | -0.187 |
deeper | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
aids | +0.134 |
ggie | +0.119 |
uren | +0.117 |
blond | +0.115 |
wig | +0.114 |
Neg logit contributions | |
Joey | -0.076 |
sorts | -0.073 |
Mill | -0.072 |
hed | -0.070 |
arp | -0.070 |
Token | They |
Token ID | 1119 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
aids | +0.080 |
ggie | +0.075 |
wig | +0.074 |
song | +0.072 |
poems | +0.070 |
Neg logit contributions | |
Joey | -0.039 |
Mill | -0.038 |
hed | -0.036 |
sorts | -0.035 |
arp | -0.034 |
Token | do |
Token ID | 466 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
aids | +0.001 |
jokes | +0.001 |
hair | +0.001 |
song | +0.001 |
wig | +0.001 |
Neg logit contributions | |
arp | -0.001 |
Joey | -0.001 |
Mill | -0.001 |
unst | -0.001 |
rolley | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
aids | +0.197 |
blond | +0.194 |
cheeks | +0.188 |
blonde | +0.181 |
wig | +0.175 |
Neg logit contributions | |
sorts | -0.183 |
unst | -0.179 |
ourselves | -0.177 |
if | -0.171 |
'll | -0.171 |
Token | need |
Token ID | 761 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
aids | +0.262 |
poems | +0.233 |
ggie | +0.232 |
uren | +0.228 |
wig | +0.223 |
Neg logit contributions | |
Joey | -0.150 |
sorts | -0.144 |
aved | -0.143 |
unst | -0.140 |
Mill | -0.136 |
Token | jokes |
Token ID | 14532 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
Joey | +0.168 |
unst | +0.163 |
sorts | +0.163 |
Mill | +0.162 |
arp | +0.158 |
Neg logit contributions | |
aids | -0.211 |
ggie | -0.179 |
uren | -0.178 |
song | -0.178 |
wig | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
aids | +0.862 |
uren | +0.737 |
wig | +0.728 |
cheeks | +0.724 |
ggie | +0.723 |
Neg logit contributions | |
unst | -0.589 |
sorts | -0.560 |
arp | -0.560 |
aved | -0.560 |
Joey | -0.557 |
Token | They |
Token ID | 1119 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
aids | +0.082 |
wig | +0.077 |
ggie | +0.077 |
song | +0.075 |
poems | +0.073 |
Neg logit contributions | |
Joey | -0.039 |
Mill | -0.037 |
hed | -0.037 |
arp | -0.035 |
sorts | -0.035 |
Token | need |
Token ID | 761 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
aids | +0.005 |
song | +0.004 |
jokes | +0.004 |
ggie | +0.004 |
hair | +0.004 |
Neg logit contributions | |
arp | -0.003 |
unst | -0.003 |
Joey | -0.003 |
sorts | -0.003 |
aved | -0.003 |
Token | hugs |
Token ID | 40657 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Joey | +0.166 |
sorts | +0.164 |
unst | +0.164 |
arp | +0.163 |
Mill | +0.160 |
Neg logit contributions | |
aids | -0.203 |
ggie | -0.173 |
wig | -0.171 |
song | -0.171 |
uren | -0.170 |
Token | . |
Token ID | 13 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
aids | +0.032 |
ggie | +0.028 |
wig | +0.027 |
uren | +0.027 |
blond | +0.027 |
Neg logit contributions | |
arp | -0.022 |
unst | -0.022 |
Joey | -0.022 |
sorts | -0.021 |
Mill | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
arp | +0.432 |
sorts | +0.423 |
unst | +0.413 |
Joey | +0.411 |
aved | +0.405 |
Neg logit contributions | |
aids | -0.501 |
jokes | -0.434 |
wig | -0.423 |
song | -0.422 |
poems | -0.421 |
Token | Every |
Token ID | 3887 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
aids | +0.025 |
jokes | +0.021 |
song | +0.021 |
wig | +0.021 |
ggie | +0.021 |
Neg logit contributions | |
arp | -0.025 |
sorts | -0.024 |
Joey | -0.024 |
unst | -0.024 |
Mill | -0.024 |
Token | day |
Token ID | 1110 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
aids | +0.161 |
wig | +0.143 |
cheeks | +0.142 |
jokes | +0.142 |
hair | +0.140 |
Neg logit contributions | |
sorts | -0.118 |
arp | -0.113 |
Joey | -0.112 |
Mill | -0.108 |
aved | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
aids | +0.128 |
jokes | +0.110 |
song | +0.109 |
poems | +0.108 |
wig | +0.108 |
Neg logit contributions | |
Joey | -0.097 |
Mill | -0.096 |
arp | -0.096 |
sorts | -0.096 |
unst | -0.095 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
arp | +0.004 |
unst | +0.004 |
Joey | +0.004 |
sorts | +0.004 |
aved | +0.004 |
Neg logit contributions | |
aids | -0.004 |
song | -0.003 |
jokes | -0.003 |
hair | -0.003 |
ggie | -0.003 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
arp | +0.170 |
Mill | +0.166 |
sorts | +0.163 |
Joey | +0.163 |
aved | +0.162 |
Neg logit contributions | |
aids | -0.072 |
jokes | -0.057 |
wig | -0.054 |
poems | -0.052 |
hair | -0.049 |
Token | would |
Token ID | 561 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
aids | +0.705 |
hair | +0.631 |
song | +0.615 |
jokes | +0.604 |
ggie | +0.588 |
Neg logit contributions | |
arp | -0.727 |
unst | -0.720 |
Joey | -0.718 |
sorts | -0.703 |
hed | -0.703 |
Token | go |
Token ID | 467 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
arp | +0.060 |
unst | +0.058 |
Joey | +0.057 |
aved | +0.056 |
ucer | +0.056 |
Neg logit contributions | |
aids | -0.054 |
song | -0.047 |
jokes | -0.046 |
hair | -0.045 |
ggie | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
hair | +0.026 |
song | +0.026 |
aids | +0.025 |
wig | +0.023 |
songs | +0.023 |
Neg logit contributions | |
arp | -0.043 |
Joey | -0.041 |
rolley | -0.040 |
sorts | -0.040 |
extingu | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
hair | +0.056 |
aids | +0.053 |
haircut | +0.053 |
song | +0.053 |
yoga | +0.052 |
Neg logit contributions | |
arp | -0.114 |
aved | -0.110 |
ucer | -0.108 |
pling | -0.104 |
rol | -0.103 |
Token | mill |
Token ID | 3939 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
Joey | +0.012 |
aved | +0.011 |
Mill | +0.011 |
aback | +0.011 |
Suz | +0.011 |
Neg logit contributions | |
aids | -0.017 |
song | -0.016 |
hair | -0.016 |
jokes | -0.015 |
clown | -0.015 |
Token | pictures |
Token ID | 5986 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
arp | +0.024 |
unst | +0.023 |
aved | +0.023 |
Joey | +0.023 |
extingu | +0.023 |
Neg logit contributions | |
aids | -0.027 |
jokes | -0.024 |
song | -0.024 |
poems | -0.023 |
hair | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
aids | +0.269 |
song | +0.235 |
jokes | +0.234 |
hair | +0.229 |
poems | +0.228 |
Neg logit contributions | |
arp | -0.251 |
unst | -0.246 |
Joey | -0.242 |
aved | -0.240 |
sorts | -0.236 |
Token | words |
Token ID | 2456 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
arp | +0.026 |
unst | +0.025 |
Joey | +0.025 |
aved | +0.025 |
sorts | +0.024 |
Neg logit contributions | |
aids | -0.026 |
jokes | -0.023 |
song | -0.023 |
hair | -0.022 |
poems | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
aids | +0.330 |
song | +0.287 |
jokes | +0.287 |
hair | +0.282 |
wig | +0.282 |
Neg logit contributions | |
arp | -0.248 |
unst | -0.243 |
Joey | -0.242 |
sorts | -0.241 |
aved | -0.236 |
Token | W |
Token ID | 370 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
arp | +0.001 |
unst | +0.001 |
sorts | +0.001 |
Joey | +0.001 |
aved | +0.001 |
Neg logit contributions | |
aids | -0.001 |
jokes | -0.001 |
song | -0.001 |
hair | -0.001 |
Dancing | -0.001 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
Joey | +0.127 |
unst | +0.127 |
arp | +0.126 |
sorts | +0.126 |
Mill | +0.125 |
Neg logit contributions | |
aids | -0.132 |
jokes | -0.112 |
ggie | -0.110 |
hair | -0.110 |
song | -0.109 |
Token | try |
Token ID | 1949 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
aids | +0.888 |
jokes | +0.788 |
song | +0.787 |
hair | +0.786 |
wig | +0.761 |
Neg logit contributions | |
arp | -0.571 |
unst | -0.555 |
Joey | -0.540 |
sorts | -0.529 |
hed | -0.521 |
Token | me |
Token ID | 502 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
aids | +0.111 |
wig | +0.096 |
ggie | +0.095 |
cheeks | +0.095 |
song | +0.095 |
Neg logit contributions | |
Joey | -0.083 |
sorts | -0.083 |
arp | -0.082 |
unst | -0.082 |
Mill | -0.081 |
Token | out |
Token ID | 503 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
aids | +0.147 |
song | +0.128 |
jokes | +0.128 |
hair | +0.127 |
ggie | +0.125 |
Neg logit contributions | |
arp | -0.118 |
unst | -0.115 |
Joey | -0.114 |
sorts | -0.114 |
aved | -0.112 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
arp | +0.222 |
unst | +0.218 |
Joey | +0.216 |
sorts | +0.215 |
aved | +0.211 |
Neg logit contributions | |
aids | -0.329 |
song | -0.288 |
jokes | -0.287 |
hair | -0.283 |
ggie | -0.282 |
Token | Mike |
Token ID | 4995 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
aids | +0.187 |
song | +0.163 |
jokes | +0.161 |
poems | +0.160 |
wig | +0.158 |
Neg logit contributions | |
Joey | -0.153 |
arp | -0.152 |
sorts | -0.150 |
unst | -0.149 |
Mill | -0.148 |
Token | together |
Token ID | 1978 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
aids | +0.161 |
jokes | +0.145 |
song | +0.145 |
hair | +0.142 |
ggie | +0.141 |
Neg logit contributions | |
arp | -0.115 |
unst | -0.111 |
Joey | -0.111 |
sorts | -0.110 |
aved | -0.108 |
Token | one |
Token ID | 530 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
sorts | +0.168 |
Joey | +0.165 |
unst | +0.163 |
arp | +0.160 |
aved | +0.159 |
Neg logit contributions | |
aids | -0.252 |
wig | -0.213 |
cheeks | -0.210 |
jokes | -0.210 |
song | -0.209 |
Token | day |
Token ID | 1110 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
aids | +0.265 |
cheeks | +0.229 |
jokes | +0.222 |
blond | +0.220 |
wig | +0.220 |
Neg logit contributions | |
sorts | -0.195 |
arp | -0.187 |
unst | -0.179 |
Joey | -0.177 |
deeper | -0.168 |
Token | when |
Token ID | 618 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
aids | +0.116 |
song | +0.099 |
jokes | +0.098 |
wig | +0.097 |
ggie | +0.097 |
Neg logit contributions | |
arp | -0.101 |
Joey | -0.100 |
unst | -0.100 |
sorts | -0.099 |
Mill | -0.097 |
Token | Bre |
Token ID | 3719 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
aids | +0.053 |
song | +0.045 |
cheeks | +0.043 |
jokes | +0.043 |
wig | +0.043 |
Neg logit contributions | |
Joey | -0.034 |
Mill | -0.032 |
sorts | -0.031 |
arp | -0.031 |
Suz | -0.030 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
arp | +0.073 |
Joey | +0.072 |
sorts | +0.071 |
aved | +0.070 |
Mill | +0.070 |
Neg logit contributions | |
aids | -0.047 |
song | -0.038 |
jokes | -0.038 |
hair | -0.038 |
wig | -0.037 |
Token | said |
Token ID | 531 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
aids | +0.637 |
hair | +0.576 |
jokes | +0.543 |
cheeks | +0.533 |
wig | +0.524 |
Neg logit contributions | |
arp | -0.802 |
sorts | -0.763 |
unst | -0.762 |
hed | -0.755 |
extingu | -0.740 |
Token | , |
Token ID | 11 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Joey | +0.012 |
Mill | +0.011 |
unst | +0.010 |
Bobby | +0.010 |
Suz | +0.010 |
Neg logit contributions | |
aids | -0.016 |
song | -0.014 |
wig | -0.014 |
cheeks | -0.014 |
poems | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
Joey | +0.025 |
Mill | +0.024 |
Bobby | +0.023 |
unst | +0.023 |
Suz | +0.022 |
Neg logit contributions | |
aids | -0.022 |
ggie | -0.018 |
song | -0.018 |
wig | -0.018 |
hair | -0.018 |
Token | Let |
Token ID | 5756 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
aids | +0.042 |
jokes | +0.037 |
cheeks | +0.036 |
song | +0.036 |
hair | +0.036 |
Neg logit contributions | |
arp | -0.024 |
sorts | -0.023 |
Joey | -0.023 |
aved | -0.023 |
unst | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
Joey | +0.208 |
unst | +0.206 |
arp | +0.204 |
Mill | +0.202 |
sorts | +0.201 |
Neg logit contributions | |
aids | -0.163 |
wig | -0.138 |
cheeks | -0.132 |
Dancing | -0.131 |
song | -0.131 |
Token | a |
Token ID | 257 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
aids | +0.001 |
ggie | +0.001 |
song | +0.001 |
hair | +0.001 |
jokes | +0.001 |
Neg logit contributions | |
arp | -0.001 |
unst | -0.001 |
sorts | -0.001 |
aved | -0.001 |
Joey | -0.001 |
Token | little |
Token ID | 1310 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
arp | +0.012 |
Joey | +0.012 |
unst | +0.012 |
Mill | +0.012 |
scaven | +0.011 |
Neg logit contributions | |
aids | -0.014 |
jokes | -0.011 |
poems | -0.011 |
cheeks | -0.011 |
hair | -0.011 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
aids | +0.080 |
song | +0.074 |
hair | +0.072 |
wig | +0.071 |
jokes | +0.070 |
Neg logit contributions | |
unst | -0.097 |
aved | -0.093 |
arp | -0.093 |
sorts | -0.093 |
neath | -0.091 |
Token | named |
Token ID | 3706 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
arp | +0.017 |
unst | +0.017 |
Joey | +0.017 |
sorts | +0.016 |
aved | +0.016 |
Neg logit contributions | |
aids | -0.012 |
song | -0.010 |
hair | -0.010 |
jokes | -0.009 |
ggie | -0.009 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
aids | +0.090 |
hair | +0.074 |
song | +0.074 |
jokes | +0.073 |
ggie | +0.071 |
Neg logit contributions | |
arp | -0.122 |
unst | -0.119 |
sorts | -0.118 |
Joey | -0.117 |
aved | -0.116 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
arp | +0.116 |
Joey | +0.114 |
sorts | +0.113 |
Mill | +0.113 |
aved | +0.112 |
Neg logit contributions | |
aids | -0.134 |
jokes | -0.117 |
song | -0.115 |
poems | -0.115 |
wig | -0.113 |
Token | was |
Token ID | 373 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
aids | +0.656 |
hair | +0.616 |
song | +0.567 |
cheeks | +0.560 |
ggie | +0.555 |
Neg logit contributions | |
arp | -0.763 |
hed | -0.729 |
sorts | -0.729 |
Joey | -0.727 |
unst | -0.726 |
Token | walking |
Token ID | 6155 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
unst | +0.012 |
Joey | +0.012 |
Mill | +0.012 |
sorts | +0.012 |
aved | +0.011 |
Neg logit contributions | |
aids | -0.013 |
jokes | -0.011 |
song | -0.011 |
wig | -0.011 |
poems | -0.011 |
Token | through |
Token ID | 832 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
aids | +0.224 |
song | +0.195 |
jokes | +0.195 |
hair | +0.192 |
ggie | +0.192 |
Neg logit contributions | |
arp | -0.156 |
unst | -0.153 |
Joey | -0.152 |
sorts | -0.152 |
aved | -0.148 |
Token | a |
Token ID | 257 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
arp | +0.185 |
unst | +0.182 |
aved | +0.177 |
Joey | +0.177 |
sorts | +0.174 |
Neg logit contributions | |
aids | -0.208 |
song | -0.182 |
hair | -0.182 |
jokes | -0.181 |
poems | -0.176 |
Token | field |
Token ID | 2214 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
unst | +0.010 |
arp | +0.010 |
Joey | +0.010 |
sorts | +0.010 |
aved | +0.010 |
Neg logit contributions | |
aids | -0.013 |
song | -0.011 |
hair | -0.011 |
jokes | -0.011 |
ggie | -0.011 |
Token | were |
Token ID | 547 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
arp | +0.016 |
unst | +0.016 |
extingu | +0.015 |
wood | +0.015 |
aved | +0.015 |
Neg logit contributions | |
aids | -0.011 |
ggie | -0.010 |
hair | -0.009 |
Dancing | -0.009 |
jokes | -0.009 |
Token | two |
Token ID | 734 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
arp | +0.264 |
unst | +0.259 |
sorts | +0.256 |
Joey | +0.254 |
aved | +0.252 |
Neg logit contributions | |
aids | -0.275 |
jokes | -0.237 |
song | -0.237 |
hair | -0.234 |
ggie | -0.231 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
arp | +0.014 |
Joey | +0.014 |
sorts | +0.014 |
unst | +0.014 |
Mill | +0.013 |
Neg logit contributions | |
aids | -0.014 |
Dancing | -0.011 |
song | -0.011 |
wig | -0.011 |
ggie | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
aids | +0.152 |
song | +0.129 |
jokes | +0.128 |
wig | +0.127 |
poems | +0.126 |
Neg logit contributions | |
Joey | -0.139 |
arp | -0.138 |
sorts | -0.135 |
Mill | -0.134 |
unst | -0.134 |
Token | Bre |
Token ID | 3719 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
arp | +0.015 |
unst | +0.014 |
sorts | +0.014 |
aved | +0.014 |
Joey | +0.014 |
Neg logit contributions | |
aids | -0.016 |
song | -0.014 |
jokes | -0.014 |
hair | -0.013 |
wig | -0.013 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
arp | +0.066 |
unst | +0.065 |
Joey | +0.064 |
sorts | +0.064 |
aved | +0.063 |
Neg logit contributions | |
aids | -0.049 |
song | -0.041 |
jokes | -0.041 |
ggie | -0.040 |
hair | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
aids | +0.684 |
song | +0.594 |
hair | +0.590 |
jokes | +0.582 |
ggie | +0.576 |
Neg logit contributions | |
arp | -0.756 |
unst | -0.738 |
sorts | -0.734 |
Joey | -0.730 |
aved | -0.719 |
Token | Mason |
Token ID | 14737 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Joey | +0.011 |
arp | +0.011 |
unst | +0.011 |
sorts | +0.011 |
Mill | +0.011 |
Neg logit contributions | |
aids | -0.017 |
song | -0.015 |
jokes | -0.015 |
hair | -0.015 |
wig | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
arp | +0.070 |
unst | +0.069 |
Joey | +0.069 |
sorts | +0.068 |
aved | +0.067 |
Neg logit contributions | |
aids | -0.074 |
song | -0.063 |
jokes | -0.062 |
wig | -0.061 |
hair | -0.061 |
Token | They |
Token ID | 1119 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
aids | +0.002 |
song | +0.002 |
jokes | +0.002 |
ggie | +0.002 |
wig | +0.002 |
Neg logit contributions | |
arp | -0.002 |
Joey | -0.002 |
sorts | -0.002 |
unst | -0.002 |
aved | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
arp | +0.060 |
unst | +0.059 |
extingu | +0.057 |
rolley | +0.056 |
ucer | +0.055 |
Neg logit contributions | |
aids | -0.042 |
jokes | -0.039 |
hair | -0.038 |
song | -0.037 |
Dancing | -0.035 |
Token | you |
Token ID | 345 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
arp | +0.195 |
unst | +0.191 |
Joey | +0.189 |
sorts | +0.189 |
aved | +0.185 |
Neg logit contributions | |
aids | -0.251 |
song | -0.218 |
jokes | -0.218 |
hair | -0.214 |
ggie | -0.213 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
arp | +0.034 |
unst | +0.033 |
Joey | +0.033 |
sorts | +0.033 |
aved | +0.032 |
Neg logit contributions | |
aids | -0.045 |
song | -0.039 |
jokes | -0.039 |
hair | -0.038 |
wig | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
aids | +0.238 |
poems | +0.213 |
wig | +0.208 |
jokes | +0.207 |
song | +0.205 |
Neg logit contributions | |
Mill | -0.139 |
Joey | -0.137 |
sorts | -0.135 |
arp | -0.130 |
Suz | -0.130 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
arp | +0.007 |
unst | +0.007 |
Joey | +0.007 |
sorts | +0.007 |
aved | +0.007 |
Neg logit contributions | |
aids | -0.008 |
song | -0.007 |
jokes | -0.007 |
hair | -0.007 |
ggie | -0.007 |
Token | Jo |
Token ID | 9908 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
arp | +0.008 |
sorts | +0.008 |
Joey | +0.008 |
unst | +0.008 |
Mill | +0.007 |
Neg logit contributions | |
aids | -0.009 |
jokes | -0.007 |
song | -0.007 |
hair | -0.007 |
poems | -0.007 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
aids | +0.052 |
poems | +0.046 |
jokes | +0.045 |
wig | +0.045 |
Dancing | +0.045 |
Neg logit contributions | |
arp | -0.079 |
Mill | -0.078 |
Joey | -0.078 |
aved | -0.075 |
unst | -0.075 |
Token | was |
Token ID | 373 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
aids | +0.720 |
jokes | +0.616 |
hair | +0.612 |
song | +0.611 |
ggie | +0.601 |
Neg logit contributions | |
arp | -0.742 |
unst | -0.718 |
sorts | -0.709 |
Joey | -0.699 |
aved | -0.693 |
Token | so |
Token ID | 523 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Joey | +0.021 |
unst | +0.021 |
Mill | +0.020 |
sorts | +0.020 |
aback | +0.019 |
Neg logit contributions | |
aids | -0.029 |
wig | -0.029 |
song | -0.028 |
poems | -0.028 |
uren | -0.028 |
Token | surprised |
Token ID | 6655 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
aids | +0.074 |
song | +0.062 |
jokes | +0.062 |
hair | +0.060 |
wig | +0.060 |
Neg logit contributions | |
arp | -0.090 |
unst | -0.089 |
Joey | -0.088 |
sorts | -0.088 |
aved | -0.087 |
Token | that |
Token ID | 326 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
aids | +0.022 |
wig | +0.018 |
ggie | +0.018 |
hair | +0.018 |
song | +0.018 |
Neg logit contributions | |
Joey | -0.016 |
Mill | -0.016 |
sorts | -0.015 |
arp | -0.015 |
unst | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
aids | +0.129 |
jokes | +0.109 |
song | +0.108 |
wig | +0.108 |
ggie | +0.107 |
Neg logit contributions | |
Joey | -0.132 |
arp | -0.132 |
sorts | -0.131 |
unst | -0.131 |
Mill | -0.129 |
Token | a |
Token ID | 257 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
arp | +0.024 |
unst | +0.023 |
sorts | +0.023 |
Joey | +0.023 |
aved | +0.023 |
Neg logit contributions | |
aids | -0.024 |
jokes | -0.021 |
song | -0.021 |
hair | -0.020 |
ggie | -0.020 |
Token | little |
Token ID | 1310 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
arp | +0.024 |
Joey | +0.024 |
unst | +0.023 |
Mill | +0.023 |
sorts | +0.023 |
Neg logit contributions | |
aids | -0.025 |
jokes | -0.020 |
poems | -0.020 |
cheeks | -0.020 |
ggie | -0.019 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
aids | +0.066 |
song | +0.063 |
hair | +0.060 |
jokes | +0.059 |
wig | +0.059 |
Neg logit contributions | |
unst | -0.083 |
aved | -0.081 |
arp | -0.080 |
sorts | -0.079 |
neath | -0.079 |
Token | called |
Token ID | 1444 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
arp | +0.023 |
sorts | +0.023 |
Mill | +0.023 |
Joey | +0.022 |
Suz | +0.022 |
Neg logit contributions | |
aids | -0.031 |
jokes | -0.027 |
poems | -0.026 |
cheeks | -0.025 |
uren | -0.025 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
arp | +0.063 |
unst | +0.062 |
sorts | +0.061 |
Joey | +0.061 |
aved | +0.060 |
Neg logit contributions | |
aids | -0.056 |
song | -0.047 |
jokes | -0.047 |
hair | -0.047 |
ggie | -0.046 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
arp | +0.133 |
Mill | +0.133 |
Joey | +0.129 |
sorts | +0.129 |
Suz | +0.125 |
Neg logit contributions | |
aids | -0.129 |
jokes | -0.111 |
poems | -0.107 |
wig | -0.104 |
hair | -0.103 |
Token | who |
Token ID | 508 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
aids | +0.761 |
jokes | +0.647 |
song | +0.640 |
wig | +0.633 |
poems | +0.629 |
Neg logit contributions | |
arp | -0.703 |
unst | -0.690 |
Joey | -0.687 |
sorts | -0.684 |
aved | -0.674 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
aids | +0.122 |
song | +0.103 |
jokes | +0.103 |
hair | +0.101 |
wig | +0.101 |
Neg logit contributions | |
arp | -0.125 |
unst | -0.123 |
sorts | -0.123 |
Joey | -0.123 |
aved | -0.121 |
Token | in |
Token ID | 287 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
arp | +0.128 |
Joey | +0.124 |
sorts | +0.124 |
unst | +0.123 |
Mill | +0.121 |
Neg logit contributions | |
aids | -0.122 |
song | -0.107 |
hair | -0.106 |
jokes | -0.105 |
ggie | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
aids | +0.108 |
song | +0.093 |
jokes | +0.092 |
hair | +0.091 |
ggie | +0.090 |
Neg logit contributions | |
arp | -0.097 |
unst | -0.095 |
Joey | -0.094 |
sorts | -0.094 |
aved | -0.093 |
Token | countryside |
Token ID | 25708 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
unst | +0.028 |
arp | +0.028 |
aved | +0.027 |
sorts | +0.027 |
Joey | +0.027 |
Neg logit contributions | |
aids | -0.039 |
song | -0.034 |
hair | -0.034 |
jokes | -0.034 |
Dancing | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
aids | +0.082 |
jokes | +0.074 |
song | +0.073 |
hair | +0.072 |
poems | +0.070 |
Neg logit contributions | |
arp | -0.089 |
aved | -0.085 |
unst | -0.082 |
ucer | -0.080 |
Joey | -0.080 |
Token | jungle |
Token ID | 20712 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Joey | +0.030 |
unst | +0.030 |
arp | +0.030 |
aved | +0.029 |
sorts | +0.029 |
Neg logit contributions | |
aids | -0.032 |
song | -0.029 |
jokes | -0.028 |
wig | -0.028 |
hair | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
aids | +0.133 |
song | +0.115 |
jokes | +0.114 |
hair | +0.112 |
ggie | +0.111 |
Neg logit contributions | |
arp | -0.130 |
unst | -0.128 |
Joey | -0.127 |
sorts | -0.125 |
aved | -0.124 |
Token | the |
Token ID | 262 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
unst | +0.013 |
Joey | +0.013 |
sorts | +0.012 |
arp | +0.012 |
Mill | +0.012 |
Neg logit contributions | |
aids | -0.015 |
ggie | -0.013 |
song | -0.013 |
jokes | -0.013 |
hair | -0.013 |
Token | sav |
Token ID | 6799 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
arp | +0.032 |
unst | +0.032 |
sorts | +0.032 |
Joey | +0.032 |
aved | +0.031 |
Neg logit contributions | |
aids | -0.028 |
jokes | -0.023 |
song | -0.023 |
ggie | -0.023 |
hair | -0.023 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
arp | +0.223 |
unst | +0.219 |
aved | +0.205 |
ucer | +0.202 |
rying | +0.201 |
Neg logit contributions | |
aids | -0.300 |
jokes | -0.268 |
song | -0.268 |
ggie | -0.255 |
Dancing | -0.252 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
aids | +0.726 |
song | +0.632 |
jokes | +0.627 |
hair | +0.625 |
wig | +0.610 |
Neg logit contributions | |
arp | -0.720 |
unst | -0.700 |
sorts | -0.697 |
Joey | -0.696 |
aved | -0.676 |
Token | the |
Token ID | 262 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
arp | +0.016 |
unst | +0.015 |
Joey | +0.015 |
sorts | +0.015 |
aved | +0.015 |
Neg logit contributions | |
aids | -0.017 |
song | -0.015 |
jokes | -0.015 |
hair | -0.015 |
wig | -0.015 |
Token | desert |
Token ID | 10326 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
arp | +0.032 |
unst | +0.032 |
sorts | +0.032 |
Joey | +0.031 |
hed | +0.031 |
Neg logit contributions | |
aids | -0.031 |
ggie | -0.026 |
jokes | -0.026 |
song | -0.025 |
hair | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
arp | +0.026 |
Joey | +0.025 |
unst | +0.025 |
sorts | +0.025 |
Mill | +0.025 |
Neg logit contributions | |
aids | -0.033 |
song | -0.028 |
jokes | -0.028 |
wig | -0.028 |
Dancing | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
arp | +0.010 |
unst | +0.010 |
Joey | +0.010 |
sorts | +0.010 |
aved | +0.009 |
Neg logit contributions | |
aids | -0.013 |
song | -0.011 |
jokes | -0.011 |
hair | -0.011 |
wig | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
aids | +0.081 |
song | +0.070 |
wig | +0.070 |
jokes | +0.069 |
ggie | +0.069 |
Neg logit contributions | |
arp | -0.058 |
sorts | -0.057 |
unst | -0.057 |
Joey | -0.057 |
Mill | -0.055 |
Token | dolls |
Token ID | 36062 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
arp | +0.040 |
sorts | +0.040 |
Joey | +0.040 |
unst | +0.040 |
hed | +0.038 |
Neg logit contributions | |
aids | -0.041 |
ggie | -0.034 |
hair | -0.033 |
wig | -0.033 |
Dancing | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
aids | +0.283 |
jokes | +0.240 |
ggie | +0.238 |
wig | +0.238 |
song | +0.238 |
Neg logit contributions | |
arp | -0.214 |
unst | -0.213 |
sorts | -0.212 |
aved | -0.207 |
Joey | -0.206 |
Token | They |
Token ID | 1119 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
aids | +0.055 |
wig | +0.052 |
ggie | +0.051 |
ggy | +0.048 |
song | +0.048 |
Neg logit contributions | |
Mill | -0.033 |
Joey | -0.032 |
hed | -0.032 |
sorts | -0.031 |
unst | -0.031 |
Token | told |
Token ID | 1297 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
arp | +0.015 |
unst | +0.015 |
sorts | +0.015 |
Joey | +0.014 |
aved | +0.014 |
Neg logit contributions | |
aids | -0.015 |
song | -0.013 |
jokes | -0.012 |
ggie | -0.012 |
hair | -0.012 |
Token | jokes |
Token ID | 14532 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
aids | +0.015 |
wig | +0.014 |
ggie | +0.014 |
uren | +0.013 |
Dancing | +0.013 |
Neg logit contributions | |
Joey | -0.012 |
Mill | -0.012 |
Bobby | -0.011 |
sorts | -0.011 |
hed | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
aids | +0.807 |
blond | +0.694 |
hair | +0.687 |
wig | +0.685 |
cheeks | +0.682 |
Neg logit contributions | |
Joey | -0.617 |
sorts | -0.616 |
arp | -0.590 |
Mill | -0.586 |
unst | -0.584 |
Token | stories |
Token ID | 3923 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
aids | +0.004 |
ggie | +0.004 |
uren | +0.004 |
Dancing | +0.004 |
agging | +0.004 |
Neg logit contributions | |
sorts | -0.005 |
Joey | -0.005 |
hed | -0.005 |
Mill | -0.005 |
unst | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
aids | +0.419 |
wig | +0.357 |
hair | +0.352 |
ggie | +0.350 |
cheeks | +0.349 |
Neg logit contributions | |
sorts | -0.350 |
unst | -0.346 |
arp | -0.344 |
aved | -0.339 |
Joey | -0.339 |
Token | They |
Token ID | 1119 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
aids | +0.058 |
ggie | +0.057 |
wig | +0.057 |
ggy | +0.054 |
haircut | +0.053 |
Neg logit contributions | |
Mill | -0.033 |
Joey | -0.033 |
hed | -0.030 |
Bobby | -0.030 |
neath | -0.029 |
Token | hugged |
Token ID | 41130 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
sorts | +0.013 |
arp | +0.013 |
Joey | +0.013 |
unst | +0.013 |
aved | +0.013 |
Neg logit contributions | |
aids | -0.015 |
song | -0.013 |
ggie | -0.012 |
hair | -0.012 |
jokes | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
arp | +0.012 |
Joey | +0.012 |
sorts | +0.012 |
unst | +0.011 |
aved | +0.011 |
Neg logit contributions | |
aids | -0.014 |
jokes | -0.013 |
song | -0.012 |
wig | -0.012 |
hair | -0.012 |
Token | One |
Token ID | 3198 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
sorts | +0.014 |
arp | +0.014 |
Mill | +0.013 |
aved | +0.013 |
Joey | +0.013 |
Neg logit contributions | |
aids | -0.012 |
cheeks | -0.010 |
wig | -0.010 |
jokes | -0.010 |
poems | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
aids | +0.266 |
wig | +0.233 |
cheeks | +0.229 |
jokes | +0.228 |
poems | +0.225 |
Neg logit contributions | |
sorts | -0.183 |
Joey | -0.178 |
arp | -0.178 |
Mill | -0.170 |
unst | -0.167 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
aids | +0.117 |
jokes | +0.100 |
song | +0.100 |
wig | +0.098 |
poems | +0.098 |
Neg logit contributions | |
arp | -0.098 |
Joey | -0.097 |
unst | -0.096 |
sorts | -0.096 |
Mill | -0.095 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
arp | +0.011 |
unst | +0.011 |
Joey | +0.011 |
sorts | +0.011 |
aved | +0.011 |
Neg logit contributions | |
aids | -0.015 |
song | -0.013 |
jokes | -0.013 |
hair | -0.013 |
ggie | -0.013 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
arp | +0.178 |
Mill | +0.175 |
Joey | +0.172 |
aved | +0.171 |
sorts | +0.171 |
Neg logit contributions | |
aids | -0.079 |
jokes | -0.064 |
wig | -0.060 |
poems | -0.059 |
song | -0.055 |
Token | dared |
Token ID | 28765 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
aids | +0.632 |
hair | +0.580 |
song | +0.543 |
ggie | +0.528 |
cheeks | +0.524 |
Neg logit contributions | |
arp | -0.764 |
hed | -0.764 |
sorts | -0.749 |
Joey | -0.746 |
unst | -0.746 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Mill | +0.136 |
Joey | +0.133 |
unst | +0.125 |
Suz | +0.125 |
hed | +0.119 |
Neg logit contributions | |
aids | -0.174 |
wig | -0.153 |
ggie | -0.149 |
song | -0.144 |
Dancing | -0.144 |
Token | venture |
Token ID | 13189 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
aids | +0.079 |
song | +0.069 |
hair | +0.069 |
jokes | +0.069 |
ggie | +0.066 |
Neg logit contributions | |
arp | -0.083 |
unst | -0.080 |
aved | -0.078 |
sorts | -0.078 |
Joey | -0.078 |
Token | into |
Token ID | 656 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
arp | +0.105 |
sorts | +0.100 |
aved | +0.096 |
Joey | +0.095 |
Mill | +0.095 |
Neg logit contributions | |
aids | -0.132 |
hair | -0.125 |
jokes | -0.118 |
song | -0.116 |
poems | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
aids | +0.009 |
hair | +0.008 |
yoga | +0.008 |
poems | +0.007 |
song | +0.007 |
Neg logit contributions | |
arp | -0.013 |
aved | -0.012 |
ucer | -0.012 |
unst | -0.012 |
Joey | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
Joey | +0.003 |
Mill | +0.003 |
Bobby | +0.003 |
unst | +0.003 |
Suz | +0.003 |
Neg logit contributions | |
aids | -0.005 |
poems | -0.004 |
ggie | -0.004 |
wig | -0.004 |
hair | -0.004 |
Token | Yes |
Token ID | 5297 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
aids | +0.082 |
cheeks | +0.072 |
poems | +0.072 |
hair | +0.071 |
jokes | +0.071 |
Neg logit contributions | |
sorts | -0.028 |
arp | -0.027 |
Joey | -0.026 |
unst | -0.025 |
aved | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
Joey | +0.069 |
arp | +0.068 |
unst | +0.068 |
Mill | +0.066 |
sorts | +0.065 |
Neg logit contributions | |
aids | -0.096 |
song | -0.083 |
jokes | -0.083 |
poems | -0.082 |
hair | -0.081 |
Token | I |
Token ID | 314 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Joey | +0.002 |
Mill | +0.002 |
unst | +0.002 |
arp | +0.002 |
sorts | +0.002 |
Neg logit contributions | |
aids | -0.003 |
hair | -0.002 |
ggie | -0.002 |
poems | -0.002 |
wig | -0.002 |
Token | like |
Token ID | 588 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
aids | +0.076 |
song | +0.069 |
jokes | +0.068 |
ggie | +0.067 |
wig | +0.066 |
Neg logit contributions | |
arp | -0.079 |
Joey | -0.075 |
Mill | -0.075 |
hed | -0.075 |
rolley | -0.073 |
Token | jokes |
Token ID | 14532 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Joey | +0.036 |
sorts | +0.034 |
Mill | +0.032 |
Bobby | +0.032 |
hed | +0.031 |
Neg logit contributions | |
aids | -0.048 |
cheeks | -0.041 |
blond | -0.041 |
agged | -0.041 |
uren | -0.041 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
aids | +1.072 |
cheeks | +0.936 |
song | +0.935 |
hair | +0.934 |
wig | +0.933 |
Neg logit contributions | |
sorts | -0.365 |
arp | -0.364 |
Joey | -0.363 |
unst | -0.349 |
Mill | -0.334 |
Token | Sally |
Token ID | 25737 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Joey | +0.165 |
Mill | +0.161 |
unst | +0.154 |
sorts | +0.153 |
Suz | +0.152 |
Neg logit contributions | |
aids | -0.261 |
ggie | -0.237 |
wig | -0.227 |
poems | -0.224 |
jokes | -0.223 |
Token | told |
Token ID | 1297 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Joey | +0.173 |
sorts | +0.171 |
Mill | +0.165 |
'll | +0.161 |
Bobby | +0.157 |
Neg logit contributions | |
aids | -0.212 |
Dancing | -0.178 |
agging | -0.177 |
poems | -0.176 |
wig | -0.173 |
Token | a |
Token ID | 257 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
aids | +0.016 |
song | +0.014 |
wig | +0.014 |
poems | +0.013 |
Dancing | +0.013 |
Neg logit contributions | |
Joey | -0.013 |
Mill | -0.013 |
unst | -0.013 |
arp | -0.012 |
Suz | -0.012 |
Token | funny |
Token ID | 8258 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
sorts | +0.017 |
Joey | +0.016 |
Mill | +0.016 |
'll | +0.016 |
unst | +0.015 |
Neg logit contributions | |
aids | -0.013 |
hair | -0.011 |
agged | -0.011 |
poems | -0.011 |
agging | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
arp | +0.011 |
unst | +0.011 |
Joey | +0.011 |
sorts | +0.011 |
aved | +0.011 |
Neg logit contributions | |
aids | -0.013 |
song | -0.011 |
jokes | -0.011 |
hair | -0.011 |
wig | -0.011 |
Token | One |
Token ID | 3198 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
sorts | +0.014 |
arp | +0.014 |
aved | +0.013 |
Mill | +0.013 |
Joey | +0.013 |
Neg logit contributions | |
aids | -0.011 |
jokes | -0.009 |
wig | -0.009 |
cheeks | -0.009 |
poems | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
aids | +0.303 |
wig | +0.269 |
cheeks | +0.266 |
jokes | +0.259 |
hair | +0.257 |
Neg logit contributions | |
sorts | -0.172 |
Joey | -0.159 |
Mill | -0.150 |
arp | -0.143 |
Suz | -0.142 |
Token | , |
Token ID | 11 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
aids | +0.121 |
jokes | +0.104 |
song | +0.104 |
poems | +0.102 |
wig | +0.102 |
Neg logit contributions | |
Joey | -0.096 |
arp | -0.096 |
Mill | -0.095 |
sorts | -0.095 |
unst | -0.094 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
arp | +0.005 |
unst | +0.005 |
Joey | +0.005 |
sorts | +0.005 |
aved | +0.005 |
Neg logit contributions | |
aids | -0.007 |
song | -0.006 |
jokes | -0.006 |
hair | -0.006 |
ggie | -0.006 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
arp | +0.162 |
Mill | +0.160 |
Joey | +0.158 |
aved | +0.158 |
sorts | +0.157 |
Neg logit contributions | |
aids | -0.084 |
jokes | -0.070 |
poems | -0.066 |
wig | -0.065 |
song | -0.063 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
aids | +0.603 |
hair | +0.572 |
song | +0.508 |
cheeks | +0.505 |
jokes | +0.499 |
Neg logit contributions | |
arp | -0.799 |
extingu | -0.771 |
unst | -0.759 |
hed | -0.758 |
Joey | -0.748 |
Token | a |
Token ID | 257 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
arp | +0.029 |
Joey | +0.029 |
sorts | +0.029 |
unst | +0.028 |
Mill | +0.028 |
Neg logit contributions | |
aids | -0.036 |
song | -0.031 |
jokes | -0.030 |
wig | -0.030 |
ggie | -0.030 |
Token | giant |
Token ID | 6175 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
arp | +0.015 |
unst | +0.015 |
Joey | +0.015 |
sorts | +0.014 |
aved | +0.014 |
Neg logit contributions | |
aids | -0.015 |
song | -0.013 |
jokes | -0.013 |
hair | -0.013 |
wig | -0.013 |
Token | stone |
Token ID | 7815 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
aids | +0.025 |
jokes | +0.021 |
Dancing | +0.021 |
ggie | +0.021 |
song | +0.021 |
Neg logit contributions | |
arp | -0.017 |
sorts | -0.017 |
Joey | -0.017 |
unst | -0.017 |
hed | -0.016 |
Token | wall |
Token ID | 3355 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
arp | +0.180 |
sorts | +0.179 |
unst | +0.177 |
aved | +0.174 |
Joey | +0.172 |
Neg logit contributions | |
aids | -0.278 |
jokes | -0.239 |
uren | -0.235 |
Dancing | -0.232 |
cheeks | -0.230 |
Token | a |
Token ID | 257 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
arp | +0.020 |
unst | +0.020 |
sorts | +0.019 |
aved | +0.019 |
Joey | +0.019 |
Neg logit contributions | |
aids | -0.019 |
jokes | -0.017 |
hair | -0.016 |
song | -0.016 |
ggie | -0.016 |
Token | smart |
Token ID | 4451 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
arp | +0.019 |
Joey | +0.019 |
unst | +0.018 |
scaven | +0.018 |
sorts | +0.018 |
Neg logit contributions | |
aids | -0.021 |
jokes | -0.017 |
cheeks | -0.017 |
poems | -0.016 |
hair | -0.016 |
Token | princess |
Token ID | 21752 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
Joey | +0.010 |
arp | +0.010 |
Mill | +0.010 |
sorts | +0.010 |
extingu | +0.009 |
Neg logit contributions | |
aids | -0.010 |
jokes | -0.008 |
ggie | -0.008 |
poems | -0.008 |
wig | -0.008 |
Token | named |
Token ID | 3706 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
aids | +0.386 |
jokes | +0.330 |
cheeks | +0.323 |
Dancing | +0.317 |
wig | +0.314 |
Neg logit contributions | |
arp | -0.272 |
sorts | -0.270 |
Mill | -0.257 |
Joey | -0.253 |
aved | -0.251 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
aids | +0.092 |
song | +0.078 |
jokes | +0.077 |
ggie | +0.076 |
wig | +0.076 |
Neg logit contributions | |
Joey | -0.093 |
Mill | -0.093 |
arp | -0.091 |
sorts | -0.091 |
unst | -0.091 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
arp | +0.138 |
Mill | +0.138 |
Joey | +0.138 |
sorts | +0.136 |
aved | +0.133 |
Neg logit contributions | |
aids | -0.105 |
jokes | -0.089 |
poems | -0.085 |
song | -0.084 |
wig | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
aids | +0.740 |
jokes | +0.631 |
song | +0.629 |
wig | +0.615 |
hair | +0.614 |
Neg logit contributions | |
arp | -0.710 |
unst | -0.696 |
Joey | -0.694 |
sorts | -0.691 |
aved | -0.682 |
Token | She |
Token ID | 1375 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
aids | +0.012 |
Dancing | +0.010 |
song | +0.010 |
hair | +0.010 |
jokes | +0.010 |
Neg logit contributions | |
unst | -0.016 |
arp | -0.016 |
Joey | -0.015 |
aved | -0.015 |
extingu | -0.015 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
sorts | +0.035 |
aved | +0.034 |
arp | +0.034 |
Joey | +0.033 |
Mill | +0.033 |
Neg logit contributions | |
aids | -0.057 |
jokes | -0.049 |
song | -0.048 |
cheeks | -0.048 |
wig | -0.047 |
Token | in |
Token ID | 287 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
arp | +0.112 |
unst | +0.110 |
Joey | +0.109 |
sorts | +0.109 |
aved | +0.107 |
Neg logit contributions | |
aids | -0.124 |
song | -0.107 |
jokes | -0.106 |
hair | -0.105 |
ggie | -0.104 |
Token | a |
Token ID | 257 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
aids | +0.126 |
jokes | +0.109 |
song | +0.108 |
wig | +0.106 |
ggie | +0.106 |
Neg logit contributions | |
arp | -0.105 |
sorts | -0.104 |
Joey | -0.104 |
unst | -0.104 |
Mill | -0.101 |
Token | really |
Token ID | 1107 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
aids | +0.123 |
song | +0.108 |
jokes | +0.108 |
hair | +0.104 |
ggie | +0.103 |
Neg logit contributions | |
arp | -0.135 |
unst | -0.129 |
sorts | -0.128 |
aved | -0.128 |
Joey | -0.127 |
Token | special |
Token ID | 2041 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
aids | +0.002 |
song | +0.002 |
jokes | +0.002 |
hair | +0.002 |
ggie | +0.002 |
Neg logit contributions | |
arp | -0.002 |
unst | -0.002 |
Joey | -0.002 |
sorts | -0.002 |
aved | -0.002 |
Token | inside |
Token ID | 2641 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
arp | +0.028 |
unst | +0.028 |
Joey | +0.027 |
aved | +0.027 |
sorts | +0.026 |
Neg logit contributions | |
aids | -0.035 |
song | -0.031 |
jokes | -0.031 |
hair | -0.030 |
poems | -0.030 |
Token | ." |
Token ID | 526 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
aved | +0.320 |
arp | +0.318 |
unst | +0.316 |
extingu | +0.310 |
erek | +0.307 |
Neg logit contributions | |
aids | -0.308 |
hair | -0.267 |
song | -0.266 |
jokes | -0.266 |
poems | -0.261 |
Token | Jo |
Token ID | 5302 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
arp | +0.066 |
unst | +0.065 |
sorts | +0.064 |
Joey | +0.064 |
aved | +0.064 |
Neg logit contributions | |
aids | -0.072 |
song | -0.061 |
jokes | -0.061 |
hair | -0.060 |
wig | -0.060 |
Token | anna |
Token ID | 7697 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Joey | +0.121 |
Mill | +0.118 |
sorts | +0.116 |
arp | +0.110 |
Bobby | +0.110 |
Neg logit contributions | |
aids | -0.142 |
poems | -0.125 |
wig | -0.124 |
jokes | -0.123 |
Dancing | -0.121 |
Token | was |
Token ID | 373 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
aids | +0.672 |
hair | +0.598 |
jokes | +0.586 |
cheeks | +0.582 |
song | +0.582 |
Neg logit contributions | |
arp | -0.763 |
unst | -0.730 |
sorts | -0.715 |
hed | -0.708 |
aved | -0.700 |
Token | very |
Token ID | 845 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
unst | +0.034 |
Joey | +0.034 |
sorts | +0.034 |
Mill | +0.033 |
aved | +0.032 |
Neg logit contributions | |
aids | -0.041 |
song | -0.035 |
wig | -0.035 |
jokes | -0.035 |
poems | -0.035 |
Token | curious |
Token ID | 11040 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
aids | +0.032 |
jokes | +0.027 |
song | +0.027 |
hair | +0.027 |
ggie | +0.026 |
Neg logit contributions | |
arp | -0.051 |
unst | -0.048 |
aved | -0.048 |
sorts | -0.047 |
Joey | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
aids | +0.000 |
wig | +0.000 |
ggie | +0.000 |
Dancing | +0.000 |
uren | +0.000 |
Neg logit contributions | |
Joey | -0.000 |
sorts | -0.000 |
Mill | -0.000 |
unst | -0.000 |
arp | -0.000 |
Token | couldn |
Token ID | 3521 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Joey | +0.026 |
sorts | +0.026 |
unst | +0.026 |
Mill | +0.026 |
arp | +0.025 |
Neg logit contributions | |
aids | -0.032 |
wig | -0.028 |
ggie | -0.027 |
jokes | -0.027 |
song | -0.027 |
Token | 's |
Token ID | 338 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
unst | +0.020 |
arp | +0.020 |
Joey | +0.020 |
aved | +0.020 |
scaven | +0.020 |
Neg logit contributions | |
aids | -0.026 |
Dancing | -0.022 |
song | -0.022 |
wig | -0.022 |
jokes | -0.022 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
aids | +0.207 |
uren | +0.171 |
ggie | +0.165 |
poems | +0.163 |
Dancing | +0.162 |
Neg logit contributions | |
arp | -0.205 |
unst | -0.205 |
scaven | -0.198 |
shed | -0.197 |
Joey | -0.193 |
Token | my |
Token ID | 1820 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
aids | +0.129 |
song | +0.111 |
jokes | +0.111 |
ggie | +0.109 |
hair | +0.109 |
Neg logit contributions | |
arp | -0.108 |
unst | -0.107 |
Joey | -0.106 |
sorts | -0.105 |
aved | -0.103 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
arp | +0.065 |
sorts | +0.063 |
unst | +0.063 |
Joey | +0.063 |
aved | +0.062 |
Neg logit contributions | |
aids | -0.056 |
jokes | -0.048 |
song | -0.047 |
hair | -0.047 |
wig | -0.047 |
Token | her |
Token ID | 607 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
aids | +0.076 |
jokes | +0.064 |
song | +0.064 |
hair | +0.063 |
poems | +0.062 |
Neg logit contributions | |
arp | -0.086 |
unst | -0.084 |
sorts | -0.084 |
Joey | -0.084 |
aved | -0.083 |
Token | if |
Token ID | 611 |
Feature activation | +7.86e+00 |
Pos logit contributions | |
aids | +0.058 |
song | +0.050 |
jokes | +0.050 |
wig | +0.049 |
ggie | +0.049 |
Neg logit contributions | |
arp | -0.043 |
unst | -0.042 |
Joey | -0.042 |
sorts | -0.042 |
Mill | -0.041 |
Token | she |
Token ID | 673 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
Joey | +0.547 |
arp | +0.547 |
unst | +0.545 |
sorts | +0.535 |
Mill | +0.534 |
Neg logit contributions | |
aids | -0.524 |
song | -0.442 |
jokes | -0.437 |
wig | -0.430 |
ggie | -0.429 |
Token | wanted |
Token ID | 2227 |
Feature activation | -8.32e-02 |
Pos logit contributions | |
aids | +0.065 |
song | +0.056 |
jokes | +0.055 |
wig | +0.055 |
hair | +0.054 |
Neg logit contributions | |
arp | -0.053 |
unst | -0.053 |
Joey | -0.053 |
sorts | -0.052 |
aved | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
aids | +0.006 |
song | +0.005 |
jokes | +0.005 |
hair | +0.005 |
ggie | +0.005 |
Neg logit contributions | |
arp | -0.006 |
unst | -0.006 |
Joey | -0.006 |
sorts | -0.006 |
aved | -0.006 |
Token | help |
Token ID | 1037 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
aids | +0.079 |
hair | +0.070 |
song | +0.070 |
jokes | +0.070 |
ggie | +0.068 |
Neg logit contributions | |
arp | -0.072 |
sorts | -0.069 |
Joey | -0.069 |
unst | -0.068 |
aved | -0.068 |
Token | clean |
Token ID | 3424 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
arp | +0.226 |
unst | +0.224 |
Joey | +0.223 |
sorts | +0.220 |
Mill | +0.217 |
Neg logit contributions | |
aids | -0.234 |
song | -0.199 |
jokes | -0.198 |
wig | -0.195 |
ggie | -0.194 |
Token | scream |
Token ID | 8196 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
arp | +0.016 |
unst | +0.015 |
Joey | +0.015 |
sorts | +0.015 |
aved | +0.015 |
Neg logit contributions | |
aids | -0.011 |
song | -0.009 |
jokes | -0.009 |
hair | -0.009 |
wig | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
arp | +0.005 |
unst | +0.005 |
Joey | +0.005 |
sorts | +0.005 |
aved | +0.005 |
Neg logit contributions | |
aids | -0.006 |
wig | -0.005 |
ggie | -0.005 |
jokes | -0.005 |
song | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
aids | +0.024 |
song | +0.021 |
wig | +0.021 |
jokes | +0.021 |
poems | +0.021 |
Neg logit contributions | |
Joey | -0.015 |
arp | -0.015 |
unst | -0.015 |
Mill | -0.015 |
sorts | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
arp | +0.010 |
unst | +0.010 |
sorts | +0.009 |
aved | +0.009 |
wood | +0.009 |
Neg logit contributions | |
aids | -0.006 |
Dancing | -0.005 |
ggie | -0.005 |
song | -0.005 |
jokes | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
arp | +0.011 |
Joey | +0.011 |
sorts | +0.011 |
unst | +0.011 |
Mill | +0.011 |
Neg logit contributions | |
aids | -0.008 |
song | -0.007 |
ggie | -0.007 |
jokes | -0.007 |
hair | -0.007 |
Token | box |
Token ID | 3091 |
Feature activation | +7.83e+00 |
Pos logit contributions | |
aids | +0.062 |
song | +0.057 |
jokes | +0.056 |
hair | +0.054 |
wig | +0.053 |
Neg logit contributions | |
sorts | -0.063 |
Joey | -0.063 |
unst | -0.063 |
arp | -0.062 |
Mill | -0.062 |
Token | reaches |
Token ID | 12229 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
sorts | +0.452 |
unst | +0.449 |
aved | +0.438 |
arp | +0.438 |
deeper | +0.434 |
Neg logit contributions | |
aids | -0.576 |
uren | -0.512 |
ggie | -0.511 |
wig | -0.510 |
blond | -0.500 |
Token | the |
Token ID | 262 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
hair | +0.155 |
aids | +0.143 |
song | +0.131 |
jokes | +0.129 |
eyes | +0.124 |
Neg logit contributions | |
arp | -0.323 |
rolley | -0.316 |
pling | -0.315 |
aved | -0.314 |
ucer | -0.304 |
Token | end |
Token ID | 886 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
sorts | +0.037 |
Mill | +0.037 |
Joey | +0.037 |
aved | +0.036 |
irs | +0.035 |
Neg logit contributions | |
song | -0.028 |
hair | -0.027 |
wig | -0.025 |
clown | -0.025 |
aids | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
aids | +0.004 |
song | +0.003 |
hair | +0.003 |
ggie | +0.003 |
Dancing | +0.003 |
Neg logit contributions | |
unst | -0.004 |
Joey | -0.004 |
aved | -0.004 |
sorts | -0.004 |
arp | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
aved | +0.007 |
arp | +0.007 |
unst | +0.007 |
'll | +0.007 |
vell | +0.007 |
Neg logit contributions | |
aids | -0.005 |
hair | -0.004 |
song | -0.004 |
jokes | -0.004 |
poems | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
arp | +0.079 |
unst | +0.076 |
sorts | +0.076 |
Joey | +0.075 |
Mill | +0.074 |
Neg logit contributions | |
aids | -0.062 |
jokes | -0.053 |
hair | -0.053 |
song | -0.052 |
ggie | -0.051 |
Token | They |
Token ID | 1119 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
aids | +0.048 |
song | +0.041 |
jokes | +0.041 |
hair | +0.040 |
wig | +0.040 |
Neg logit contributions | |
arp | -0.046 |
Joey | -0.045 |
unst | -0.045 |
sorts | -0.045 |
aved | -0.044 |
Token | also |
Token ID | 635 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
arp | +0.010 |
rolley | +0.009 |
ucer | +0.009 |
unst | +0.009 |
sorts | +0.009 |
Neg logit contributions | |
aids | -0.009 |
jokes | -0.008 |
hair | -0.008 |
cheeks | -0.008 |
wig | -0.007 |
Token | want |
Token ID | 765 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
aids | +0.014 |
hair | +0.012 |
jokes | +0.012 |
wig | +0.012 |
song | +0.012 |
Neg logit contributions | |
arp | -0.015 |
Mill | -0.013 |
ucer | -0.013 |
Joey | -0.013 |
rolley | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
arp | +0.082 |
aved | +0.080 |
unst | +0.079 |
sorts | +0.078 |
ucer | +0.078 |
Neg logit contributions | |
aids | -0.054 |
jokes | -0.048 |
hair | -0.046 |
song | -0.045 |
poems | -0.044 |
Token | box |
Token ID | 3091 |
Feature activation | +7.45e+00 |
Pos logit contributions | |
irs | +0.012 |
Mill | +0.012 |
ucer | +0.012 |
aved | +0.012 |
sorts | +0.012 |
Neg logit contributions | |
song | -0.015 |
jokes | -0.015 |
hair | -0.015 |
aids | -0.014 |
wig | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
arp | +0.576 |
neath | +0.545 |
sorts | +0.544 |
Joey | +0.544 |
aved | +0.540 |
Neg logit contributions | |
aids | -0.434 |
song | -0.388 |
hair | -0.383 |
jokes | -0.372 |
ggie | -0.359 |
Token |
|
Token ID | 198 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
aids | +0.050 |
song | +0.043 |
jokes | +0.043 |
hair | +0.042 |
ggie | +0.042 |
Neg logit contributions | |
arp | -0.045 |
unst | -0.044 |
Joey | -0.044 |
sorts | -0.043 |
aved | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
aids | +0.010 |
ggie | +0.009 |
Dancing | +0.008 |
ggy | +0.008 |
jokes | +0.008 |
Neg logit contributions | |
unst | -0.016 |
arp | -0.016 |
aved | -0.016 |
extingu | -0.015 |
wood | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | -8.21e-03 |
Pos logit contributions | |
aids | +0.012 |
ggie | +0.010 |
song | +0.010 |
jokes | +0.010 |
wig | +0.010 |
Neg logit contributions | |
unst | -0.014 |
arp | -0.013 |
Joey | -0.013 |
sorts | -0.013 |
Mill | -0.013 |
Token | Let |
Token ID | 5756 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
aids | +0.001 |
jokes | +0.001 |
song | +0.001 |
hair | +0.001 |
poems | +0.001 |
Neg logit contributions | |
arp | -0.001 |
unst | -0.001 |
Joey | -0.001 |
sorts | -0.000 |
aved | -0.000 |
Token | bunny |
Token ID | 44915 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
aids | +0.136 |
jokes | +0.115 |
ggie | +0.114 |
wig | +0.113 |
Dancing | +0.112 |
Neg logit contributions | |
arp | -0.095 |
Joey | -0.094 |
unst | -0.093 |
sorts | -0.090 |
Mill | -0.090 |
Token | said |
Token ID | 531 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
aids | +0.018 |
Dancing | +0.015 |
wig | +0.015 |
poems | +0.015 |
jokes | +0.015 |
Neg logit contributions | |
Joey | -0.011 |
Mill | -0.011 |
sorts | -0.011 |
scaven | -0.010 |
'll | -0.010 |
Token | hello |
Token ID | 23748 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
Joey | +0.005 |
Mill | +0.005 |
unst | +0.004 |
Bobby | +0.004 |
deeper | +0.004 |
Neg logit contributions | |
aids | -0.007 |
wig | -0.007 |
poems | -0.006 |
uren | -0.006 |
song | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
aids | +0.356 |
poems | +0.297 |
jokes | +0.297 |
ggie | +0.295 |
wig | +0.291 |
Neg logit contributions | |
Joey | -0.268 |
unst | -0.265 |
arp | -0.262 |
Mill | -0.259 |
wood | -0.249 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
arp | +0.002 |
aved | +0.002 |
unst | +0.002 |
sorts | +0.002 |
rolley | +0.002 |
Neg logit contributions | |
aids | -0.002 |
song | -0.002 |
jokes | -0.002 |
hair | -0.002 |
wig | -0.002 |
Token | if |
Token ID | 611 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
aids | +0.091 |
jokes | +0.083 |
song | +0.080 |
poems | +0.079 |
hair | +0.079 |
Neg logit contributions | |
arp | -0.096 |
aved | -0.091 |
rolley | -0.088 |
sorts | -0.087 |
unst | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
arp | +0.488 |
unst | +0.476 |
sorts | +0.473 |
Joey | +0.471 |
aved | +0.465 |
Neg logit contributions | |
aids | -0.575 |
song | -0.497 |
jokes | -0.497 |
hair | -0.488 |
ggie | -0.486 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
arp | +0.030 |
Joey | +0.029 |
unst | +0.029 |
Mill | +0.028 |
sorts | +0.028 |
Neg logit contributions | |
aids | -0.038 |
jokes | -0.032 |
ggie | -0.032 |
wig | -0.032 |
poems | -0.031 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
aids | +0.139 |
wig | +0.119 |
song | +0.119 |
hair | +0.118 |
poems | +0.117 |
Neg logit contributions | |
Joey | -0.101 |
Mill | -0.097 |
sorts | -0.097 |
unst | -0.095 |
arp | -0.093 |
Token | to |
Token ID | 284 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
aids | +0.013 |
wig | +0.011 |
song | +0.011 |
uren | +0.011 |
ggie | +0.011 |
Neg logit contributions | |
Joey | -0.011 |
unst | -0.010 |
Mill | -0.010 |
sorts | -0.010 |
arp | -0.010 |
Token | be |
Token ID | 307 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
aids | +0.093 |
jokes | +0.079 |
song | +0.079 |
poems | +0.079 |
wig | +0.078 |
Neg logit contributions | |
arp | -0.074 |
unst | -0.073 |
Joey | -0.073 |
sorts | -0.072 |
Mill | -0.071 |
Token | grass |
Token ID | 8701 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
sorts | +0.031 |
Joey | +0.031 |
aved | +0.029 |
Suz | +0.029 |
aback | +0.029 |
Neg logit contributions | |
song | -0.029 |
hair | -0.029 |
aids | -0.028 |
wig | -0.027 |
songs | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
unst | +0.104 |
Joey | +0.103 |
sorts | +0.103 |
arp | +0.103 |
Mill | +0.102 |
Neg logit contributions | |
aids | -0.064 |
song | -0.056 |
hair | -0.056 |
wig | -0.053 |
ggie | -0.052 |
Token | She |
Token ID | 1375 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
aids | +0.013 |
hair | +0.011 |
Dancing | +0.011 |
jokes | +0.010 |
wig | +0.010 |
Neg logit contributions | |
arp | -0.019 |
sorts | -0.018 |
unst | -0.018 |
aved | -0.018 |
Joey | -0.018 |
Token | turned |
Token ID | 2900 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
arp | +0.059 |
Joey | +0.058 |
Mill | +0.055 |
sorts | +0.055 |
wood | +0.054 |
Neg logit contributions | |
aids | -0.042 |
hair | -0.040 |
wig | -0.039 |
song | -0.037 |
ggie | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
aids | +0.043 |
hair | +0.041 |
poems | +0.036 |
song | +0.036 |
jokes | +0.035 |
Neg logit contributions | |
arp | -0.053 |
sorts | -0.051 |
rolley | -0.051 |
wood | -0.049 |
erek | -0.048 |
Token | box |
Token ID | 3091 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
Joey | +0.030 |
sorts | +0.030 |
Suz | +0.028 |
Mill | +0.027 |
Bobby | +0.026 |
Neg logit contributions | |
song | -0.035 |
hair | -0.033 |
aids | -0.033 |
poems | -0.032 |
songs | -0.032 |
Token | upside |
Token ID | 17196 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
arp | +0.556 |
Joey | +0.541 |
sorts | +0.530 |
unst | +0.528 |
aved | +0.522 |
Neg logit contributions | |
aids | -0.522 |
song | -0.456 |
hair | -0.451 |
jokes | -0.441 |
poems | -0.433 |
Token | down |
Token ID | 866 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
sorts | +0.060 |
Joey | +0.054 |
hed | +0.054 |
arp | +0.054 |
Mill | +0.053 |
Neg logit contributions | |
aids | -0.084 |
hair | -0.083 |
wig | -0.079 |
song | -0.078 |
cheeks | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
arp | +0.025 |
aved | +0.024 |
Joey | +0.024 |
sorts | +0.024 |
ylan | +0.024 |
Neg logit contributions | |
aids | -0.011 |
hair | -0.010 |
song | -0.010 |
poems | -0.009 |
curly | -0.009 |
Token | cut |
Token ID | 2005 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
arp | +0.025 |
sorts | +0.023 |
Joey | +0.023 |
rolley | +0.023 |
aved | +0.022 |
Neg logit contributions | |
aids | -0.020 |
hair | -0.019 |
wig | -0.018 |
jokes | -0.017 |
song | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
sorts | +0.101 |
arp | +0.098 |
Joey | +0.096 |
scaven | +0.094 |
rolley | +0.094 |
Neg logit contributions | |
aids | -0.095 |
hair | -0.095 |
poems | -0.081 |
ggie | -0.080 |
song | -0.080 |
Token | should |
Token ID | 815 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
arp | +0.053 |
rolley | +0.052 |
hed | +0.051 |
unst | +0.050 |
ylan | +0.050 |
Neg logit contributions | |
aids | -0.044 |
jokes | -0.040 |
ggie | -0.039 |
hair | -0.038 |
song | -0.037 |
Token | not |
Token ID | 407 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
arp | +0.315 |
unst | +0.311 |
sorts | +0.311 |
aved | +0.306 |
Joey | +0.306 |
Neg logit contributions | |
aids | -0.176 |
jokes | -0.144 |
song | -0.144 |
hair | -0.141 |
ggie | -0.140 |
Token | climb |
Token ID | 12080 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
aids | +0.182 |
jokes | +0.155 |
song | +0.154 |
poems | +0.154 |
wig | +0.152 |
Neg logit contributions | |
arp | -0.165 |
unst | -0.163 |
Joey | -0.162 |
sorts | -0.160 |
aved | -0.159 |
Token | the |
Token ID | 262 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
arp | +0.046 |
sorts | +0.046 |
rolley | +0.043 |
aved | +0.043 |
ucer | +0.043 |
Neg logit contributions | |
aids | -0.040 |
hair | -0.037 |
jokes | -0.035 |
poems | -0.035 |
song | -0.034 |
Token | ladder |
Token ID | 18002 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
Joey | +0.042 |
sorts | +0.040 |
aved | +0.039 |
arp | +0.039 |
Mill | +0.039 |
Neg logit contributions | |
aids | -0.040 |
hair | -0.039 |
song | -0.039 |
yoga | -0.035 |
jokes | -0.035 |
Token | without |
Token ID | 1231 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
arp | +0.258 |
Joey | +0.257 |
Mill | +0.253 |
sorts | +0.251 |
aved | +0.249 |
Neg logit contributions | |
aids | -0.189 |
song | -0.163 |
hair | -0.162 |
jokes | -0.157 |
ggie | -0.154 |
Token | me |
Token ID | 502 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
arp | +0.312 |
unst | +0.309 |
Joey | +0.308 |
sorts | +0.304 |
aved | +0.299 |
Neg logit contributions | |
aids | -0.295 |
song | -0.250 |
jokes | -0.248 |
hair | -0.244 |
ggie | -0.243 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
aids | +0.117 |
song | +0.100 |
hair | +0.099 |
jokes | +0.099 |
ggie | +0.098 |
Neg logit contributions | |
arp | -0.122 |
sorts | -0.119 |
Joey | -0.119 |
unst | -0.118 |
aved | -0.117 |
Token | It |
Token ID | 632 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
aids | +0.022 |
song | +0.019 |
jokes | +0.019 |
ggie | +0.019 |
hair | +0.019 |
Neg logit contributions | |
arp | -0.023 |
unst | -0.023 |
Joey | -0.023 |
sorts | -0.022 |
aved | -0.022 |
Token | is |
Token ID | 318 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
aids | +0.127 |
song | +0.108 |
jokes | +0.108 |
ggie | +0.106 |
hair | +0.106 |
Neg logit contributions | |
arp | -0.134 |
Joey | -0.132 |
sorts | -0.130 |
unst | -0.130 |
Mill | -0.128 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
arp | +0.045 |
Joey | +0.044 |
sorts | +0.044 |
aved | +0.044 |
unst | +0.044 |
Neg logit contributions | |
aids | -0.032 |
song | -0.027 |
jokes | -0.026 |
hair | -0.026 |
ggie | -0.026 |
Token | find |
Token ID | 1064 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
aids | +0.076 |
ggie | +0.067 |
cheeks | +0.067 |
agged | +0.063 |
ggy | +0.063 |
Neg logit contributions | |
sorts | -0.062 |
Joey | -0.057 |
unst | -0.055 |
hed | -0.054 |
neath | -0.053 |
Token | some |
Token ID | 617 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
arp | +0.279 |
unst | +0.276 |
aved | +0.270 |
Joey | +0.269 |
Mill | +0.263 |
Neg logit contributions | |
aids | -0.270 |
jokes | -0.240 |
song | -0.235 |
hair | -0.235 |
poems | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
aids | +0.083 |
ggie | +0.068 |
uren | +0.067 |
wig | +0.067 |
cheeks | +0.066 |
Neg logit contributions | |
sorts | -0.092 |
arp | -0.088 |
hed | -0.086 |
unst | -0.085 |
Joey | -0.085 |
Token | He |
Token ID | 679 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
aids | +0.012 |
song | +0.010 |
wig | +0.010 |
jokes | +0.010 |
poems | +0.010 |
Neg logit contributions | |
Joey | -0.013 |
sorts | -0.013 |
arp | -0.013 |
unst | -0.012 |
Mill | -0.012 |
Token | wandered |
Token ID | 36036 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
arp | +0.006 |
unst | +0.006 |
Joey | +0.006 |
sorts | +0.006 |
aved | +0.006 |
Neg logit contributions | |
aids | -0.007 |
song | -0.006 |
jokes | -0.006 |
hair | -0.006 |
wig | -0.006 |
Token | through |
Token ID | 832 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
hair | +0.033 |
aids | +0.033 |
song | +0.032 |
songs | +0.032 |
jokes | +0.031 |
Neg logit contributions | |
extingu | -0.052 |
arp | -0.051 |
unst | -0.049 |
pling | -0.049 |
rolley | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
arp | +0.241 |
unst | +0.237 |
ucer | +0.229 |
aved | +0.228 |
ylan | +0.226 |
Neg logit contributions | |
aids | -0.180 |
hair | -0.171 |
jokes | -0.166 |
song | -0.163 |
poems | -0.163 |
Token | forest |
Token ID | 8222 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Joey | +0.038 |
unst | +0.038 |
arp | +0.036 |
aved | +0.036 |
Mill | +0.036 |
Neg logit contributions | |
aids | -0.049 |
hair | -0.045 |
song | -0.045 |
jokes | -0.044 |
poems | -0.043 |
Token | until |
Token ID | 1566 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
arp | +0.200 |
unst | +0.191 |
Joey | +0.188 |
neath | +0.188 |
aved | +0.185 |
Neg logit contributions | |
aids | -0.119 |
song | -0.111 |
hair | -0.109 |
jokes | -0.106 |
songs | -0.101 |
Token | he |
Token ID | 339 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
arp | +0.184 |
sorts | +0.179 |
unst | +0.178 |
Joey | +0.174 |
aved | +0.173 |
Neg logit contributions | |
aids | -0.155 |
song | -0.130 |
jokes | -0.130 |
hair | -0.129 |
ggie | -0.127 |
Token | found |
Token ID | 1043 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
aids | +0.035 |
song | +0.030 |
jokes | +0.030 |
hair | +0.030 |
wig | +0.030 |
Neg logit contributions | |
arp | -0.025 |
unst | -0.025 |
Joey | -0.025 |
sorts | -0.025 |
aved | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
arp | +0.026 |
sorts | +0.025 |
unst | +0.025 |
aved | +0.025 |
rolley | +0.024 |
Neg logit contributions | |
aids | -0.025 |
jokes | -0.022 |
hair | -0.022 |
song | -0.022 |
ggie | -0.022 |
Token | wise |
Token ID | 10787 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
Joey | +0.023 |
arp | +0.023 |
unst | +0.023 |
sorts | +0.023 |
Mill | +0.022 |
Neg logit contributions | |
aids | -0.022 |
jokes | -0.019 |
hair | -0.018 |
poems | -0.018 |
Dancing | -0.018 |
Token | old |
Token ID | 1468 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
arp | +0.071 |
Joey | +0.071 |
sorts | +0.070 |
unst | +0.070 |
Mill | +0.069 |
Neg logit contributions | |
aids | -0.064 |
jokes | -0.054 |
song | -0.053 |
ggie | -0.053 |
hair | -0.053 |
Token | crab |
Token ID | 32202 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Joey | +0.133 |
arp | +0.133 |
sorts | +0.131 |
unst | +0.130 |
Mill | +0.129 |
Neg logit contributions | |
aids | -0.118 |
jokes | -0.098 |
song | -0.096 |
ggie | -0.096 |
hair | -0.096 |
Token | crawled |
Token ID | 45668 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
aids | +0.137 |
jokes | +0.119 |
song | +0.119 |
hair | +0.118 |
poems | +0.118 |
Neg logit contributions | |
arp | -0.098 |
Joey | -0.096 |
unst | -0.096 |
aved | -0.095 |
sorts | -0.094 |
Token | up |
Token ID | 510 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
sorts | +0.030 |
arp | +0.029 |
rolley | +0.028 |
pling | +0.027 |
ucer | +0.027 |
Neg logit contributions | |
aids | -0.029 |
hair | -0.027 |
song | -0.026 |
jokes | -0.025 |
poems | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
arp | +0.151 |
aved | +0.141 |
ucer | +0.140 |
rolley | +0.139 |
sorts | +0.139 |
Neg logit contributions | |
aids | -0.114 |
song | -0.096 |
hair | -0.096 |
jokes | -0.095 |
ggie | -0.090 |
Token | them |
Token ID | 606 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
aids | +0.071 |
jokes | +0.065 |
song | +0.063 |
wig | +0.060 |
hair | +0.059 |
Neg logit contributions | |
arp | -0.092 |
aved | -0.088 |
rolley | -0.087 |
ucer | -0.084 |
pling | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
aids | +0.100 |
song | +0.086 |
jokes | +0.085 |
hair | +0.084 |
ggie | +0.082 |
Neg logit contributions | |
arp | -0.120 |
unst | -0.116 |
sorts | -0.116 |
aved | -0.115 |
Joey | -0.114 |
Token | said |
Token ID | 531 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
arp | +0.012 |
sorts | +0.011 |
aved | +0.011 |
unst | +0.011 |
Joey | +0.011 |
Neg logit contributions | |
aids | -0.010 |
jokes | -0.008 |
song | -0.008 |
wig | -0.008 |
hair | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Joey | +0.005 |
Mill | +0.004 |
unst | +0.004 |
Suz | +0.004 |
Bobby | +0.004 |
Neg logit contributions | |
aids | -0.006 |
song | -0.005 |
wig | -0.005 |
poems | -0.005 |
Dancing | -0.005 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
aids | +0.041 |
jokes | +0.037 |
song | +0.037 |
ggie | +0.036 |
hair | +0.036 |
Neg logit contributions | |
arp | -0.026 |
Joey | -0.024 |
Mill | -0.024 |
unst | -0.024 |
hed | -0.024 |
Token | glad |
Token ID | 9675 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Joey | +0.087 |
unst | +0.086 |
Mill | +0.084 |
sorts | +0.084 |
arp | +0.081 |
Neg logit contributions | |
aids | -0.099 |
song | -0.086 |
jokes | -0.085 |
cheeks | -0.085 |
wig | -0.084 |
Token | we |
Token ID | 356 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Joey | +0.072 |
Mill | +0.068 |
Bobby | +0.063 |
Suz | +0.061 |
sorts | +0.059 |
Neg logit contributions | |
aids | -0.141 |
wig | -0.124 |
ggie | -0.121 |
hair | -0.120 |
blond | -0.119 |
Token | grew |
Token ID | 6348 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
arp | +0.071 |
extingu | +0.067 |
hed | +0.065 |
rolley | +0.064 |
Mill | +0.064 |
Neg logit contributions | |
aids | -0.063 |
jokes | -0.059 |
hair | -0.057 |
song | -0.057 |
Dancing | -0.054 |
Token | them |
Token ID | 606 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
hair | +0.075 |
jokes | +0.074 |
aids | +0.073 |
poems | +0.070 |
song | +0.070 |
Neg logit contributions | |
erek | -0.101 |
aved | -0.099 |
arp | -0.099 |
ylan | -0.099 |
rolley | -0.098 |
Token | together |
Token ID | 1978 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
song | +0.099 |
aids | +0.097 |
jokes | +0.096 |
hair | +0.093 |
poems | +0.093 |
Neg logit contributions | |
arp | -0.098 |
aved | -0.097 |
erek | -0.093 |
neath | -0.092 |
sorts | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
arp | +0.220 |
unst | +0.212 |
aved | +0.212 |
Joey | +0.209 |
sorts | +0.206 |
Neg logit contributions | |
aids | -0.218 |
song | -0.199 |
jokes | -0.194 |
hair | -0.190 |
poems | -0.188 |
Token | Can |
Token ID | 1680 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
aids | +0.019 |
song | +0.016 |
jokes | +0.016 |
hair | +0.016 |
ggie | +0.016 |
Neg logit contributions | |
arp | -0.018 |
unst | -0.018 |
Joey | -0.017 |
sorts | -0.017 |
aved | -0.017 |
Token | we |
Token ID | 356 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
aids | +0.241 |
poems | +0.210 |
ggie | +0.209 |
wig | +0.209 |
jokes | +0.208 |
Neg logit contributions | |
Joey | -0.078 |
Mill | -0.074 |
Bobby | -0.070 |
arp | -0.063 |
'll | -0.061 |
Token | still |
Token ID | 991 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
arp | +0.052 |
unst | +0.051 |
sorts | +0.051 |
Joey | +0.051 |
aved | +0.050 |
Neg logit contributions | |
aids | -0.043 |
song | -0.038 |
jokes | -0.038 |
hair | -0.037 |
wig | -0.036 |
Token | be |
Token ID | 307 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
arp | +0.026 |
unst | +0.026 |
Joey | +0.026 |
sorts | +0.026 |
aved | +0.025 |
Neg logit contributions | |
aids | -0.021 |
song | -0.017 |
jokes | -0.017 |
hair | -0.017 |
ggie | -0.017 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Joey | +0.079 |
Mill | +0.077 |
Suz | +0.076 |
unst | +0.076 |
extingu | +0.075 |
Neg logit contributions | |
aids | -0.093 |
poems | -0.081 |
Dancing | -0.080 |
song | -0.078 |
hair | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
aids | +0.174 |
ggie | +0.157 |
wig | +0.153 |
uren | +0.151 |
jokes | +0.146 |
Neg logit contributions | |
unst | -0.094 |
arp | -0.092 |
Joey | -0.090 |
sorts | -0.088 |
deeper | -0.087 |
Token | said |
Token ID | 531 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
aids | +0.009 |
ggie | +0.007 |
song | +0.007 |
poems | +0.007 |
jokes | +0.007 |
Neg logit contributions | |
unst | -0.008 |
Joey | -0.008 |
sorts | -0.008 |
Mill | -0.008 |
arp | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
aids | +0.007 |
song | +0.006 |
wig | +0.006 |
jokes | +0.006 |
poems | +0.006 |
Neg logit contributions | |
unst | -0.004 |
Joey | -0.004 |
Mill | -0.004 |
arp | -0.004 |
aved | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
aids | +0.001 |
poems | +0.001 |
ggie | +0.001 |
jokes | +0.001 |
wig | +0.001 |
Neg logit contributions | |
Mill | -0.001 |
Joey | -0.001 |
unst | -0.001 |
Bobby | -0.001 |
extingu | -0.001 |
Token | Don |
Token ID | 3987 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
aids | +0.067 |
jokes | +0.059 |
hair | +0.059 |
ggie | +0.058 |
cheeks | +0.058 |
Neg logit contributions | |
arp | -0.038 |
sorts | -0.036 |
unst | -0.035 |
Joey | -0.034 |
Mill | -0.034 |
Token | 't |
Token ID | 470 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
arp | +0.339 |
unst | +0.338 |
Joey | +0.331 |
Mill | +0.325 |
sorts | +0.325 |
Neg logit contributions | |
aids | -0.288 |
jokes | -0.244 |
wig | -0.240 |
hair | -0.240 |
song | -0.240 |
Token | be |
Token ID | 307 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
aids | +0.182 |
poems | +0.164 |
ggie | +0.160 |
uren | +0.157 |
wig | +0.157 |
Neg logit contributions | |
Joey | -0.093 |
Mill | -0.088 |
unst | -0.085 |
Suz | -0.082 |
arp | -0.076 |
Token | scared |
Token ID | 12008 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
aids | +0.334 |
song | +0.293 |
poems | +0.292 |
cheeks | +0.291 |
wig | +0.289 |
Neg logit contributions | |
unst | -0.249 |
Joey | -0.239 |
Mill | -0.230 |
sorts | -0.229 |
hed | -0.227 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e-03 |
Pos logit contributions | |
arp | +0.050 |
unst | +0.050 |
Joey | +0.049 |
sorts | +0.049 |
Mill | +0.048 |
Neg logit contributions | |
aids | -0.058 |
song | -0.050 |
jokes | -0.049 |
wig | -0.049 |
hair | -0.049 |
Token | Anna |
Token ID | 11735 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
Joey | +0.000 |
Mill | +0.000 |
unst | +0.000 |
arp | +0.000 |
sorts | +0.000 |
Neg logit contributions | |
aids | -0.000 |
ggie | -0.000 |
wig | -0.000 |
Dancing | -0.000 |
hair | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Joey | +0.102 |
Mill | +0.099 |
unst | +0.097 |
sorts | +0.096 |
Suz | +0.093 |
Neg logit contributions | |
aids | -0.137 |
poems | -0.119 |
Dancing | -0.116 |
wig | -0.116 |
song | -0.115 |
Token | so |
Token ID | 523 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
unst | +0.026 |
Joey | +0.025 |
sorts | +0.025 |
Mill | +0.024 |
Suz | +0.023 |
Neg logit contributions | |
aids | -0.039 |
poems | -0.036 |
wig | -0.035 |
song | -0.035 |
jokes | -0.035 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
aids | +0.065 |
jokes | +0.053 |
song | +0.053 |
hair | +0.053 |
ggie | +0.052 |
Neg logit contributions | |
arp | -0.091 |
unst | -0.086 |
Joey | -0.085 |
sorts | -0.085 |
aved | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
aids | +0.080 |
song | +0.067 |
jokes | +0.067 |
wig | +0.067 |
hair | +0.067 |
Neg logit contributions | |
Joey | -0.066 |
arp | -0.064 |
sorts | -0.064 |
unst | -0.063 |
Mill | -0.063 |
Token | he |
Token ID | 339 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
Joey | +0.015 |
unst | +0.015 |
sorts | +0.015 |
Mill | +0.014 |
arp | +0.014 |
Neg logit contributions | |
aids | -0.017 |
wig | -0.015 |
jokes | -0.014 |
poems | -0.014 |
song | -0.014 |
Token | bark |
Token ID | 21405 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
aids | +0.042 |
jokes | +0.035 |
song | +0.035 |
wig | +0.034 |
poems | +0.034 |
Neg logit contributions | |
unst | -0.036 |
Joey | -0.036 |
sorts | -0.036 |
Mill | -0.035 |
arp | -0.035 |
Token | ed |
Token ID | 276 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
aids | +0.353 |
wig | +0.311 |
jokes | +0.310 |
song | +0.310 |
poems | +0.309 |
Neg logit contributions | |
unst | -0.173 |
arp | -0.169 |
Joey | -0.168 |
aved | -0.167 |
sorts | -0.167 |
Token | with |
Token ID | 351 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
Joey | +0.041 |
unst | +0.041 |
sorts | +0.040 |
arp | +0.039 |
Mill | +0.039 |
Neg logit contributions | |
aids | -0.053 |
wig | -0.045 |
ggie | -0.045 |
song | -0.045 |
poems | -0.045 |
Token | joy |
Token ID | 8716 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
aids | +0.057 |
jokes | +0.050 |
song | +0.050 |
hair | +0.049 |
wig | +0.048 |
Neg logit contributions | |
arp | -0.043 |
unst | -0.041 |
Joey | -0.040 |
aved | -0.040 |
sorts | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Joey | +0.108 |
Mill | +0.102 |
arp | +0.102 |
unst | +0.100 |
sorts | +0.097 |
Neg logit contributions | |
aids | -0.150 |
Dancing | -0.126 |
wig | -0.126 |
ggie | -0.125 |
song | -0.123 |
Token | He |
Token ID | 679 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
aids | +0.013 |
song | +0.012 |
wig | +0.012 |
ggie | +0.012 |
jokes | +0.011 |
Neg logit contributions | |
Joey | -0.011 |
Mill | -0.010 |
unst | -0.010 |
Bobby | -0.010 |
sorts | -0.010 |
Token | sheep |
Token ID | 15900 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
arp | +0.040 |
unst | +0.039 |
Joey | +0.039 |
sorts | +0.038 |
aved | +0.038 |
Neg logit contributions | |
aids | -0.038 |
jokes | -0.031 |
song | -0.031 |
ggie | -0.031 |
wig | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
aids | +0.128 |
song | +0.110 |
jokes | +0.110 |
hair | +0.108 |
ggie | +0.107 |
Neg logit contributions | |
arp | -0.121 |
unst | -0.119 |
Joey | -0.118 |
sorts | -0.117 |
aved | -0.115 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
arp | +0.022 |
aved | +0.020 |
unst | +0.020 |
Joey | +0.020 |
sorts | +0.020 |
Neg logit contributions | |
aids | -0.016 |
hair | -0.014 |
song | -0.014 |
jokes | -0.014 |
poems | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Joey | +0.013 |
arp | +0.013 |
unst | +0.013 |
sorts | +0.013 |
Mill | +0.013 |
Neg logit contributions | |
aids | -0.017 |
song | -0.015 |
jokes | -0.015 |
ggie | -0.015 |
hair | -0.015 |
Token | dog |
Token ID | 3290 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
arp | +0.039 |
unst | +0.039 |
Joey | +0.038 |
sorts | +0.038 |
aved | +0.037 |
Neg logit contributions | |
aids | -0.039 |
jokes | -0.032 |
ggie | -0.032 |
song | -0.032 |
Dancing | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
aids | +0.067 |
song | +0.057 |
jokes | +0.057 |
wig | +0.056 |
poems | +0.056 |
Neg logit contributions | |
unst | -0.055 |
arp | -0.054 |
sorts | -0.054 |
Joey | -0.054 |
aved | -0.053 |
Token | |
Token ID | 220 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
aids | +0.009 |
song | +0.008 |
wig | +0.008 |
ggie | +0.008 |
jokes | +0.008 |
Neg logit contributions | |
Joey | -0.008 |
arp | -0.007 |
sorts | -0.007 |
unst | -0.007 |
Mill | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
aids | +0.045 |
Dancing | +0.037 |
ggie | +0.037 |
jokes | +0.036 |
hair | +0.036 |
Neg logit contributions | |
arp | -0.061 |
unst | -0.060 |
aved | -0.059 |
sorts | -0.059 |
extingu | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
unst | +0.026 |
arp | +0.026 |
aved | +0.025 |
Joey | +0.025 |
sorts | +0.025 |
Neg logit contributions | |
aids | -0.024 |
song | -0.021 |
ggie | -0.020 |
jokes | -0.020 |
Dancing | -0.020 |
Token | At |
Token ID | 2953 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
arp | +0.023 |
sorts | +0.023 |
Joey | +0.022 |
aved | +0.022 |
neath | +0.022 |
Neg logit contributions | |
aids | -0.027 |
cheeks | -0.024 |
hair | -0.024 |
wig | -0.023 |
jokes | -0.023 |
Token | first |
Token ID | 717 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
aids | +0.029 |
song | +0.027 |
jokes | +0.026 |
hair | +0.026 |
ggie | +0.026 |
Neg logit contributions | |
arp | -0.032 |
aved | -0.029 |
Joey | -0.029 |
unst | -0.029 |
rolley | -0.029 |
Token | bug |
Token ID | 5434 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
arp | +0.038 |
unst | +0.037 |
aved | +0.037 |
sorts | +0.037 |
Joey | +0.036 |
Neg logit contributions | |
aids | -0.040 |
song | -0.036 |
jokes | -0.035 |
hair | -0.035 |
wig | -0.034 |
Token | ! |
Token ID | 0 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
aids | +0.117 |
song | +0.103 |
jokes | +0.101 |
hair | +0.101 |
ggie | +0.100 |
Neg logit contributions | |
arp | -0.107 |
unst | -0.105 |
Joey | -0.104 |
sorts | -0.103 |
aved | -0.102 |
Token | Sarah |
Token ID | 10490 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Mill | +0.218 |
sorts | +0.217 |
unst | +0.216 |
Joey | +0.210 |
arp | +0.203 |
Neg logit contributions | |
aids | -0.324 |
wig | -0.301 |
ggie | -0.299 |
song | -0.290 |
jokes | -0.290 |
Token | was |
Token ID | 373 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
arp | +0.073 |
Joey | +0.072 |
unst | +0.072 |
sorts | +0.072 |
aved | +0.071 |
Neg logit contributions | |
aids | -0.091 |
song | -0.078 |
jokes | -0.078 |
wig | -0.077 |
poems | -0.076 |
Token | surprised |
Token ID | 6655 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
unst | +0.021 |
Joey | +0.020 |
Mill | +0.020 |
sorts | +0.019 |
deeper | +0.019 |
Neg logit contributions | |
aids | -0.026 |
uren | -0.023 |
wig | -0.023 |
poems | -0.023 |
cheeks | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
aids | +0.019 |
song | +0.016 |
wig | +0.016 |
jokes | +0.016 |
ggie | +0.016 |
Neg logit contributions | |
Joey | -0.016 |
arp | -0.016 |
sorts | -0.016 |
unst | -0.016 |
Mill | -0.015 |
Token | find |
Token ID | 1064 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
aids | +0.112 |
poems | +0.100 |
ggie | +0.100 |
song | +0.098 |
wig | +0.098 |
Neg logit contributions | |
Joey | -0.048 |
unst | -0.047 |
Mill | -0.046 |
sorts | -0.045 |
aved | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
rolley | +0.286 |
ylan | +0.283 |
wood | +0.282 |
arp | +0.280 |
erek | +0.278 |
Neg logit contributions | |
aids | -0.237 |
hair | -0.223 |
song | -0.206 |
jokes | -0.201 |
poems | -0.198 |
Token | dead |
Token ID | 2636 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
arp | +0.024 |
aved | +0.024 |
sorts | +0.023 |
Joey | +0.023 |
unst | +0.023 |
Neg logit contributions | |
aids | -0.022 |
song | -0.020 |
hair | -0.019 |
wig | -0.019 |
jokes | -0.019 |
Token | bug |
Token ID | 5434 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
arp | +0.042 |
unst | +0.042 |
Joey | +0.041 |
sorts | +0.041 |
aved | +0.041 |
Neg logit contributions | |
aids | -0.042 |
song | -0.036 |
jokes | -0.036 |
hair | -0.035 |
wig | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
aids | +0.108 |
song | +0.094 |
jokes | +0.094 |
hair | +0.092 |
wig | +0.092 |
Neg logit contributions | |
arp | -0.111 |
unst | -0.108 |
Joey | -0.108 |
sorts | -0.107 |
aved | -0.106 |
Token | who |
Token ID | 508 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
unst | +0.085 |
Joey | +0.082 |
arp | +0.082 |
sorts | +0.081 |
aved | +0.079 |
Neg logit contributions | |
aids | -0.104 |
uren | -0.091 |
poems | -0.090 |
cheeks | -0.087 |
song | -0.087 |
Token | had |
Token ID | 550 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
aids | +0.119 |
song | +0.102 |
jokes | +0.102 |
wig | +0.101 |
hair | +0.101 |
Neg logit contributions | |
Joey | -0.094 |
arp | -0.094 |
sorts | -0.093 |
unst | -0.093 |
aved | -0.091 |
Token | fallen |
Token ID | 9292 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
aids | +0.092 |
uren | +0.079 |
song | +0.079 |
Dancing | +0.079 |
jokes | +0.078 |
Neg logit contributions | |
unst | -0.061 |
Joey | -0.058 |
sorts | -0.056 |
Mill | -0.056 |
arp | -0.055 |
Token | down |
Token ID | 866 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
arp | +0.176 |
sorts | +0.175 |
Joey | +0.171 |
ylan | +0.169 |
erek | +0.168 |
Neg logit contributions | |
aids | -0.217 |
hair | -0.209 |
song | -0.197 |
wig | -0.189 |
jokes | -0.186 |
Token | and |
Token ID | 290 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
arp | +0.037 |
ylan | +0.037 |
erek | +0.036 |
aved | +0.036 |
ucer | +0.036 |
Neg logit contributions | |
aids | -0.018 |
hair | -0.016 |
song | -0.015 |
poems | -0.014 |
curly | -0.013 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
arp | +0.047 |
sorts | +0.045 |
Joey | +0.044 |
aved | +0.044 |
unst | +0.044 |
Neg logit contributions | |
aids | -0.042 |
song | -0.035 |
jokes | -0.035 |
hair | -0.035 |
wig | -0.035 |
Token | his |
Token ID | 465 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
aids | +0.114 |
song | +0.096 |
jokes | +0.096 |
ggie | +0.094 |
wig | +0.094 |
Neg logit contributions | |
arp | -0.122 |
unst | -0.120 |
Joey | -0.120 |
sorts | -0.118 |
aved | -0.116 |
Token | knee |
Token ID | 10329 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
aids | +0.068 |
uren | +0.056 |
Dancing | +0.051 |
ggie | +0.050 |
poems | +0.049 |
Neg logit contributions | |
unst | -0.105 |
arp | -0.101 |
extingu | -0.098 |
Joey | -0.097 |
afloat | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
aids | +0.302 |
jokes | +0.259 |
wig | +0.254 |
ggie | +0.253 |
song | +0.252 |
Neg logit contributions | |
unst | -0.256 |
arp | -0.250 |
aved | -0.241 |
sorts | -0.239 |
Joey | -0.237 |
Token | just |
Token ID | 655 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
unst | +0.039 |
Joey | +0.039 |
Mill | +0.037 |
sorts | +0.037 |
arp | +0.037 |
Neg logit contributions | |
aids | -0.050 |
ggie | -0.044 |
jokes | -0.043 |
wig | -0.043 |
Dancing | -0.043 |
Token | like |
Token ID | 588 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
unst | +0.038 |
Joey | +0.038 |
sorts | +0.037 |
Mill | +0.037 |
aved | +0.036 |
Neg logit contributions | |
aids | -0.046 |
ggie | -0.039 |
wig | -0.039 |
song | -0.039 |
jokes | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
arp | +0.038 |
unst | +0.038 |
Joey | +0.037 |
sorts | +0.037 |
aved | +0.037 |
Neg logit contributions | |
aids | -0.040 |
jokes | -0.034 |
song | -0.034 |
ggie | -0.033 |
hair | -0.033 |
Token | The |
Token ID | 464 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
arp | +0.036 |
sorts | +0.036 |
Joey | +0.035 |
unst | +0.035 |
neath | +0.034 |
Neg logit contributions | |
aids | -0.042 |
hair | -0.036 |
wig | -0.036 |
jokes | -0.036 |
cheeks | -0.036 |
Token | doctor |
Token ID | 6253 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
aids | +0.039 |
cheeks | +0.033 |
uren | +0.033 |
jokes | +0.032 |
Dancing | +0.032 |
Neg logit contributions | |
handy | -0.036 |
unst | -0.034 |
deeper | -0.034 |
rolley | -0.031 |
shed | -0.031 |
Token | then |
Token ID | 788 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
aids | +0.009 |
jokes | +0.008 |
song | +0.008 |
hair | +0.008 |
wig | +0.008 |
Neg logit contributions | |
arp | -0.008 |
unst | -0.008 |
Joey | -0.008 |
sorts | -0.008 |
Mill | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
aids | +0.197 |
jokes | +0.169 |
song | +0.169 |
hair | +0.165 |
ggie | +0.164 |
Neg logit contributions | |
arp | -0.194 |
unst | -0.188 |
Joey | -0.185 |
sorts | -0.185 |
aved | -0.184 |
Token | Molly |
Token ID | 30236 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
Joey | +0.029 |
Mill | +0.028 |
Bobby | +0.027 |
unst | +0.026 |
if | +0.025 |
Neg logit contributions | |
aids | -0.041 |
wig | -0.037 |
song | -0.036 |
Dancing | -0.036 |
hair | -0.036 |
Token | should |
Token ID | 815 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
Joey | +0.005 |
unst | +0.005 |
Mill | +0.005 |
sorts | +0.005 |
arp | +0.005 |
Neg logit contributions | |
aids | -0.007 |
wig | -0.007 |
song | -0.007 |
jokes | -0.006 |
Dancing | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
arp | +0.272 |
unst | +0.267 |
Joey | +0.265 |
sorts | +0.264 |
aved | +0.260 |
Neg logit contributions | |
aids | -0.263 |
song | -0.224 |
jokes | -0.223 |
hair | -0.219 |
ggie | -0.218 |
Token | honest |
Token ID | 5508 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
aids | +0.267 |
song | +0.227 |
jokes | +0.226 |
wig | +0.223 |
ggie | +0.221 |
Neg logit contributions | |
unst | -0.252 |
arp | -0.249 |
sorts | -0.249 |
Joey | -0.248 |
aved | -0.241 |
Token | and |
Token ID | 290 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
arp | +0.114 |
unst | +0.111 |
aved | +0.110 |
Joey | +0.110 |
sorts | +0.108 |
Neg logit contributions | |
aids | -0.104 |
song | -0.090 |
jokes | -0.090 |
hair | -0.089 |
poems | -0.087 |
Token | not |
Token ID | 407 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
arp | +0.044 |
unst | +0.044 |
Joey | +0.044 |
sorts | +0.044 |
aved | +0.043 |
Neg logit contributions | |
aids | -0.044 |
song | -0.038 |
jokes | -0.037 |
hair | -0.037 |
wig | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Joey | +0.137 |
Mill | +0.132 |
unst | +0.124 |
Suz | +0.122 |
Bobby | +0.122 |
Neg logit contributions | |
aids | -0.185 |
song | -0.162 |
wig | -0.161 |
Dancing | -0.158 |
poems | -0.157 |
Token | " |
Token ID | 366 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Joey | +0.133 |
Mill | +0.128 |
unst | +0.123 |
Bobby | +0.120 |
Suz | +0.119 |
Neg logit contributions | |
aids | -0.125 |
ggie | -0.109 |
wig | -0.106 |
poems | -0.104 |
jokes | -0.104 |
Token | I |
Token ID | 40 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
arp | +0.035 |
Joey | +0.034 |
sorts | +0.034 |
Mill | +0.033 |
neath | +0.033 |
Neg logit contributions | |
aids | -0.056 |
jokes | -0.051 |
cheeks | -0.050 |
hair | -0.050 |
poems | -0.049 |
Token | miss |
Token ID | 2051 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
arp | +0.117 |
Joey | +0.108 |
unst | +0.108 |
hed | +0.106 |
sorts | +0.105 |
Neg logit contributions | |
aids | -0.189 |
jokes | -0.169 |
song | -0.168 |
ggie | -0.167 |
hair | -0.167 |
Token | you |
Token ID | 345 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
aids | +0.092 |
song | +0.080 |
jokes | +0.080 |
wig | +0.079 |
ggie | +0.079 |
Neg logit contributions | |
arp | -0.063 |
Joey | -0.062 |
unst | -0.062 |
sorts | -0.061 |
Mill | -0.060 |
Token | too |
Token ID | 1165 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
arp | +0.064 |
unst | +0.063 |
Joey | +0.063 |
sorts | +0.062 |
aved | +0.061 |
Neg logit contributions | |
aids | -0.080 |
song | -0.069 |
jokes | -0.069 |
hair | -0.068 |
wig | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
aids | +0.342 |
song | +0.303 |
hair | +0.302 |
jokes | +0.299 |
ggie | +0.290 |
Neg logit contributions | |
arp | -0.373 |
unst | -0.356 |
aved | -0.353 |
neath | -0.348 |
erek | -0.342 |
Token | daddy |
Token ID | 35822 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Joey | +0.044 |
arp | +0.043 |
unst | +0.043 |
Mill | +0.042 |
sorts | +0.042 |
Neg logit contributions | |
aids | -0.042 |
song | -0.034 |
jokes | -0.034 |
ggie | -0.034 |
hair | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
arp | +0.180 |
unst | +0.177 |
aved | +0.175 |
sorts | +0.173 |
Joey | +0.173 |
Neg logit contributions | |
aids | -0.183 |
song | -0.161 |
jokes | -0.159 |
hair | -0.156 |
ggie | -0.156 |
Token | But |
Token ID | 887 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
aids | +0.006 |
song | +0.005 |
jokes | +0.005 |
ggie | +0.005 |
wig | +0.005 |
Neg logit contributions | |
Joey | -0.005 |
arp | -0.005 |
Mill | -0.005 |
unst | -0.005 |
sorts | -0.005 |
Token | don |
Token ID | 836 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
aids | +0.081 |
song | +0.072 |
jokes | +0.072 |
hair | +0.070 |
wig | +0.069 |
Neg logit contributions | |
arp | -0.084 |
aved | -0.080 |
sorts | -0.079 |
unst | -0.078 |
rolley | -0.076 |
Token | go |
Token ID | 467 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
aids | +0.068 |
poems | +0.059 |
uren | +0.058 |
wig | +0.058 |
cheeks | +0.058 |
Neg logit contributions | |
Joey | -0.047 |
sorts | -0.047 |
unst | -0.046 |
Mill | -0.045 |
arp | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
aids | +0.010 |
song | +0.009 |
jokes | +0.009 |
hair | +0.009 |
wig | +0.009 |
Neg logit contributions | |
arp | -0.009 |
unst | -0.009 |
Joey | -0.009 |
sorts | -0.009 |
aved | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
aids | +0.062 |
jokes | +0.055 |
song | +0.055 |
hair | +0.054 |
poems | +0.053 |
Neg logit contributions | |
arp | -0.054 |
unst | -0.052 |
aved | -0.052 |
Joey | -0.051 |
sorts | -0.050 |
Token | meeting |
Token ID | 3249 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
arp | +0.035 |
Joey | +0.034 |
sorts | +0.034 |
unst | +0.034 |
scaven | +0.034 |
Neg logit contributions | |
aids | -0.048 |
cheeks | -0.041 |
hair | -0.040 |
jokes | -0.040 |
poems | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
aids | +0.374 |
cheeks | +0.320 |
uren | +0.317 |
wig | +0.317 |
Dancing | +0.315 |
Neg logit contributions | |
sorts | -0.256 |
Joey | -0.242 |
unst | -0.241 |
arp | -0.238 |
Mill | -0.236 |
Token | His |
Token ID | 2399 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
arp | +0.008 |
unst | +0.008 |
aved | +0.008 |
Joey | +0.008 |
sorts | +0.008 |
Neg logit contributions | |
aids | -0.008 |
jokes | -0.007 |
song | -0.007 |
hair | -0.006 |
poems | -0.006 |
Token | mum |
Token ID | 25682 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
aids | +0.384 |
wig | +0.302 |
poems | +0.298 |
song | +0.295 |
uren | +0.286 |
Neg logit contributions | |
Joey | -0.349 |
Mill | -0.349 |
erek | -0.336 |
shed | -0.334 |
barrel | -0.334 |
Token | told |
Token ID | 1297 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
aids | +0.071 |
song | +0.062 |
ggie | +0.062 |
hair | +0.061 |
jokes | +0.061 |
Neg logit contributions | |
arp | -0.086 |
unst | -0.083 |
hed | -0.083 |
aved | -0.081 |
Joey | -0.080 |
Token | him |
Token ID | 683 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
arp | +0.015 |
unst | +0.014 |
aved | +0.014 |
sorts | +0.014 |
Joey | +0.013 |
Neg logit contributions | |
aids | -0.027 |
jokes | -0.024 |
song | -0.024 |
poems | -0.024 |
hair | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
Joey | +0.227 |
Mill | +0.221 |
arp | +0.215 |
sorts | +0.214 |
unst | +0.211 |
Neg logit contributions | |
aids | -0.256 |
wig | -0.224 |
song | -0.222 |
hair | -0.216 |
Dancing | -0.214 |
Token | � |
Token ID | 6184 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Joey | +0.041 |
Mill | +0.040 |
unst | +0.039 |
sorts | +0.039 |
arp | +0.039 |
Neg logit contributions | |
aids | -0.034 |
ggie | -0.028 |
wig | -0.028 |
song | -0.028 |
jokes | -0.028 |
Token | hospital |
Token ID | 4436 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
arp | +0.035 |
unst | +0.034 |
sorts | +0.032 |
Joey | +0.032 |
aved | +0.031 |
Neg logit contributions | |
aids | -0.058 |
poems | -0.051 |
jokes | -0.051 |
cheeks | -0.050 |
song | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
unst | +0.054 |
Mill | +0.052 |
sorts | +0.051 |
Joey | +0.051 |
arp | +0.051 |
Neg logit contributions | |
aids | -0.079 |
wig | -0.069 |
jokes | -0.069 |
Dancing | -0.068 |
ggie | -0.068 |
Token | but |
Token ID | 475 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
arp | +0.039 |
aved | +0.037 |
sorts | +0.037 |
Joey | +0.036 |
wood | +0.036 |
Neg logit contributions | |
aids | -0.032 |
song | -0.028 |
hair | -0.027 |
jokes | -0.027 |
wig | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
arp | +0.028 |
aved | +0.027 |
sorts | +0.027 |
extingu | +0.026 |
Joey | +0.026 |
Neg logit contributions | |
aids | -0.023 |
song | -0.020 |
hair | -0.020 |
jokes | -0.020 |
poems | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
arp | +0.096 |
unst | +0.093 |
Joey | +0.093 |
sorts | +0.093 |
aved | +0.091 |
Neg logit contributions | |
aids | -0.121 |
song | -0.106 |
jokes | -0.105 |
ggie | -0.103 |
hair | -0.103 |
Token | too |
Token ID | 1165 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
arp | +0.053 |
unst | +0.052 |
Joey | +0.052 |
sorts | +0.052 |
aved | +0.051 |
Neg logit contributions | |
aids | -0.041 |
song | -0.034 |
jokes | -0.034 |
hair | -0.033 |
wig | -0.033 |
Token | late |
Token ID | 2739 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
aids | +0.407 |
song | +0.371 |
poems | +0.360 |
hair | +0.357 |
jokes | +0.352 |
Neg logit contributions | |
arp | -0.323 |
sorts | -0.319 |
Joey | -0.318 |
aved | -0.314 |
unst | -0.310 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
arp | +0.306 |
unst | +0.302 |
Joey | +0.300 |
sorts | +0.298 |
aved | +0.292 |
Neg logit contributions | |
aids | -0.326 |
jokes | -0.278 |
song | -0.278 |
wig | -0.273 |
hair | -0.272 |
Token | The |
Token ID | 383 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
unst | +0.008 |
Mill | +0.008 |
Joey | +0.007 |
Bobby | +0.007 |
arp | +0.007 |
Neg logit contributions | |
aids | -0.010 |
wig | -0.009 |
ggie | -0.009 |
song | -0.009 |
jokes | -0.009 |
Token | water |
Token ID | 1660 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
aids | +0.096 |
uren | +0.084 |
poems | +0.083 |
blond | +0.082 |
ggie | +0.081 |
Neg logit contributions | |
arp | -0.078 |
unst | -0.075 |
deeper | -0.073 |
hed | -0.071 |
aved | -0.070 |
Token | from |
Token ID | 422 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
arp | +0.144 |
unst | +0.141 |
sorts | +0.140 |
Joey | +0.140 |
aved | +0.137 |
Neg logit contributions | |
aids | -0.170 |
song | -0.147 |
jokes | -0.146 |
hair | -0.144 |
ggie | -0.143 |
Token | � |
Token ID | 95 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
Joey | +0.109 |
arp | +0.106 |
unst | +0.103 |
aved | +0.103 |
scaven | +0.099 |
Neg logit contributions | |
aids | -0.141 |
poems | -0.127 |
song | -0.122 |
jokes | -0.119 |
hair | -0.117 |
Token | € |
Token ID | 26391 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
sorts | +0.052 |
arp | +0.052 |
unst | +0.051 |
Joey | +0.051 |
aback | +0.049 |
Neg logit contributions | |
aids | -0.056 |
poems | -0.053 |
cheeks | -0.052 |
jokes | -0.050 |
song | -0.050 |
Token | � |
Token ID | 129 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
aids | +0.388 |
song | +0.334 |
jokes | +0.334 |
wig | +0.325 |
hair | +0.324 |
Neg logit contributions | |
arp | -0.332 |
Joey | -0.330 |
unst | -0.329 |
sorts | -0.325 |
aved | -0.320 |
Token | � |
Token ID | 241 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
aids | +0.027 |
wig | +0.025 |
cheeks | +0.024 |
song | +0.024 |
poems | +0.023 |
Neg logit contributions | |
unst | -0.029 |
Joey | -0.028 |
sorts | -0.028 |
arp | -0.027 |
aved | -0.026 |
Token | Me |
Token ID | 5308 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
aids | +0.296 |
jokes | +0.251 |
cheeks | +0.251 |
poems | +0.248 |
hair | +0.247 |
Neg logit contributions | |
Joey | -0.221 |
sorts | -0.220 |
arp | -0.209 |
Mill | -0.209 |
unst | -0.207 |
Token | too |
Token ID | 1165 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
aids | +0.057 |
poems | +0.047 |
wig | +0.047 |
jokes | +0.045 |
song | +0.045 |
Neg logit contributions | |
Joey | -0.063 |
unst | -0.062 |
Mill | -0.060 |
sorts | -0.059 |
Suz | -0.058 |
Token | ! |
Token ID | 0 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
aids | +0.480 |
song | +0.428 |
jokes | +0.427 |
hair | +0.421 |
ggie | +0.420 |
Neg logit contributions | |
arp | -0.247 |
unst | -0.240 |
Joey | -0.236 |
sorts | -0.235 |
aved | -0.231 |
Token | I |
Token ID | 314 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
Joey | +0.287 |
arp | +0.286 |
unst | +0.283 |
sorts | +0.281 |
Mill | +0.277 |
Neg logit contributions | |
aids | -0.321 |
song | -0.277 |
jokes | -0.276 |
ggie | -0.272 |
wig | -0.271 |
Token | like |
Token ID | 588 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
aids | +0.045 |
song | +0.040 |
jokes | +0.040 |
hair | +0.039 |
ggie | +0.039 |
Neg logit contributions | |
arp | -0.028 |
unst | -0.026 |
Joey | -0.026 |
Mill | -0.025 |
sorts | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
Joey | +0.073 |
sorts | +0.072 |
unst | +0.070 |
Mill | +0.070 |
arp | +0.070 |
Neg logit contributions | |
aids | -0.098 |
ggie | -0.085 |
wig | -0.084 |
song | -0.083 |
cheeks | -0.082 |
Token | talk |
Token ID | 1561 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
aids | +0.051 |
poems | +0.043 |
song | +0.043 |
ggie | +0.043 |
jokes | +0.043 |
Neg logit contributions | |
Joey | -0.047 |
arp | -0.047 |
unst | -0.047 |
sorts | -0.047 |
Mill | -0.046 |
Token | clown |
Token ID | 25573 |
Feature activation | -8.30e+00 |
Pos logit contributions | |
aids | +0.101 |
ggie | +0.085 |
uren | +0.083 |
anna | +0.077 |
ggy | +0.076 |
Neg logit contributions | |
barrel | -0.128 |
treasure | -0.120 |
treasures | -0.118 |
sorts | -0.117 |
lighthouse | -0.116 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
aids | +0.686 |
cheeks | +0.566 |
blond | +0.565 |
wig | +0.564 |
uren | +0.561 |
Neg logit contributions | |
sorts | -0.489 |
Joey | -0.445 |
aved | -0.445 |
arp | -0.439 |
'll | -0.426 |
Token | to |
Token ID | 284 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
aids | +0.234 |
uren | +0.206 |
ggie | +0.202 |
cheeks | +0.199 |
Dancing | +0.196 |
Neg logit contributions | |
Joey | -0.137 |
sorts | -0.127 |
Mill | -0.122 |
scaven | -0.121 |
Bobby | -0.120 |
Token | make |
Token ID | 787 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
aids | +0.099 |
ggie | +0.084 |
uren | +0.084 |
Dancing | +0.084 |
poems | +0.083 |
Neg logit contributions | |
sorts | -0.070 |
Joey | -0.068 |
aved | -0.065 |
Mill | -0.065 |
Suz | -0.064 |
Token | people |
Token ID | 661 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
aids | +0.017 |
wig | +0.014 |
song | +0.014 |
Dancing | +0.014 |
cheeks | +0.014 |
Neg logit contributions | |
sorts | -0.018 |
Joey | -0.017 |
arp | -0.017 |
unst | -0.017 |
Mill | -0.017 |
Token | laugh |
Token ID | 6487 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
aids | +0.052 |
uren | +0.046 |
ggie | +0.045 |
blond | +0.043 |
Dancing | +0.042 |
Neg logit contributions | |
sorts | -0.044 |
Joey | -0.042 |
arp | -0.041 |
unst | -0.041 |
Mill | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
aids | +0.410 |
wig | +0.350 |
ggie | +0.344 |
hair | +0.341 |
song | +0.341 |
Neg logit contributions | |
arp | -0.337 |
sorts | -0.335 |
unst | -0.332 |
Joey | -0.331 |
aved | -0.321 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
aids | +0.039 |
wig | +0.035 |
ggie | +0.035 |
song | +0.035 |
poems | +0.035 |
Neg logit contributions | |
Joey | -0.024 |
sorts | -0.022 |
Mill | -0.021 |
arp | -0.021 |
Bobby | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
arp | +0.008 |
Joey | +0.008 |
unst | +0.008 |
sorts | +0.008 |
aved | +0.008 |
Neg logit contributions | |
aids | -0.010 |
jokes | -0.008 |
song | -0.008 |
hair | -0.008 |
wig | -0.008 |
Token | One |
Token ID | 3198 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
sorts | +0.008 |
arp | +0.008 |
scaven | +0.007 |
hed | +0.007 |
deeper | +0.007 |
Neg logit contributions | |
aids | -0.012 |
cheeks | -0.012 |
throat | -0.011 |
wig | -0.011 |
hair | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
aids | +0.313 |
cheeks | +0.278 |
wig | +0.271 |
blond | +0.267 |
uren | +0.264 |
Neg logit contributions | |
sorts | -0.152 |
Joey | -0.134 |
arp | -0.126 |
cy | -0.121 |
deeper | -0.119 |