TOP ACTIVATIONS
MAX = 0.262

. Eleven , twelve , thirteen , fourteen , fifteen .
, eleven , twelve , thirteen , fourteen , fifteen ,
, eleven , twelve , thirteen , fourteen , fifteen ,
. He says " L adies and gentlemen , boys and
her hand . CR ASH ! The tower fell
They want to write about volcan oes . They
, seven , eight , nine , ten ! Ready or
. Lily and Ben think volcan oes are cool . They
The book has pictures of volcan oes . Vol can oes
, seven , eight , nine , ten !"
not understand . They like volcan oes . They think they
They said , " L adies and gentlemen , welcome to
Cars didn 't fly to volcan oes . <|endoftext|> L ily
, seven , eight , nine , ten . The slide
, seven , eight , nine , ten !"
big book with pictures of volcan oes . Vol can oes
. You should not like volcan oes . You should like
" Ten , nine , eight , seven ,
, seven , eight , nine , ten !"
, seven , eight , nine , ten !" Ben says

MIN ACTIVATIONS
MIN = -0.264

would heal soon . Wh isk ers was very happy to
After Mr . Wh isk ers was done with his
. The vet showed Wh isk ers the x - ray
flew down and scared Wh isk ers away .
. After Wh isk ers got better , he
a naughty cat named Wh isk ers . Wh isk ers
Ch ir py and Wh isk ers knew that poison was
Ch ir py and Wh isk ers became good friends ,
j olly cat named Wh isk ers . Wh isk ers
was heading straight towards Wh isk ers . She ran as
, and he and Wh isk ers played with the new
I 'm sorry , Wh isk ers . Let 's go
ink . Mr . Wh isk ers went to the store
Wh isk ers . Wh isk ers loved to play with
a smart cat named Wh isk ers . Wh isk ers
Wh isk ers . Wh isk ers loved to eat tuna
his paw again . Wh isk ers loved playing in the
. One day , Wh isk ers saw a can of
A little cat named Wh isk ers also wanted the ball
song . Wh isk ers wanted to get closer

INTERVAL 0.131 - 0.262
CONTAINS 0.250%

scared . The fireworks were not pretty anymore .
blue shirt . They make two teams with other kids .
smiled back and immediately the two of them were having a
was so fat that the rain couldn 't reach him .
ever !" The two children spent the rest of

INTERVAL -0.001 - 0.131
CONTAINS 50.146%

, but she stumbled on a rock and fell down .
They started to scoop more sauce from the bowl
check it out ," Ben said . " But be quiet
together ." After they drank juice , Tim my
" Really ? Did you ever lose your boats ?"

INTERVAL -0.132 - -0.001
CONTAINS 49.192%

. She had many colors and made pretty pictures of flowers
Ben and Mia thought about it . They liked their
told him about the loud sound and the barking dog .
Do you want to play with me ?" Carl looked at
. " There 's a dog ! It might bite us

INTERVAL -0.264 - -0.132
CONTAINS 0.412%

But she didn 't know how to mind her own business
did not like math . Max wanted to play and not
wanted to go on an adventure so he decided to climb
the book . They hugged each other . "
there was a dog named Max . Max loved to chew
Token.
Token ID13
Feature activation+5.53e-03

Pos logit contributions
ingu+0.067
 pistol+0.064
tto+0.061
ascal+0.061
 brand+0.061
Neg logit contributions
 Danger-0.060
 nine-0.055
 Ab-0.054
 thirteen-0.053
 arc-0.051
Token Eleven
Token ID37339
Feature activation+4.99e-02

Pos logit contributions
 nine+0.009
 thirteen+0.009
 Danger+0.009
 arc+0.008
+0.008
Neg logit contributions
ingu-0.008
 hockey-0.007
tto-0.007
 pistol-0.007
 brand-0.007
Token,
Token ID11
Feature activation+1.93e-02

Pos logit contributions
 Danger+0.064
 nine+0.060
+0.058
 Ab+0.056
 thirteen+0.055
Neg logit contributions
ingu-0.096
tto-0.089
affle-0.087
 pistol-0.087
ascal-0.087
Token twelve
Token ID14104
Feature activation+1.23e-01

Pos logit contributions
 Ab+0.025
 Danger+0.024
 Suz+0.024
 Jess+0.022
adies+0.022
Neg logit contributions
pron-0.032
 brand-0.031
 pistol-0.030
 hockey-0.030
 handsome-0.030
Token,
Token ID11
Feature activation+1.95e-02

Pos logit contributions
 Danger+0.185
+0.164
 Ab+0.161
 nine+0.154
 Sylv+0.146
Neg logit contributions
ingu-0.203
ravings-0.191
affle-0.186
 brand-0.183
 pistol-0.182
Token thirteen
Token ID28306
Feature activation+2.26e-01

Pos logit contributions
 Danger+0.024
 Ab+0.023
 Suz+0.022
 Jess+0.020
 Sylv+0.018
Neg logit contributions
pron-0.033
 brand-0.033
 hockey-0.032
 pistol-0.031
 handsome-0.031
Token,
Token ID11
Feature activation+1.96e-02

Pos logit contributions
 Danger+0.290
+0.261
 nine+0.255
 Ab+0.246
 arc+0.225
Neg logit contributions
ingu-0.450
tto-0.427
ravings-0.416
 pistol-0.414
ascal-0.413
Token fourteen
Token ID29167
Feature activation+1.80e-01

Pos logit contributions
 Danger+0.024
 Ab+0.020
+0.020
 Suz+0.018
 Jess+0.018
Neg logit contributions
ingu-0.037
 brand-0.035
 hockey-0.034
pron-0.034
 pistol-0.033
Token,
Token ID11
Feature activation+1.99e-02

Pos logit contributions
 Danger+0.282
+0.231
 nine+0.229
 Ab+0.221
 arc+0.209
Neg logit contributions
ingu-0.315
 pistol-0.290
 brand-0.289
ravings-0.276
tto-0.276
Token fifteen
Token ID17280
Feature activation+7.88e-02

Pos logit contributions
 Danger+0.026
 Ab+0.023
 Suz+0.022
 Jess+0.021
 Sylv+0.020
Neg logit contributions
ingu-0.034
 brand-0.033
 hockey-0.032
 pistol-0.031
 cowboy-0.030
Token.
Token ID13
Feature activation+7.12e-03

Pos logit contributions
 Danger+0.115
+0.100
 Ab+0.096
 nine+0.092
 arc+0.086
Neg logit contributions
ingu-0.144
ravings-0.131
tto-0.130
affle-0.130
 brand-0.130
Token,
Token ID11
Feature activation+1.21e-02

Pos logit contributions
 Danger+0.021
+0.018
 Ab+0.017
 Sylv+0.017
 arc+0.017
Neg logit contributions
ingu-0.021
ittens-0.020
ravings-0.020
affle-0.020
ishing-0.020
Token eleven
Token ID22216
Feature activation+1.10e-01

Pos logit contributions
 Danger+0.016
 arc+0.014
 Ab+0.013
 Flowers+0.013
 Sylv+0.013
Neg logit contributions
 hockey-0.019
 cowboy-0.018
 pistol-0.018
Years-0.018
 helmet-0.017
Token,
Token ID11
Feature activation+1.25e-02

Pos logit contributions
 Danger+0.180
+0.156
 nine+0.143
 thirteen+0.137
 Ab+0.134
Neg logit contributions
ingu-0.160
uddle-0.155
ravings-0.155
ittens-0.153
ishing-0.149
Token twelve
Token ID14104
Feature activation+1.20e-01

Pos logit contributions
 Danger+0.016
 Suz+0.013
 Ab+0.013
 Sylv+0.012
 Fourth+0.012
Neg logit contributions
 hockey-0.020
 pistol-0.018
 brand-0.018
 cowboy-0.018
ingu-0.017
Token,
Token ID11
Feature activation+1.27e-02

Pos logit contributions
 Danger+0.209
+0.170
 Ev+0.155
 Ab+0.154
 nine+0.154
Neg logit contributions
ingu-0.165
ravings-0.159
uddle-0.155
ishing-0.154
affle-0.154
Token thirteen
Token ID28306
Feature activation+2.25e-01

Pos logit contributions
 Danger+0.016
 Ab+0.013
 Suz+0.013
adies+0.012
 Ev+0.011
Neg logit contributions
 hockey-0.021
 brand-0.020
ingu-0.020
 pistol-0.020
zed-0.019
Token,
Token ID11
Feature activation+1.32e-02

Pos logit contributions
 Danger+0.309
+0.268
 nine+0.256
 Ab+0.249
 arc+0.233
Neg logit contributions
ingu-0.433
tto-0.415
ravings-0.402
affle-0.400
ascal-0.398
Token fourteen
Token ID29167
Feature activation+1.78e-01

Pos logit contributions
 Danger+0.017
+0.013
 Ab+0.012
 Suz+0.012
 arc+0.012
Neg logit contributions
ingu-0.026
ip-0.023
tto-0.023
zed-0.023
 brand-0.022
Token,
Token ID11
Feature activation+1.38e-02

Pos logit contributions
 Danger+0.287
 nine+0.227
+0.226
 Ab+0.219
 arc+0.211
Neg logit contributions
ingu-0.300
 pistol-0.276
 brand-0.276
tto-0.266
ravings-0.264
Token fifteen
Token ID17280
Feature activation+7.71e-02

Pos logit contributions
 Danger+0.017
 Ab+0.015
 Suz+0.014
 Jess+0.013
 arc+0.013
Neg logit contributions
ingu-0.024
 brand-0.022
 pistol-0.022
 hockey-0.022
 cowboy-0.021
Token,
Token ID11
Feature activation+1.41e-02

Pos logit contributions
 Danger+0.126
+0.103
 Ab+0.098
 nine+0.093
 Ev+0.092
Neg logit contributions
ingu-0.124
affle-0.115
ravings-0.115
iflower-0.112
 brand-0.112
Token,
Token ID11
Feature activation+1.27e-02

Pos logit contributions
 Danger+0.021
+0.019
 Ab+0.019
 nine+0.017
 Sylv+0.017
Neg logit contributions
ingu-0.022
ravings-0.021
ascal-0.020
 pistol-0.020
affle-0.020
Token eleven
Token ID22216
Feature activation+1.10e-01

Pos logit contributions
 Danger+0.019
 Suz+0.017
 Ab+0.016
+0.015
 arc+0.015
Neg logit contributions
Years-0.019
 hockey-0.018
 cowboy-0.017
 brand-0.016
Days-0.016
Token,
Token ID11
Feature activation+1.30e-02

Pos logit contributions
 Danger+0.153
+0.140
 nine+0.130
 Ab+0.130
 thirteen+0.122
Neg logit contributions
ingu-0.205
ravings-0.188
tto-0.186
 pistol-0.184
 brand-0.184
Token twelve
Token ID14104
Feature activation+1.20e-01

Pos logit contributions
 Danger+0.019
 Ab+0.017
 Suz+0.017
 Sylv+0.015
 Jess+0.014
Neg logit contributions
 brand-0.019
 hockey-0.018
Years-0.018
pron-0.017
zed-0.017
Token,
Token ID11
Feature activation+1.32e-02

Pos logit contributions
 Danger+0.188
+0.162
 Ab+0.156
 nine+0.145
 Sylv+0.142
Neg logit contributions
ingu-0.205
ravings-0.189
 brand-0.185
affle-0.182
 pistol-0.180
Token thirteen
Token ID28306
Feature activation+2.25e-01

Pos logit contributions
 Danger+0.019
 Ab+0.016
 Suz+0.016
+0.014
 Sylv+0.014
Neg logit contributions
 brand-0.020
 hockey-0.019
ingu-0.019
Years-0.019
zed-0.019
Token,
Token ID11
Feature activation+1.36e-02

Pos logit contributions
 Danger+0.303
+0.270
 nine+0.259
 Ab+0.254
 arc+0.234
Neg logit contributions
ingu-0.436
tto-0.413
ravings-0.403
ascal-0.400
affle-0.398
Token fourteen
Token ID29167
Feature activation+1.78e-01

Pos logit contributions
 Danger+0.018
+0.014
 Ab+0.014
 Suz+0.013
 Sylv+0.012
Neg logit contributions
ingu-0.026
 brand-0.023
zed-0.023
 hockey-0.022
udd-0.022
Token,
Token ID11
Feature activation+1.41e-02

Pos logit contributions
 Danger+0.283
+0.226
 Ab+0.223
 nine+0.216
adies+0.204
Neg logit contributions
ingu-0.308
 brand-0.284
 pistol-0.279
ravings-0.270
tto-0.267
Token fifteen
Token ID17280
Feature activation+7.64e-02

Pos logit contributions
 Danger+0.019
 Ab+0.018
 Suz+0.016
 Jess+0.016
 Sylv+0.016
Neg logit contributions
ingu-0.023
 brand-0.022
 hockey-0.021
 pistol-0.020
 handsome-0.019
Token,
Token ID11
Feature activation+1.43e-02

Pos logit contributions
 Danger+0.111
+0.097
 Ab+0.094
 nine+0.088
 Sylv+0.082
Neg logit contributions
ingu-0.139
ravings-0.127
 brand-0.126
affle-0.126
tto-0.125
Token.
Token ID13
Feature activation+8.54e-05

Pos logit contributions
 Ab+0.014
 thirteen+0.013
 nine+0.013
 Danger+0.013
+0.012
Neg logit contributions
 pistol-0.011
ingu-0.011
ravings-0.010
 hockey-0.010
 brand-0.010
Token He
Token ID679
Feature activation-3.98e-02

Pos logit contributions
+0.000
 nine+0.000
 Danger+0.000
 thirteen+0.000
 arc+0.000
Neg logit contributions
ingu-0.000
 pistol-0.000
ravings-0.000
tto-0.000
affle-0.000
Token says
Token ID1139
Feature activation+6.11e-02

Pos logit contributions
ingu+0.077
tto+0.074
 pistol+0.073
 brand+0.071
ravings+0.071
Neg logit contributions
 Danger-0.050
 nine-0.047
 Ab-0.046
-0.046
 thirteen-0.043
Token "
Token ID366
Feature activation-2.19e-02

Pos logit contributions
 Danger+0.094
 nine+0.092
+0.091
 thirteen+0.085
 arc+0.085
Neg logit contributions
ingu-0.101
tto-0.095
 pistol-0.094
ascal-0.092
 brand-0.091
TokenL
Token ID43
Feature activation+2.09e-02

Pos logit contributions
tto+0.035
ingu+0.035
Years+0.034
ascal+0.034
 pistol+0.033
Neg logit contributions
 nine-0.031
 Ab-0.029
 Danger-0.029
 thirteen-0.028
 Jen-0.028
Tokenadies
Token ID50192
Feature activation+2.21e-01

Pos logit contributions
+0.032
 nine+0.028
 arc+0.028
 thirteen+0.027
 Danger+0.027
Neg logit contributions
affle-0.036
tto-0.034
ingu-0.034
ascal-0.032
ogo-0.031
Token and
Token ID290
Feature activation-1.01e-02

Pos logit contributions
 Danger+0.318
+0.305
 nine+0.289
 thirteen+0.278
 Ab+0.273
Neg logit contributions
ingu-0.401
tto-0.373
ascal-0.372
ravings-0.370
 pistol-0.365
Token gentlemen
Token ID28527
Feature activation+1.05e-01

Pos logit contributions
ingu+0.015
 pistol+0.014
 hockey+0.013
 handsome+0.013
 brand+0.013
Neg logit contributions
 Danger-0.016
 arc-0.015
 Ab-0.015
 thirteen-0.014
 ago-0.014
Token,
Token ID11
Feature activation+1.73e-02

Pos logit contributions
 Danger+0.144
 Ab+0.135
 thirteen+0.131
 arc+0.129
 nine+0.128
Neg logit contributions
ingu-0.180
affle-0.159
tto-0.159
 pistol-0.157
ravings-0.156
Token boys
Token ID6510
Feature activation+1.29e-02

Pos logit contributions
 arc+0.021
 Danger+0.020
 thirteen+0.019
 ind+0.019
 Ab+0.018
Neg logit contributions
ingu-0.032
 pistol-0.029
 hockey-0.029
 cowboy-0.028
 brand-0.028
Token and
Token ID290
Feature activation-9.75e-03

Pos logit contributions
 Danger+0.019
 thirteen+0.017
 Ab+0.016
+0.016
 nine+0.016
Neg logit contributions
ingu-0.022
tto-0.020
 pistol-0.020
affle-0.020
ravings-0.020
Token her
Token ID607
Feature activation+3.42e-02

Pos logit contributions
ingu+0.034
tto+0.034
ravings+0.033
ascal+0.033
affle+0.033
Neg logit contributions
-0.016
 nine-0.016
 Danger-0.016
 Ab-0.014
 Jen-0.014
Token hand
Token ID1021
Feature activation+5.05e-03

Pos logit contributions
 Danger+0.056
 nine+0.054
+0.053
 thirteen+0.051
 Ab+0.050
Neg logit contributions
ingu-0.055
tto-0.052
 pistol-0.050
ravings-0.049
ascal-0.049
Token.
Token ID13
Feature activation+2.20e-02

Pos logit contributions
 Danger+0.008
 nine+0.007
 thirteen+0.007
 arc+0.006
+0.006
Neg logit contributions
ingu-0.009
tto-0.009
 pistol-0.009
 brand-0.008
pron-0.008
Token
Token ID198
Feature activation-1.75e-02

Pos logit contributions
 Danger+0.030
 thirteen+0.030
 nine+0.030
 arc+0.028
 paint+0.026
Neg logit contributions
ingu-0.038
tto-0.034
 brand-0.034
ravings-0.034
 hockey-0.033
Token
Token ID198
Feature activation-1.96e-02

Pos logit contributions
ingu+0.029
tto+0.028
ascal+0.027
ravings+0.026
 pistol+0.026
Neg logit contributions
 Danger-0.027
 nine-0.026
 thirteen-0.025
-0.025
 Ab-0.024
TokenCR
Token ID9419
Feature activation+2.21e-01

Pos logit contributions
tto+0.029
Years+0.028
ingu+0.027
scar+0.027
pron+0.027
Neg logit contributions
 thirteen-0.031
 Danger-0.031
 nine-0.031
 Ab-0.031
 arc-0.030
TokenASH
Token ID11211
Feature activation+1.66e-02

Pos logit contributions
 Danger+0.309
+0.270
 Ab+0.260
 thirteen+0.260
 volcan+0.249
Neg logit contributions
ingu-0.389
ravings-0.372
tto-0.367
 pistol-0.366
ascal-0.360
Token!
Token ID0
Feature activation-2.57e-02

Pos logit contributions
 Danger+0.026
 nine+0.025
+0.023
 thirteen+0.023
 Ab+0.023
Neg logit contributions
ingu-0.028
tto-0.027
ravings-0.026
 pistol-0.025
 brand-0.025
Token The
Token ID383
Feature activation+2.08e-02

Pos logit contributions
ingu+0.036
tto+0.035
 pistol+0.033
pron+0.033
 hockey+0.033
Neg logit contributions
 thirteen-0.041
 arc-0.039
 nine-0.038
 ind-0.035
adies-0.035
Token tower
Token ID10580
Feature activation+4.33e-02

Pos logit contributions
 Danger+0.034
+0.032
 nine+0.031
 Ab+0.030
 thirteen+0.029
Neg logit contributions
 pistol-0.034
ingu-0.033
pron-0.032
tto-0.031
affle-0.031
Token fell
Token ID3214
Feature activation+2.16e-02

Pos logit contributions
 Danger+0.072
 Ab+0.069
 nine+0.066
 Am+0.063
adies+0.062
Neg logit contributions
 pistol-0.060
zed-0.059
tto-0.059
 brand-0.059
uddle-0.059
Token They
Token ID1119
Feature activation-9.49e-03

Pos logit contributions
 Danger+0.005
 nine+0.005
+0.004
 thirteen+0.004
 Ab+0.004
Neg logit contributions
ingu-0.009
tto-0.008
ascal-0.008
 pistol-0.008
ravings-0.008
Token want
Token ID765
Feature activation+8.35e-02

Pos logit contributions
ingu+0.017
 pistol+0.016
affle+0.015
 cowboy+0.015
 armor+0.015
Neg logit contributions
 Danger-0.012
 Ab-0.012
 Jen-0.011
 arc-0.011
 nine-0.011
Token to
Token ID284
Feature activation+8.41e-03

Pos logit contributions
+0.153
 Danger+0.148
 thirteen+0.148
 nine+0.145
 arc+0.145
Neg logit contributions
ingu-0.106
 pistol-0.100
 brand-0.099
ravings-0.091
Years-0.089
Token write
Token ID3551
Feature activation-7.40e-02

Pos logit contributions
 thirteen+0.012
 nine+0.012
+0.012
 Ab+0.012
 Danger+0.011
Neg logit contributions
ingu-0.014
 pistol-0.013
 brand-0.012
pron-0.012
affle-0.012
Token about
Token ID546
Feature activation-5.96e-02

Pos logit contributions
ingu+0.130
 brand+0.125
 pistol+0.125
tto+0.120
pron+0.118
Neg logit contributions
 Danger-0.107
 nine-0.101
-0.099
 Ab-0.097
 thirteen-0.093
Token volcan
Token ID17516
Feature activation+2.20e-01

Pos logit contributions
 brand+0.087
 pistol+0.086
ingu+0.084
 hockey+0.076
 steak+0.075
Neg logit contributions
-0.093
 Danger-0.092
 thirteen-0.089
 nine-0.088
 arc-0.083
Tokenoes
Token ID3028
Feature activation+3.83e-02

Pos logit contributions
 Danger+0.181
 nine+0.175
+0.171
 Ab+0.153
 thirteen+0.147
Neg logit contributions
ingu-0.534
tto-0.512
ascal-0.504
ravings-0.496
 pistol-0.492
Token.
Token ID13
Feature activation+4.86e-03

Pos logit contributions
 Danger+0.058
 nine+0.053
 Ab+0.052
 thirteen+0.050
+0.050
Neg logit contributions
ingu-0.064
 pistol-0.063
tto-0.059
ascal-0.058
ravings-0.058
Token
Token ID198
Feature activation-1.42e-02

Pos logit contributions
 Danger+0.007
 nine+0.007
+0.006
 thirteen+0.006
 Ab+0.006
Neg logit contributions
ingu-0.009
tto-0.009
 pistol-0.008
ascal-0.008
ravings-0.008
Token
Token ID198
Feature activation-1.40e-02

Pos logit contributions
ingu+0.033
ravings+0.032
ascal+0.031
 pistol+0.031
tto+0.030
Neg logit contributions
-0.015
 Danger-0.014
 nine-0.013
 Ab-0.012
 Jen-0.012
TokenThey
Token ID2990
Feature activation-5.34e-03

Pos logit contributions
tto+0.023
ingu+0.023
pron+0.021
Years+0.021
scar+0.021
Neg logit contributions
 Danger-0.022
 nine-0.021
 Ab-0.021
 thirteen-0.021
 arc-0.020
Token,
Token ID11
Feature activation+2.22e-02

Pos logit contributions
 Danger+0.096
+0.086
 nine+0.086
 Ab+0.081
 thirteen+0.079
Neg logit contributions
ingu-0.136
tto-0.130
ravings-0.128
affle-0.127
ascal-0.127
Token seven
Token ID3598
Feature activation+1.64e-01

Pos logit contributions
 Danger+0.031
 Ab+0.026
otion+0.024
 Suz+0.024
 Ev+0.023
Neg logit contributions
 cowboy-0.036
 brand-0.035
 hockey-0.035
 pistol-0.034
 helmet-0.034
Token,
Token ID11
Feature activation+2.25e-02

Pos logit contributions
 Danger+0.213
 nine+0.190
+0.189
 Ab+0.180
 thirteen+0.177
Neg logit contributions
ingu-0.310
tto-0.296
ravings-0.291
affle-0.289
ascal-0.288
Token eight
Token ID3624
Feature activation+9.85e-02

Pos logit contributions
 Danger+0.028
 Ab+0.025
 arc+0.023
 Fourth+0.023
 Suz+0.023
Neg logit contributions
 cowboy-0.037
ingu-0.036
 pistol-0.036
 hockey-0.036
 brand-0.035
Token,
Token ID11
Feature activation+2.26e-02

Pos logit contributions
 Danger+0.146
 Ab+0.125
+0.125
 nine+0.123
 arc+0.121
Neg logit contributions
ingu-0.159
 pistol-0.151
ravings-0.150
affle-0.150
tto-0.148
Token nine
Token ID5193
Feature activation+2.20e-01

Pos logit contributions
 Danger+0.026
 Ab+0.021
 arc+0.020
 Suz+0.020
 Sylv+0.019
Neg logit contributions
Years-0.039
 cowboy-0.038
 hockey-0.038
 helmet-0.037
zed-0.037
Token,
Token ID11
Feature activation+2.24e-02

Pos logit contributions
 Danger+0.340
+0.301
 Ab+0.285
 nine+0.285
 arc+0.280
Neg logit contributions
ingu-0.347
ravings-0.331
affle-0.326
zed-0.319
ittens-0.318
Token ten
Token ID3478
Feature activation+1.84e-02

Pos logit contributions
 arc+0.030
 Danger+0.029
+0.027
 Ab+0.027
 Flowers+0.026
Neg logit contributions
Years-0.035
 cowboy-0.033
ingu-0.032
 hockey-0.032
Days-0.031
Token!
Token ID0
Feature activation-2.26e-02

Pos logit contributions
 Danger+0.026
+0.024
 Ab+0.022
 nine+0.022
 arc+0.022
Neg logit contributions
ingu-0.032
affle-0.030
tto-0.030
ravings-0.030
ascal-0.030
Token Ready
Token ID23432
Feature activation+1.40e-01

Pos logit contributions
ingu+0.038
 hockey+0.035
 Rudolph+0.034
Jeremy+0.032
 Jeremy+0.031
Neg logit contributions
 paint-0.030
 arc-0.029
 spr-0.027
 ostr-0.027
 ind-0.027
Token or
Token ID393
Feature activation+6.30e-02

Pos logit contributions
 thirteen+0.188
 Danger+0.185
 arc+0.180
+0.178
 nine+0.173
Neg logit contributions
ingu-0.227
tto-0.215
affle-0.209
zed-0.201
ravings-0.199
Token.
Token ID13
Feature activation+3.85e-03

Pos logit contributions
 Danger+0.132
 nine+0.128
 Ab+0.122
+0.122
 thirteen+0.114
Neg logit contributions
ingu-0.171
 pistol-0.165
tto-0.162
ravings-0.160
ascal-0.158
Token Lily
Token ID20037
Feature activation+3.66e-03

Pos logit contributions
 nine+0.005
 Danger+0.005
 thirteen+0.005
+0.005
 Ab+0.004
Neg logit contributions
ingu-0.007
 brand-0.007
ravings-0.007
 pistol-0.007
tto-0.006
Token and
Token ID290
Feature activation-9.58e-03

Pos logit contributions
 Danger+0.006
 Ab+0.005
 nine+0.005
 thirteen+0.005
 arc+0.005
Neg logit contributions
ingu-0.006
tto-0.006
 pistol-0.006
ravings-0.006
ascal-0.006
Token Ben
Token ID3932
Feature activation-8.81e-02

Pos logit contributions
tto+0.019
ingu+0.019
 brand+0.019
ravings+0.018
ascal+0.018
Neg logit contributions
 nine-0.011
 Danger-0.011
-0.011
 Jen-0.010
 Ab-0.010
Token think
Token ID892
Feature activation+6.65e-02

Pos logit contributions
 pistol+0.161
ingu+0.160
affle+0.145
 handsome+0.143
tto+0.143
Neg logit contributions
 Ab-0.108
 Danger-0.104
 Jen-0.102
 nine-0.101
 Sylv-0.094
Token volcan
Token ID17516
Feature activation+2.20e-01

Pos logit contributions
 Danger+0.095
 nine+0.095
+0.090
 thirteen+0.089
 arc+0.086
Neg logit contributions
ingu-0.106
 pistol-0.105
 brand-0.104
zed-0.100
tto-0.098
Tokenoes
Token ID3028
Feature activation+3.84e-02

Pos logit contributions
 Danger+0.204
 nine+0.201
+0.196
 Ab+0.177
 thirteen+0.175
Neg logit contributions
ingu-0.506
tto-0.484
ascal-0.475
 pistol-0.467
ravings-0.467
Token are
Token ID389
Feature activation+1.04e-01

Pos logit contributions
 nine+0.026
 Danger+0.026
 Ab+0.024
 thirteen+0.021
+0.021
Neg logit contributions
ingu-0.094
 pistol-0.092
tto-0.091
 brand-0.089
ascal-0.089
Token cool
Token ID3608
Feature activation-8.11e-03

Pos logit contributions
 Danger+0.180
 nine+0.174
+0.171
 Ab+0.165
 arc+0.160
Neg logit contributions
ingu-0.153
tto-0.143
 pistol-0.143
 brand-0.141
ascal-0.140
Token.
Token ID13
Feature activation+4.19e-03

Pos logit contributions
ingu+0.013
 pistol+0.013
ravings+0.012
 brand+0.012
ascal+0.012
Neg logit contributions
 Danger-0.013
 nine-0.012
 Ab-0.012
-0.011
 thirteen-0.011
Token They
Token ID1119
Feature activation-9.49e-03

Pos logit contributions
 Danger+0.005
 nine+0.005
+0.004
 thirteen+0.004
 Ab+0.004
Neg logit contributions
ingu-0.009
tto-0.008
ascal-0.008
 pistol-0.008
ravings-0.008
Token The
Token ID383
Feature activation+2.00e-02

Pos logit contributions
 nine+0.004
 Danger+0.004
+0.004
 thirteen+0.003
 Ab+0.003
Neg logit contributions
ingu-0.008
tto-0.008
 pistol-0.008
ravings-0.008
ascal-0.008
Token book
Token ID1492
Feature activation-9.66e-03

Pos logit contributions
 Danger+0.035
+0.034
 nine+0.034
 Ab+0.033
 thirteen+0.032
Neg logit contributions
ingu-0.029
tto-0.027
 pistol-0.027
 brand-0.026
ravings-0.026
Token has
Token ID468
Feature activation+6.20e-02

Pos logit contributions
ingu+0.018
 pistol+0.017
tto+0.017
 brand+0.017
ravings+0.016
Neg logit contributions
 Danger-0.013
 Ab-0.012
 nine-0.012
 thirteen-0.011
-0.011
Token pictures
Token ID5986
Feature activation+7.10e-02

Pos logit contributions
 Danger+0.108
 Ab+0.106
+0.105
 arc+0.105
 Suz+0.097
Neg logit contributions
ingu-0.082
 brand-0.079
 pistol-0.074
ravings-0.071
zed-0.068
Token of
Token ID286
Feature activation+9.84e-02

Pos logit contributions
 Danger+0.106
 Ab+0.102
 nine+0.097
 thirteen+0.092
+0.091
Neg logit contributions
ingu-0.115
 brand-0.114
 pistol-0.112
pron-0.105
ravings-0.105
Token volcan
Token ID17516
Feature activation+2.20e-01

Pos logit contributions
 Danger+0.144
+0.140
 nine+0.139
 thirteen+0.131
 Ab+0.129
Neg logit contributions
ingu-0.172
 pistol-0.161
 brand-0.158
tto-0.155
ascal-0.154
Tokenoes
Token ID3028
Feature activation+3.81e-02

Pos logit contributions
 Danger+0.188
+0.179
 nine+0.179
 Ab+0.159
 thirteen+0.151
Neg logit contributions
ingu-0.525
tto-0.502
ascal-0.494
ravings-0.488
affle-0.482
Token.
Token ID13
Feature activation+3.05e-03

Pos logit contributions
 Danger+0.054
 nine+0.052
 Ab+0.049
 thirteen+0.048
+0.047
Neg logit contributions
ingu-0.067
 pistol-0.065
tto-0.064
ravings-0.062
 brand-0.061
Token Vol
Token ID4709
Feature activation+1.07e-02

Pos logit contributions
 nine+0.003
 Danger+0.003
+0.003
 thirteen+0.003
 Ab+0.003
Neg logit contributions
ingu-0.006
ravings-0.006
tto-0.006
 pistol-0.006
 brand-0.006
Tokencan
Token ID5171
Feature activation+8.75e-02

Pos logit contributions
 nine+0.014
 Ab+0.013
 Danger+0.013
+0.013
 thirteen+0.012
Neg logit contributions
tto-0.020
ingu-0.020
ascal-0.019
scar-0.019
 pistol-0.019
Tokenoes
Token ID3028
Feature activation+3.81e-02

Pos logit contributions
 thirteen+0.124
 nine+0.120
 Danger+0.118
 arc+0.116
 Ab+0.112
Neg logit contributions
ingu-0.142
 pistol-0.130
tto-0.128
ravings-0.125
ascal-0.125
Token,
Token ID11
Feature activation+2.18e-02

Pos logit contributions
 Danger+0.094
 nine+0.084
+0.083
 Ab+0.076
 thirteen+0.076
Neg logit contributions
ingu-0.138
tto-0.133
ascal-0.131
affle-0.130
ravings-0.129
Token seven
Token ID3598
Feature activation+1.62e-01

Pos logit contributions
 Danger+0.028
 Ab+0.023
otion+0.021
 Sylv+0.021
 arc+0.021
Neg logit contributions
 brand-0.037
 pistol-0.036
pron-0.036
 hockey-0.036
 cowboy-0.036
Token,
Token ID11
Feature activation+2.18e-02

Pos logit contributions
 Danger+0.226
 nine+0.192
+0.191
 arc+0.182
 Ab+0.178
Neg logit contributions
ingu-0.293
affle-0.276
tto-0.276
ravings-0.276
ascal-0.273
Token eight
Token ID3624
Feature activation+1.00e-01

Pos logit contributions
 Danger+0.026
 Ab+0.022
adies+0.021
 Sylv+0.021
 arc+0.021
Neg logit contributions
 pistol-0.037
ingu-0.037
 brand-0.037
 hockey-0.037
pron-0.037
Token,
Token ID11
Feature activation+2.18e-02

Pos logit contributions
 Danger+0.148
+0.120
 arc+0.119
 nine+0.119
 Ab+0.118
Neg logit contributions
ingu-0.169
affle-0.159
ravings-0.159
ascal-0.159
 pistol-0.158
Token nine
Token ID5193
Feature activation+2.20e-01

Pos logit contributions
 Danger+0.027
 Ab+0.020
 Sylv+0.019
 arc+0.018
Warning+0.018
Neg logit contributions
Years-0.038
 brand-0.037
 hockey-0.036
ingu-0.035
pron-0.035
Token,
Token ID11
Feature activation+2.17e-02

Pos logit contributions
 Danger+0.340
+0.280
 nine+0.275
 arc+0.273
 Sylv+0.268
Neg logit contributions
ingu-0.350
ravings-0.337
affle-0.329
 brand-0.328
ascal-0.324
Token ten
Token ID3478
Feature activation+1.94e-02

Pos logit contributions
 Danger+0.028
 arc+0.025
 Sylv+0.024
 Ab+0.024
 Flowers+0.023
Neg logit contributions
Years-0.034
 hockey-0.033
 cowboy-0.032
 brand-0.031
ingu-0.031
Token!"
Token ID2474
Feature activation+3.93e-02

Pos logit contributions
 Danger+0.026
+0.022
 nine+0.022
 Ab+0.021
 arc+0.021
Neg logit contributions
ingu-0.035
affle-0.033
tto-0.033
ascal-0.033
ravings-0.033
Token
Token ID198
Feature activation-7.59e-03

Pos logit contributions
 Danger+0.060
 nine+0.060
 thirteen+0.057
+0.054
 arc+0.054
Neg logit contributions
ingu-0.066
tto-0.063
 pistol-0.062
 brand-0.061
ascal-0.059
Token
Token ID198
Feature activation-7.56e-03

Pos logit contributions
ingu+0.015
tto+0.015
ravings+0.014
ascal+0.014
 pistol+0.014
Neg logit contributions
 Danger-0.009
-0.009
 nine-0.009
 Ab-0.008
 thirteen-0.008
Token not
Token ID407
Feature activation-2.11e-02

Pos logit contributions
ingu+0.060
tto+0.057
ascal+0.055
 pistol+0.054
ravings+0.054
Neg logit contributions
 Danger-0.052
 nine-0.051
-0.050
 Ab-0.047
 thirteen-0.046
Token understand
Token ID1833
Feature activation-2.54e-03

Pos logit contributions
ingu+0.038
ascal+0.037
tto+0.036
 pistol+0.036
affle+0.035
Neg logit contributions
 nine-0.028
 Danger-0.028
 Ab-0.026
 thirteen-0.026
 arc-0.026
Token.
Token ID13
Feature activation+6.35e-03

Pos logit contributions
ingu+0.005
 pistol+0.004
ascal+0.004
tto+0.004
 brand+0.004
Neg logit contributions
 Danger-0.003
 nine-0.003
-0.003
 thirteen-0.003
 Ab-0.003
Token They
Token ID1119
Feature activation-1.03e-02

Pos logit contributions
 nine+0.008
 Danger+0.008
 thirteen+0.008
+0.008
 Ab+0.007
Neg logit contributions
ingu-0.011
ravings-0.011
ascal-0.011
 pistol-0.011
 brand-0.010
Token like
Token ID588
Feature activation+3.69e-02

Pos logit contributions
ingu+0.021
tto+0.021
 pistol+0.020
affle+0.020
ravings+0.019
Neg logit contributions
 Danger-0.011
 nine-0.011
 arc-0.010
 thirteen-0.010
 Ab-0.010
Token volcan
Token ID17516
Feature activation+2.20e-01

Pos logit contributions
+0.057
 Danger+0.053
 arc+0.051
 thirteen+0.051
 nine+0.051
Neg logit contributions
ingu-0.059
ascal-0.055
ravings-0.055
 brand-0.055
 pistol-0.052
Tokenoes
Token ID3028
Feature activation+3.60e-02

Pos logit contributions
 Danger+0.197
 nine+0.190
+0.190
 Ab+0.167
 thirteen+0.164
Neg logit contributions
ingu-0.514
tto-0.496
ascal-0.488
ravings-0.479
 pistol-0.475
Token.
Token ID13
Feature activation+6.67e-03

Pos logit contributions
 Danger+0.044
 nine+0.042
+0.040
 Ab+0.038
 thirteen+0.038
Neg logit contributions
ingu-0.072
tto-0.069
 pistol-0.068
ascal-0.067
ravings-0.067
Token They
Token ID1119
Feature activation-1.03e-02

Pos logit contributions
 nine+0.010
 thirteen+0.010
+0.009
 Danger+0.009
adies+0.009
Neg logit contributions
ingu-0.010
ravings-0.010
 brand-0.010
ascal-0.010
 pistol-0.009
Token think
Token ID892
Feature activation+6.76e-02

Pos logit contributions
ingu+0.019
 pistol+0.018
tto+0.018
affle+0.018
ravings+0.017
Neg logit contributions
 Danger-0.013
 nine-0.012
 arc-0.012
 Ab-0.012
 thirteen-0.011
Token they
Token ID484
Feature activation+1.78e-02

Pos logit contributions
 Danger+0.105
+0.104
 arc+0.096
 nine+0.095
 thirteen+0.095
Neg logit contributions
 brand-0.102
ingu-0.097
zed-0.092
 pistol-0.090
Years-0.088
Token They
Token ID1119
Feature activation-1.59e-02

Pos logit contributions
 nine+0.003
+0.003
 Danger+0.003
 thirteen+0.003
 arc+0.003
Neg logit contributions
ingu-0.005
ravings-0.005
tto-0.005
 pistol-0.005
 brand-0.005
Token said
Token ID531
Feature activation+1.10e-02

Pos logit contributions
ingu+0.026
tto+0.024
 pistol+0.023
ascal+0.023
pron+0.023
Neg logit contributions
 Danger-0.026
-0.024
 nine-0.024
 thirteen-0.023
 Ab-0.023
Token,
Token ID11
Feature activation+1.29e-02

Pos logit contributions
 Danger+0.015
 nine+0.014
+0.014
 thirteen+0.013
 Ab+0.013
Neg logit contributions
ingu-0.021
 pistol-0.019
 brand-0.019
tto-0.019
ascal-0.019
Token "
Token ID366
Feature activation-2.61e-02

Pos logit contributions
 Danger+0.021
 nine+0.021
+0.020
 thirteen+0.020
 Ab+0.019
Neg logit contributions
ingu-0.020
 pistol-0.018
 brand-0.018
pron-0.018
tto-0.018
TokenL
Token ID43
Feature activation+1.53e-02

Pos logit contributions
ingu+0.040
ascal+0.038
tto+0.037
Years+0.037
pron+0.037
Neg logit contributions
 Danger-0.040
 Ab-0.039
 Jen-0.037
 nine-0.037
 ago-0.036
Tokenadies
Token ID50192
Feature activation+2.20e-01

Pos logit contributions
+0.020
 Ab+0.020
 Danger+0.018
 Am+0.018
 nine+0.018
Neg logit contributions
ingu-0.029
affle-0.028
udd-0.027
tto-0.027
ascal-0.027
Token and
Token ID290
Feature activation-1.22e-02

Pos logit contributions
 Danger+0.310
+0.296
 nine+0.284
 thirteen+0.271
 Ab+0.266
Neg logit contributions
ingu-0.406
tto-0.378
ascal-0.375
ravings-0.374
 pistol-0.367
Token gentlemen
Token ID28527
Feature activation+1.01e-01

Pos logit contributions
ingu+0.020
 pistol+0.017
 brand+0.017
 handsome+0.017
 hockey+0.016
Neg logit contributions
 Danger-0.019
 Ab-0.017
 thirteen-0.017
 arc-0.017
 ago-0.016
Token,
Token ID11
Feature activation+1.32e-02

Pos logit contributions
 Danger+0.152
 thirteen+0.136
 Ab+0.136
 nine+0.129
+0.128
Neg logit contributions
ingu-0.164
ravings-0.142
affle-0.141
pron-0.141
tto-0.141
Token welcome
Token ID7062
Feature activation-1.50e-02

Pos logit contributions
 Danger+0.017
 thirteen+0.016
+0.016
 arc+0.016
 Ab+0.016
Neg logit contributions
ingu-0.024
 brand-0.021
 pistol-0.021
pron-0.020
ascal-0.020
Token to
Token ID284
Feature activation+4.25e-03

Pos logit contributions
ingu+0.025
ascal+0.023
 pistol+0.023
ravings+0.022
ishing+0.022
Neg logit contributions
 Danger-0.023
 thirteen-0.022
-0.021
 nine-0.020
 arc-0.020
Token Cars
Token ID25277
Feature activation+9.20e-02

Pos logit contributions
 Danger+0.010
 nine+0.010
 thirteen+0.010
+0.010
 Ab+0.009
Neg logit contributions
ingu-0.016
ascal-0.015
tto-0.015
 brand-0.015
ravings-0.015
Token didn
Token ID1422
Feature activation-2.74e-02

Pos logit contributions
 Danger+0.117
 nine+0.114
+0.107
 Ab+0.106
 thirteen+0.102
Neg logit contributions
ingu-0.178
tto-0.170
 pistol-0.168
 brand-0.164
ascal-0.162
Token't
Token ID470
Feature activation+9.61e-02

Pos logit contributions
ingu+0.057
tto+0.057
 pistol+0.056
 brand+0.055
Years+0.053
Neg logit contributions
 nine-0.028
 Ab-0.027
 Danger-0.026
 thirteen-0.025
 arc-0.024
Token fly
Token ID6129
Feature activation+4.24e-02

Pos logit contributions
 Danger+0.118
 nine+0.115
+0.114
 Ab+0.106
 thirteen+0.105
Neg logit contributions
ingu-0.190
tto-0.180
 pistol-0.179
ascal-0.176
ravings-0.174
Token to
Token ID284
Feature activation+1.03e-02

Pos logit contributions
 Danger+0.050
 nine+0.049
+0.048
 thirteen+0.044
 Ab+0.044
Neg logit contributions
ingu-0.088
tto-0.085
ascal-0.082
ravings-0.081
affle-0.081
Token volcan
Token ID17516
Feature activation+2.19e-01

Pos logit contributions
 Danger+0.013
+0.013
 nine+0.013
 thirteen+0.012
 Ab+0.012
Neg logit contributions
ingu-0.019
 pistol-0.018
tto-0.018
 brand-0.018
ascal-0.018
Tokenoes
Token ID3028
Feature activation+3.75e-02

Pos logit contributions
 Danger+0.146
 nine+0.143
+0.133
 thirteen+0.114
 Ab+0.113
Neg logit contributions
ingu-0.560
tto-0.548
 pistol-0.530
ascal-0.529
ravings-0.528
Token.
Token ID13
Feature activation+9.73e-03

Pos logit contributions
 Danger+0.045
 nine+0.042
+0.040
 Ab+0.039
 thirteen+0.039
Neg logit contributions
ingu-0.075
 pistol-0.072
tto-0.072
ascal-0.070
 brand-0.070
Token<|endoftext|>
Token ID50256
Feature activation+1.17e-03

Pos logit contributions
 nine+0.012
 Danger+0.012
+0.011
 thirteen+0.011
 arc+0.010
Neg logit contributions
ingu-0.019
ascal-0.018
ravings-0.017
 brand-0.017
tto-0.017
TokenL
Token ID43
Feature activation+2.40e-02

Pos logit contributions
 Danger+0.001
 nine+0.001
+0.001
 thirteen+0.001
 Ab+0.001
Neg logit contributions
ingu-0.002
tto-0.002
ascal-0.002
 pistol-0.002
ravings-0.002
Tokenily
Token ID813
Feature activation+8.70e-02

Pos logit contributions
 Danger+0.027
+0.026
 nine+0.026
 thirteen+0.024
 Ab+0.023
Neg logit contributions
ingu-0.052
tto-0.049
ascal-0.047
affle-0.047
ravings-0.046
Token,
Token ID11
Feature activation+2.15e-02

Pos logit contributions
 Danger+0.110
+0.093
 Ab+0.087
 nine+0.086
 arc+0.084
Neg logit contributions
ingu-0.112
affle-0.108
ravings-0.107
ittens-0.106
tto-0.105
Token seven
Token ID3598
Feature activation+1.62e-01

Pos logit contributions
 Danger+0.031
 Ab+0.026
 Suz+0.026
otion+0.025
 Jess+0.024
Neg logit contributions
 hockey-0.032
 cowboy-0.032
pron-0.031
 brand-0.031
 pistol-0.030
Token,
Token ID11
Feature activation+2.15e-02

Pos logit contributions
 Danger+0.260
+0.219
 Ab+0.209
 Ev+0.207
 arc+0.206
Neg logit contributions
ingu-0.243
ravings-0.233
affle-0.229
ittens-0.226
 hockey-0.223
Token eight
Token ID3624
Feature activation+9.87e-02

Pos logit contributions
 Danger+0.026
 Ab+0.023
 Suz+0.022
adies+0.022
 arc+0.021
Neg logit contributions
 hockey-0.035
 pistol-0.034
 cowboy-0.034
ingu-0.033
pron-0.033
Token,
Token ID11
Feature activation+2.14e-02

Pos logit contributions
 Danger+0.167
 Ab+0.134
 Sylv+0.134
+0.134
 arc+0.132
Neg logit contributions
ingu-0.135
 hockey-0.135
 pistol-0.131
ravings-0.130
ittens-0.129
Token nine
Token ID5193
Feature activation+2.19e-01

Pos logit contributions
 Danger+0.023
 Ab+0.017
 Suz+0.017
 Sylv+0.016
 Flowers+0.016
Neg logit contributions
 hockey-0.039
Years-0.039
 cowboy-0.037
pron-0.036
 pistol-0.036
Token,
Token ID11
Feature activation+2.14e-02

Pos logit contributions
 Danger+0.390
+0.327
 Sylv+0.313
 arc+0.310
 Ab+0.309
Neg logit contributions
ingu-0.283
ravings-0.276
ittens-0.274
affle-0.262
 hockey-0.261
Token ten
Token ID3478
Feature activation+1.79e-02

Pos logit contributions
 arc+0.028
 Danger+0.027
+0.025
 Flowers+0.025
 Ab+0.024
Neg logit contributions
Years-0.033
 cowboy-0.031
 hockey-0.031
ingu-0.030
 pistol-0.029
Token.
Token ID13
Feature activation+9.12e-03

Pos logit contributions
 Danger+0.028
+0.023
 Ab+0.022
 arc+0.022
 Sylv+0.022
Neg logit contributions
ingu-0.028
ravings-0.027
affle-0.027
tto-0.026
ittens-0.026
Token The
Token ID383
Feature activation+2.40e-02

Pos logit contributions
 ostr+0.011
 spr+0.011
 gasp+0.011
 Ab+0.011
 arc+0.010
Neg logit contributions
ingu-0.014
 hockey-0.013
 Rudolph-0.012
 cowboy-0.011
 pistol-0.011
Token slide
Token ID10649
Feature activation+6.76e-02

Pos logit contributions
 Danger+0.036
+0.032
adies+0.029
 Ab+0.029
 Ev+0.028
Neg logit contributions
ingu-0.040
affle-0.039
ravings-0.039
 brand-0.039
pron-0.038
Token,
Token ID11
Feature activation+3.94e-02

Pos logit contributions
 Danger+0.146
 Ab+0.121
+0.120
 nine+0.117
 Ev+0.114
Neg logit contributions
ingu-0.188
tto-0.179
ravings-0.177
affle-0.177
 pistol-0.176
Token seven
Token ID3598
Feature activation+1.73e-01

Pos logit contributions
 Danger+0.059
 nine+0.049
 arc+0.048
adies+0.047
 Ab+0.046
Neg logit contributions
 pistol-0.065
 brand-0.062
pron-0.061
 hockey-0.061
ingu-0.059
Token,
Token ID11
Feature activation+2.32e-02

Pos logit contributions
 Danger+0.239
+0.202
 nine+0.200
 Ab+0.196
 arc+0.194
Neg logit contributions
ingu-0.313
tto-0.301
affle-0.292
 brand-0.289
 pistol-0.289
Token eight
Token ID3624
Feature activation+1.04e-01

Pos logit contributions
 Danger+0.030
 arc+0.026
adies+0.025
 Ab+0.025
 Ev+0.023
Neg logit contributions
 pistol-0.039
 hockey-0.038
 brand-0.037
pron-0.037
ingu-0.037
Token,
Token ID11
Feature activation+1.83e-02

Pos logit contributions
 Danger+0.153
 Ab+0.129
 arc+0.125
+0.125
 nine+0.124
Neg logit contributions
ingu-0.172
tto-0.166
 pistol-0.165
affle-0.163
ravings-0.161
Token nine
Token ID5193
Feature activation+2.19e-01

Pos logit contributions
 Danger+0.021
 arc+0.018
 Ab+0.016
 Flowers+0.015
Warning+0.015
Neg logit contributions
 hockey-0.031
 pistol-0.031
 helmet-0.031
pron-0.030
ingu-0.030
Token,
Token ID11
Feature activation+1.58e-02

Pos logit contributions
 Danger+0.344
+0.290
 Ab+0.283
 arc+0.280
 nine+0.275
Neg logit contributions
ingu-0.333
ravings-0.315
zed-0.311
tto-0.308
 brand-0.307
Token ten
Token ID3478
Feature activation+1.65e-02

Pos logit contributions
 Danger+0.020
 arc+0.020
 Flowers+0.017
 ind+0.016
Warning+0.016
Neg logit contributions
 hockey-0.024
 pistol-0.023
Years-0.023
ingu-0.023
 helmet-0.023
Token!"
Token ID2474
Feature activation+3.60e-02

Pos logit contributions
 Danger+0.024
+0.022
 Ab+0.021
 arc+0.021
 nine+0.020
Neg logit contributions
ingu-0.027
tto-0.026
affle-0.025
ravings-0.025
 pistol-0.025
Token
Token ID198
Feature activation-2.76e-02

Pos logit contributions
 arc+0.054
 Danger+0.053
 thirteen+0.052
 nine+0.048
adies+0.047
Neg logit contributions
ingu-0.049
 hockey-0.048
tto-0.048
zed-0.046
 Jeremy-0.045
Token
Token ID198
Feature activation-2.99e-02

Pos logit contributions
tto+0.041
ingu+0.040
ascal+0.036
scar+0.036
Years+0.036
Neg logit contributions
 Danger-0.045
 nine-0.045
 thirteen-0.045
 arc-0.043
 Ab-0.041
Token big
Token ID1263
Feature activation-2.07e-02

Pos logit contributions
 Danger+0.006
 nine+0.006
+0.006
 paint+0.006
 Ab+0.006
Neg logit contributions
ingu-0.007
ascal-0.007
tto-0.006
ravings-0.006
zed-0.006
Token book
Token ID1492
Feature activation-1.03e-02

Pos logit contributions
ingu+0.033
 pistol+0.032
tto+0.031
 brand+0.031
ravings+0.030
Neg logit contributions
 Danger-0.034
 nine-0.032
-0.032
 Ab-0.031
 thirteen-0.030
Token with
Token ID351
Feature activation-1.39e-02

Pos logit contributions
ingu+0.016
tto+0.016
 brand+0.016
 pistol+0.015
pron+0.015
Neg logit contributions
 Danger-0.016
 Ab-0.016
 nine-0.015
 thirteen-0.015
-0.014
Token pictures
Token ID5986
Feature activation+7.04e-02

Pos logit contributions
ingu+0.021
 brand+0.021
 pistol+0.020
ravings+0.017
 hockey+0.017
Neg logit contributions
 Danger-0.023
-0.022
 arc-0.021
 Ab-0.021
 nine-0.021
Token of
Token ID286
Feature activation+9.90e-02

Pos logit contributions
 Danger+0.120
 Ab+0.116
 thirteen+0.108
 nine+0.107
+0.104
Neg logit contributions
 brand-0.096
 pistol-0.095
ingu-0.095
pron-0.089
ravings-0.087
Token volcan
Token ID17516
Feature activation+2.19e-01

Pos logit contributions
 Danger+0.147
+0.143
 nine+0.140
 thirteen+0.134
 Ab+0.133
Neg logit contributions
ingu-0.169
 pistol-0.159
 brand-0.158
ravings-0.147
ascal-0.147
Tokenoes
Token ID3028
Feature activation+3.77e-02

Pos logit contributions
 Danger+0.190
+0.181
 nine+0.180
 Ab+0.157
 thirteen+0.152
Neg logit contributions
ingu-0.521
tto-0.500
ascal-0.491
ravings-0.484
affle-0.479
Token.
Token ID13
Feature activation+7.16e-03

Pos logit contributions
 Danger+0.060
 nine+0.057
 thirteen+0.054
 Ab+0.053
+0.052
Neg logit contributions
 pistol-0.060
ingu-0.059
tto-0.056
 brand-0.054
ravings-0.054
Token Vol
Token ID4709
Feature activation+9.76e-03

Pos logit contributions
 Danger+0.008
 nine+0.008
+0.008
 thirteen+0.008
 arc+0.007
Neg logit contributions
ingu-0.014
tto-0.013
ravings-0.013
 brand-0.013
 pistol-0.013
Tokencan
Token ID5171
Feature activation+8.71e-02

Pos logit contributions
 nine+0.013
 Ab+0.012
 Danger+0.012
+0.012
 thirteen+0.011
Neg logit contributions
tto-0.018
ingu-0.018
ascal-0.017
scar-0.017
 pistol-0.017
Tokenoes
Token ID3028
Feature activation+3.76e-02

Pos logit contributions
 thirteen+0.127
 nine+0.123
 Danger+0.121
 arc+0.118
 Ab+0.112
Neg logit contributions
ingu-0.135
 pistol-0.124
tto-0.122
ables-0.118
ravings-0.118
Token.
Token ID13
Feature activation+5.29e-03

Pos logit contributions
 Danger+0.049
 nine+0.046
 Ab+0.045
 thirteen+0.043
+0.043
Neg logit contributions
ingu-0.066
 pistol-0.065
tto-0.064
ravings-0.063
ascal-0.062
Token You
Token ID921
Feature activation+5.88e-02

Pos logit contributions
 nine+0.008
 arc+0.007
 Danger+0.007
 thirteen+0.007
 Ab+0.007
Neg logit contributions
ascal-0.008
ingu-0.008
 pistol-0.008
ravings-0.007
 Rudolph-0.007
Token should
Token ID815
Feature activation+2.78e-02

Pos logit contributions
 Ab+0.077
 nine+0.073
 arc+0.072
 Danger+0.072
 thirteen+0.071
Neg logit contributions
ingu-0.109
 pistol-0.105
tto-0.102
ascal-0.100
affle-0.095
Token not
Token ID407
Feature activation-2.19e-02

Pos logit contributions
 Danger+0.039
 nine+0.037
 thirteen+0.036
 Ab+0.035
 arc+0.035
Neg logit contributions
ingu-0.050
tto-0.049
 pistol-0.046
ascal-0.045
affle-0.045
Token like
Token ID588
Feature activation+3.60e-02

Pos logit contributions
ingu+0.037
 pistol+0.036
tto+0.035
ascal+0.034
ravings+0.034
Neg logit contributions
 nine-0.029
adies-0.029
 Ab-0.028
 thirteen-0.028
 Danger-0.027
Token volcan
Token ID17516
Feature activation+2.18e-01

Pos logit contributions
+0.059
 Danger+0.056
 arc+0.056
 nine+0.054
 thirteen+0.054
Neg logit contributions
ingu-0.049
 brand-0.048
 pistol-0.048
ravings-0.047
ascal-0.046
Tokenoes
Token ID3028
Feature activation+3.49e-02

Pos logit contributions
 Danger+0.200
+0.198
 nine+0.195
 Ab+0.179
 thirteen+0.168
Neg logit contributions
ingu-0.506
ascal-0.482
tto-0.480
ravings-0.470
affle-0.460
Token.
Token ID13
Feature activation+5.53e-03

Pos logit contributions
 Danger+0.049
 nine+0.046
 Ab+0.046
 thirteen+0.043
 arc+0.042
Neg logit contributions
 pistol-0.061
ingu-0.061
ravings-0.058
ascal-0.058
tto-0.058
Token You
Token ID921
Feature activation+5.92e-02

Pos logit contributions
 nine+0.008
 arc+0.008
 thirteen+0.008
 closer+0.007
 bud+0.007
Neg logit contributions
ascal-0.009
ingu-0.008
ravings-0.007
tto-0.007
 pistol-0.007
Token should
Token ID815
Feature activation+2.80e-02

Pos logit contributions
 arc+0.083
 Ab+0.083
 nine+0.081
 thirteen+0.080
 Danger+0.079
Neg logit contributions
ingu-0.104
 pistol-0.099
tto-0.098
ascal-0.096
affle-0.090
Token like
Token ID588
Feature activation+3.63e-02

Pos logit contributions
 Danger+0.038
 nine+0.036
 thirteen+0.035
 arc+0.035
 Ab+0.034
Neg logit contributions
ingu-0.051
tto-0.050
 pistol-0.047
ascal-0.047
affle-0.047
Token
Token ID198
Feature activation-1.63e-02

Pos logit contributions
 nine+0.004
 Danger+0.004
+0.004
 thirteen+0.003
 arc+0.003
Neg logit contributions
ingu-0.006
tto-0.005
 brand-0.005
 pistol-0.005
ravings-0.005
Token
Token ID198
Feature activation-1.61e-02

Pos logit contributions
ingu+0.031
tto+0.029
ascal+0.028
 pistol+0.028
ravings+0.028
Neg logit contributions
 Danger-0.022
 nine-0.022
-0.021
 Ab-0.020
 thirteen-0.020
Token"
Token ID1
Feature activation+6.38e-02

Pos logit contributions
tto+0.023
Years+0.022
ingu+0.022
Days+0.021
pron+0.021
Neg logit contributions
 Ab-0.028
 Danger-0.027
 thirteen-0.025
 arc-0.025
 nine-0.024
TokenTen
Token ID24893
Feature activation+6.83e-02

Pos logit contributions
 Danger+0.095
 Ab+0.091
+0.088
 ago+0.087
 nine+0.086
Neg logit contributions
Years-0.103
ingu-0.100
tto-0.099
pron-0.095
ascal-0.094
Token,
Token ID11
Feature activation+2.03e-02

Pos logit contributions
 Danger+0.086
+0.078
 Ab+0.073
 nine+0.073
 thirteen+0.068
Neg logit contributions
ingu-0.134
tto-0.126
affle-0.125
ascal-0.123
 brand-0.123
Token nine
Token ID5193
Feature activation+2.18e-01

Pos logit contributions
 Danger+0.025
 Ab+0.022
 arc+0.021
+0.020
 Those+0.020
Neg logit contributions
 cowboy-0.035
ingu-0.034
 brand-0.034
 armor-0.034
 pistol-0.034
Token,
Token ID11
Feature activation+2.04e-02

Pos logit contributions
 Danger+0.342
+0.294
 Ab+0.291
 Sylv+0.278
 arc+0.269
Neg logit contributions
ingu-0.355
 brand-0.333
 pistol-0.331
ravings-0.326
affle-0.325
Token eight
Token ID3624
Feature activation+9.82e-02

Pos logit contributions
 arc+0.025
 Danger+0.024
 Ab+0.023
+0.023
bird+0.022
Neg logit contributions
 cowboy-0.034
ingu-0.034
Years-0.032
 brand-0.031
 pistol-0.031
Token,
Token ID11
Feature activation+2.04e-02

Pos logit contributions
 Danger+0.142
 Ab+0.120
+0.119
 nine+0.114
 Sylv+0.112
Neg logit contributions
ingu-0.172
 pistol-0.163
tto-0.160
affle-0.158
ravings-0.158
Token seven
Token ID3598
Feature activation+1.63e-01

Pos logit contributions
 Danger+0.022
 Ab+0.018
 arc+0.017
+0.017
 Sylv+0.017
Neg logit contributions
 cowboy-0.039
ingu-0.038
Years-0.038
 helmet-0.037
 brand-0.036
Token,
Token ID11
Feature activation+2.03e-02

Pos logit contributions
 Danger+0.227
+0.198
 Ab+0.193
 nine+0.188
 arc+0.180
Neg logit contributions
ingu-0.298
tto-0.277
 pistol-0.273
ravings-0.273
affle-0.272
Token,
Token ID11
Feature activation+2.02e-02

Pos logit contributions
 Danger+0.096
+0.085
 Ab+0.082
 nine+0.082
 thirteen+0.077
Neg logit contributions
ingu-0.131
tto-0.122
affle-0.121
 brand-0.121
 pistol-0.121
Token seven
Token ID3598
Feature activation+1.62e-01

Pos logit contributions
 Danger+0.030
 Ab+0.027
 Suz+0.025
otion+0.024
 Sylv+0.023
Neg logit contributions
 cowboy-0.030
 hockey-0.030
 brand-0.029
pron-0.029
Years-0.029
Token,
Token ID11
Feature activation+2.03e-02

Pos logit contributions
 Danger+0.229
+0.199
 Ab+0.197
 nine+0.187
 thirteen+0.181
Neg logit contributions
ingu-0.287
ravings-0.264
 brand-0.262
affle-0.262
 pistol-0.260
Token eight
Token ID3624
Feature activation+9.88e-02

Pos logit contributions
 Danger+0.025
 Ab+0.025
 Suz+0.023
 Sylv+0.022
 Jen+0.021
Neg logit contributions
 cowboy-0.032
 hockey-0.032
ingu-0.032
pron-0.031
 pistol-0.031
Token,
Token ID11
Feature activation+2.03e-02

Pos logit contributions
 Danger+0.155
 Ab+0.133
+0.129
 Sylv+0.126
 arc+0.123
Neg logit contributions
ingu-0.155
 pistol-0.144
 hockey-0.143
affle-0.141
ravings-0.141
Token nine
Token ID5193
Feature activation+2.18e-01

Pos logit contributions
 Danger+0.023
 Ab+0.018
 Suz+0.017
 Sylv+0.016
 arc+0.016
Neg logit contributions
Years-0.038
 hockey-0.036
ingu-0.036
 cowboy-0.035
pron-0.035
Token,
Token ID11
Feature activation+2.04e-02

Pos logit contributions
 Danger+0.354
+0.308
 Ab+0.301
 Sylv+0.288
 arc+0.282
Neg logit contributions
ingu-0.330
ravings-0.305
 brand-0.300
affle-0.299
ittens-0.297
Token ten
Token ID3478
Feature activation+1.78e-02

Pos logit contributions
 Danger+0.026
 arc+0.025
+0.024
 Ab+0.023
 Flowers+0.023
Neg logit contributions
Years-0.033
 cowboy-0.032
 hockey-0.031
ingu-0.031
 pistol-0.029
Token!"
Token ID2474
Feature activation+3.64e-02

Pos logit contributions
 Danger+0.024
+0.022
 Ab+0.021
 nine+0.020
 arc+0.019
Neg logit contributions
ingu-0.032
affle-0.030
ravings-0.030
 pistol-0.029
tto-0.029
Token
Token ID198
Feature activation-1.39e-02

Pos logit contributions
 Danger+0.052
+0.049
 nine+0.049
 thirteen+0.047
 arc+0.046
Neg logit contributions
ingu-0.066
tto-0.062
 pistol-0.060
ravings-0.059
ascal-0.059
Token
Token ID198
Feature activation-1.41e-02

Pos logit contributions
ingu+0.030
tto+0.029
 pistol+0.028
ravings+0.028
ascal+0.028
Neg logit contributions
 nine-0.015
 Danger-0.015
-0.015
 Jen-0.014
 Ab-0.013
Token,
Token ID11
Feature activation+1.84e-02

Pos logit contributions
 Danger+0.096
+0.081
 Ab+0.080
 nine+0.080
 Jen+0.073
Neg logit contributions
ingu-0.129
tto-0.122
affle-0.121
ascal-0.120
 pistol-0.120
Token seven
Token ID3598
Feature activation+1.61e-01

Pos logit contributions
 Danger+0.026
 Ab+0.024
 Suz+0.022
 Sylv+0.021
otion+0.020
Neg logit contributions
 hockey-0.029
 cowboy-0.029
pron-0.027
 pistol-0.027
 brand-0.026
Token,
Token ID11
Feature activation+1.86e-02

Pos logit contributions
 Danger+0.234
 Ab+0.198
+0.194
 nine+0.188
 arc+0.182
Neg logit contributions
ingu-0.280
ravings-0.258
affle-0.257
 pistol-0.255
tto-0.254
Token eight
Token ID3624
Feature activation+9.71e-02

Pos logit contributions
 Danger+0.022
 Ab+0.022
 Suz+0.020
 Sylv+0.019
 Jen+0.019
Neg logit contributions
 hockey-0.031
 cowboy-0.030
ingu-0.030
 pistol-0.030
pron-0.029
Token,
Token ID11
Feature activation+1.85e-02

Pos logit contributions
 Danger+0.156
 Ab+0.132
 Sylv+0.126
+0.124
 Jen+0.121
Neg logit contributions
ingu-0.149
 hockey-0.143
 pistol-0.141
affle-0.138
ravings-0.136
Token nine
Token ID5193
Feature activation+2.18e-01

Pos logit contributions
 Danger+0.020
 Ab+0.018
 Suz+0.016
 Sylv+0.016
 Jess+0.014
Neg logit contributions
 hockey-0.033
Years-0.032
 cowboy-0.031
ingu-0.030
 pistol-0.030
Token,
Token ID11
Feature activation+1.88e-02

Pos logit contributions
 Danger+0.369
 Ab+0.306
+0.305
 Sylv+0.297
 arc+0.280
Neg logit contributions
ingu-0.317
ravings-0.292
affle-0.291
 hockey-0.288
 pistol-0.286
Token ten
Token ID3478
Feature activation+1.77e-02

Pos logit contributions
 Danger+0.023
 arc+0.022
 Ab+0.022
+0.021
 Sylv+0.021
Neg logit contributions
Years-0.030
 hockey-0.029
 cowboy-0.028
ingu-0.028
 pistol-0.027
Token!"
Token ID2474
Feature activation+3.34e-02

Pos logit contributions
 Danger+0.025
 Ab+0.021
+0.020
 Sylv+0.020
 arc+0.019
Neg logit contributions
ingu-0.031
affle-0.029
tto-0.029
ravings-0.029
 pistol-0.029
Token Ben
Token ID3932
Feature activation-8.63e-02

Pos logit contributions
 Danger+0.059
 thirteen+0.057
 nine+0.056
 arc+0.056
 ind+0.053
Neg logit contributions
ingu-0.048
 pistol-0.044
 hockey-0.043
tto-0.040
 brand-0.040
Token says
Token ID1139
Feature activation+6.18e-02

Pos logit contributions
ingu+0.119
 hockey+0.118
 pistol+0.115
affle+0.113
 tricks+0.113
Neg logit contributions
 Danger-0.130
 Ab-0.124
adies-0.117
 ago-0.116
 nine-0.114
Token would
Token ID561
Feature activation-7.30e-02

Pos logit contributions
ingu+0.143
tto+0.137
 pistol+0.132
ascal+0.130
ravings+0.130
Neg logit contributions
 Danger-0.130
 nine-0.129
-0.123
 thirteen-0.118
 Ab-0.117
Token heal
Token ID12035
Feature activation-1.16e-01

Pos logit contributions
ingu+0.138
tto+0.133
 pistol+0.132
 brand+0.130
ravings+0.126
Neg logit contributions
 Danger-0.094
 nine-0.092
 thirteen-0.083
 arc-0.082
 Ab-0.082
Token soon
Token ID2582
Feature activation+3.25e-02

Pos logit contributions
ingu+0.227
tto+0.220
ravings+0.212
ascal+0.210
affle+0.209
Neg logit contributions
-0.146
 nine-0.144
 Danger-0.143
 Ab-0.130
 thirteen-0.127
Token.
Token ID13
Feature activation-4.14e-03

Pos logit contributions
 Danger+0.039
 nine+0.038
+0.036
 Ab+0.034
 thirteen+0.034
Neg logit contributions
ingu-0.066
tto-0.064
 pistol-0.062
ravings-0.062
ascal-0.061
Token Wh
Token ID854
Feature activation-2.95e-02

Pos logit contributions
ingu+0.008
tto+0.008
 pistol+0.007
ascal+0.007
ravings+0.007
Neg logit contributions
 Danger-0.005
 nine-0.005
-0.005
 thirteen-0.005
 Ab-0.005
Tokenisk
Token ID1984
Feature activation-2.64e-01

Pos logit contributions
ingu+0.021
tto+0.020
 pistol+0.019
 brand+0.019
pron+0.018
Neg logit contributions
 Danger-0.072
 nine-0.072
-0.071
 Ab-0.068
 thirteen-0.067
Tokeners
Token ID364
Feature activation-3.43e-02

Pos logit contributions
ingu+0.341
tto+0.323
ascal+0.304
 pistol+0.301
ravings+0.301
Neg logit contributions
 Danger-0.509
 nine-0.503
-0.494
 Ab-0.470
 thirteen-0.470
Token was
Token ID373
Feature activation-2.32e-02

Pos logit contributions
ingu+0.057
tto+0.054
ascal+0.052
 pistol+0.052
ravings+0.052
Neg logit contributions
 Danger-0.054
 nine-0.053
-0.052
 Ab-0.049
 thirteen-0.049
Token very
Token ID845
Feature activation-5.44e-02

Pos logit contributions
ingu+0.039
tto+0.037
ascal+0.036
ravings+0.035
 pistol+0.035
Neg logit contributions
-0.037
 nine-0.037
 Danger-0.035
 Ab-0.034
 thirteen-0.033
Token happy
Token ID3772
Feature activation-1.44e-02

Pos logit contributions
ingu+0.087
tto+0.083
ascal+0.080
ravings+0.079
 pistol+0.078
Neg logit contributions
-0.090
 nine-0.088
 Danger-0.087
 Ab-0.082
 thirteen-0.080
Token to
Token ID284
Feature activation-3.08e-03

Pos logit contributions
ingu+0.032
tto+0.032
affle+0.030
ascal+0.030
ravings+0.030
Neg logit contributions
-0.014
 nine-0.014
 Danger-0.013
 Ab-0.013
 Jen-0.012
Token
Token ID198
Feature activation-2.67e-02

Pos logit contributions
ingu+0.054
ravings+0.051
 pistol+0.051
tto+0.051
ascal+0.050
Neg logit contributions
-0.032
 Danger-0.032
 nine-0.031
 Ab-0.029
 Jen-0.027
TokenAfter
Token ID3260
Feature activation+7.33e-02

Pos logit contributions
tto+0.040
ingu+0.039
scar+0.036
ascal+0.036
Years+0.036
Neg logit contributions
 Danger-0.045
 nine-0.045
 thirteen-0.043
 arc-0.043
 Ab-0.042
Token Mr
Token ID1770
Feature activation-5.60e-02

Pos logit contributions
 Danger+0.114
 nine+0.110
+0.108
 thirteen+0.104
 arc+0.101
Neg logit contributions
ingu-0.123
tto-0.116
 pistol-0.113
 brand-0.112
ascal-0.110
Token.
Token ID13
Feature activation-1.57e-03

Pos logit contributions
ingu+0.117
tto+0.113
ascal+0.108
 brand+0.108
ravings+0.108
Neg logit contributions
 Danger-0.064
 nine-0.063
-0.061
 Ab-0.057
 thirteen-0.056
Token Wh
Token ID854
Feature activation-2.86e-02

Pos logit contributions
ingu+0.003
tto+0.002
 pistol+0.002
ravings+0.002
ascal+0.002
Neg logit contributions
 Danger-0.003
 nine-0.002
-0.002
 thirteen-0.002
 arc-0.002
Tokenisk
Token ID1984
Feature activation-2.64e-01

Pos logit contributions
ingu+0.023
 brand+0.022
 pistol+0.021
pron+0.020
tto+0.020
Neg logit contributions
 Danger-0.066
-0.066
 nine-0.066
 Ab-0.063
 Jen-0.063
Tokeners
Token ID364
Feature activation-3.23e-02

Pos logit contributions
ingu+0.305
tto+0.296
ascal+0.265
affle+0.258
ravings+0.255
Neg logit contributions
 Danger-0.547
 nine-0.534
-0.526
 Ab-0.505
 arc-0.503
Token was
Token ID373
Feature activation-2.00e-02

Pos logit contributions
ingu+0.058
tto+0.056
ascal+0.054
 pistol+0.053
ravings+0.053
Neg logit contributions
 Danger-0.046
 nine-0.045
-0.044
 Ab-0.041
 thirteen-0.041
Token done
Token ID1760
Feature activation-5.20e-02

Pos logit contributions
ingu+0.035
ascal+0.033
tto+0.033
 pistol+0.033
ravings+0.032
Neg logit contributions
 nine-0.030
-0.030
 Danger-0.028
 Ab-0.028
 thirteen-0.027
Token with
Token ID351
Feature activation-2.53e-02

Pos logit contributions
ingu+0.099
tto+0.097
 pistol+0.094
 brand+0.093
ravings+0.092
Neg logit contributions
 Danger-0.069
 nine-0.067
-0.061
 thirteen-0.060
 Ab-0.058
Token his
Token ID465
Feature activation-5.79e-02

Pos logit contributions
ascal+0.055
pron+0.054
ouse+0.053
uddle+0.053
iflower+0.053
Neg logit contributions
 Jen-0.029
 Ab-0.029
-0.027
 nine-0.026
 K-0.025
Token.
Token ID13
Feature activation-4.09e-03

Pos logit contributions
ingu+0.067
tto+0.065
 pistol+0.064
ravings+0.063
ascal+0.063
Neg logit contributions
 Danger-0.047
 nine-0.046
-0.042
 thirteen-0.041
 Ab-0.040
Token The
Token ID383
Feature activation+4.80e-03

Pos logit contributions
ingu+0.007
tto+0.007
ravings+0.006
ascal+0.006
 pistol+0.006
Neg logit contributions
 Danger-0.006
 nine-0.006
 thirteen-0.005
 arc-0.005
 paint-0.005
Token vet
Token ID20202
Feature activation-3.21e-02

Pos logit contributions
 Danger+0.009
+0.008
 nine+0.008
 Ab+0.008
 thirteen+0.008
Neg logit contributions
ingu-0.007
 pistol-0.007
tto-0.006
ascal-0.006
ravings-0.006
Token showed
Token ID3751
Feature activation-8.76e-03

Pos logit contributions
ingu+0.050
tto+0.047
 pistol+0.045
pron+0.044
ascal+0.044
Neg logit contributions
 Danger-0.055
 nine-0.051
 thirteen-0.049
 arc-0.048
-0.047
Token Wh
Token ID854
Feature activation-3.07e-02

Pos logit contributions
ingu+0.017
tto+0.017
 pistol+0.016
ascal+0.016
ravings+0.016
Neg logit contributions
 Danger-0.011
 nine-0.011
-0.010
 thirteen-0.010
 Ab-0.010
Tokenisk
Token ID1984
Feature activation-2.62e-01

Pos logit contributions
ingu+0.026
tto+0.023
 brand+0.023
 pistol+0.022
ravings+0.021
Neg logit contributions
 Danger-0.072
 nine-0.072
-0.071
 Ab-0.067
 thirteen-0.067
Tokeners
Token ID364
Feature activation-3.27e-02

Pos logit contributions
ingu+0.323
tto+0.309
ascal+0.286
 pistol+0.281
ravings+0.278
Neg logit contributions
 Danger-0.519
 nine-0.512
-0.503
 Ab-0.482
 thirteen-0.479
Token the
Token ID262
Feature activation-1.41e-02

Pos logit contributions
ingu+0.055
tto+0.052
 pistol+0.050
 brand+0.049
ravings+0.049
Neg logit contributions
 Danger-0.051
 nine-0.050
-0.048
 thirteen-0.046
 Ab-0.046
Token x
Token ID2124
Feature activation-3.52e-02

Pos logit contributions
ingu+0.020
 pistol+0.020
tto+0.019
 brand+0.019
ravings+0.019
Neg logit contributions
 Danger-0.025
-0.024
 nine-0.024
 arc-0.023
 Ab-0.023
Token-
Token ID12
Feature activation-5.65e-02

Pos logit contributions
ingu+0.039
tto+0.036
ascal+0.033
ravings+0.033
 pistol+0.032
Neg logit contributions
 Danger-0.076
 nine-0.075
-0.074
 thirteen-0.071
 Ab-0.070
Tokenray
Token ID2433
Feature activation-6.92e-03

Pos logit contributions
ingu+0.083
tto+0.082
 pistol+0.080
ascal+0.077
Years+0.076
Neg logit contributions
 arc-0.095
 Danger-0.091
 nine-0.088
 Ab-0.088
-0.085
Token flew
Token ID13112
Feature activation+2.34e-02

Pos logit contributions
ingu+0.004
tto+0.004
 pistol+0.003
ascal+0.003
ravings+0.003
Neg logit contributions
 Danger-0.003
 nine-0.003
 thirteen-0.003
-0.002
 arc-0.002
Token down
Token ID866
Feature activation-2.78e-02

Pos logit contributions
 Danger+0.038
 nine+0.035
+0.034
 thirteen+0.034
 arc+0.033
Neg logit contributions
ingu-0.037
tto-0.036
 pistol-0.036
 brand-0.035
ascal-0.034
Token and
Token ID290
Feature activation-2.12e-02

Pos logit contributions
 pistol+0.035
 hockey+0.034
 brand+0.034
tto+0.033
Years+0.032
Neg logit contributions
 Danger-0.049
 thirteen-0.048
 arc-0.046
-0.045
 nine-0.043
Token scared
Token ID12008
Feature activation+3.69e-02

Pos logit contributions
ingu+0.036
tto+0.035
 pistol+0.033
ascal+0.033
ravings+0.033
Neg logit contributions
 Danger-0.032
 nine-0.032
-0.031
 thirteen-0.029
 Ab-0.029
Token Wh
Token ID854
Feature activation-2.92e-02

Pos logit contributions
 Danger+0.051
 nine+0.049
+0.048
 thirteen+0.046
 arc+0.045
Neg logit contributions
ingu-0.066
tto-0.062
 pistol-0.062
ascal-0.062
ravings-0.062
Tokenisk
Token ID1984
Feature activation-2.62e-01

Pos logit contributions
ingu+0.023
 brand+0.021
 pistol+0.021
tto+0.021
pron+0.020
Neg logit contributions
 Danger-0.071
 nine-0.069
-0.068
 Ab-0.067
 Jen-0.066
Tokeners
Token ID364
Feature activation-3.53e-02

Pos logit contributions
ingu+0.307
tto+0.298
ascal+0.270
 pistol+0.263
ravings+0.262
Neg logit contributions
 Danger-0.534
 nine-0.527
-0.519
 thirteen-0.495
 Ab-0.495
Token away
Token ID1497
Feature activation-1.65e-02

Pos logit contributions
ingu+0.058
 pistol+0.058
tto+0.056
ravings+0.056
 brand+0.054
Neg logit contributions
 Danger-0.051
 nine-0.049
 thirteen-0.048
 arc-0.047
 Ab-0.046
Token.
Token ID13
Feature activation-4.04e-03

Pos logit contributions
ingu+0.032
tto+0.031
 pistol+0.030
 brand+0.030
ravings+0.030
Neg logit contributions
 Danger-0.021
 nine-0.020
-0.020
 thirteen-0.019
 arc-0.018
Token
Token ID198
Feature activation-2.79e-02

Pos logit contributions
ingu+0.008
tto+0.007
ravings+0.007
 brand+0.007
 pistol+0.007
Neg logit contributions
 Danger-0.005
 nine-0.005
-0.005
 thirteen-0.005
 arc-0.004
Token
Token ID198
Feature activation-2.71e-02

Pos logit contributions
ingu+0.060
ravings+0.057
ascal+0.057
 pistol+0.057
tto+0.056
Neg logit contributions
-0.032
 Danger-0.030
 nine-0.030
 Ab-0.027
 Jen-0.026
Token.
Token ID13
Feature activation-4.76e-03

Pos logit contributions
ingu+0.003
tto+0.003
ascal+0.003
ravings+0.003
 pistol+0.003
Neg logit contributions
 Danger-0.002
 nine-0.002
-0.002
 Ab-0.002
 thirteen-0.002
Token
Token ID198
Feature activation-2.94e-02

Pos logit contributions
ingu+0.010
tto+0.010
ascal+0.009
affle+0.009
ravings+0.009
Neg logit contributions
 Danger-0.006
-0.006
 nine-0.006
 Ab-0.005
 Jen-0.005
Token
Token ID198
Feature activation-2.87e-02

Pos logit contributions
ravings+0.071
ingu+0.070
ishing+0.069
ascal+0.068
 pistol+0.066
Neg logit contributions
-0.030
 Danger-0.025
 nine-0.024
 Jen-0.021
 have-0.020
TokenAfter
Token ID3260
Feature activation+7.43e-02

Pos logit contributions
ingu+0.056
tto+0.053
ascal+0.052
ravings+0.052
 pistol+0.051
Neg logit contributions
-0.039
 Danger-0.038
 nine-0.037
 thirteen-0.033
 Ab-0.032
Token Wh
Token ID854
Feature activation-2.83e-02

Pos logit contributions
 Danger+0.099
 nine+0.098
+0.095
 Ab+0.088
 thirteen+0.087
Neg logit contributions
ingu-0.141
tto-0.137
ascal-0.131
ravings-0.131
 pistol-0.129
Tokenisk
Token ID1984
Feature activation-2.61e-01

Pos logit contributions
ingu+0.021
tto+0.019
 brand+0.019
 pistol+0.019
pron+0.017
Neg logit contributions
 Danger-0.070
 nine-0.069
-0.068
 thirteen-0.064
 Ab-0.064
Tokeners
Token ID364
Feature activation-3.30e-02

Pos logit contributions
ingu+0.302
tto+0.293
ascal+0.264
affle+0.256
ravings+0.253
Neg logit contributions
 Danger-0.539
 nine-0.527
-0.519
 Ab-0.502
 arc-0.498
Token got
Token ID1392
Feature activation-3.49e-02

Pos logit contributions
ingu+0.059
tto+0.056
 pistol+0.054
ascal+0.054
ravings+0.054
Neg logit contributions
 Danger-0.047
 nine-0.047
-0.044
 thirteen-0.043
 Ab-0.042
Token better
Token ID1365
Feature activation-5.30e-03

Pos logit contributions
tto+0.071
ingu+0.071
ascal+0.070
affle+0.070
ravings+0.068
Neg logit contributions
 nine-0.041
-0.039
 Ab-0.036
 Danger-0.036
 paint-0.035
Token,
Token ID11
Feature activation+8.24e-03

Pos logit contributions
ingu+0.013
tto+0.013
affle+0.012
Years+0.012
ravings+0.012
Neg logit contributions
-0.004
 nine-0.004
 Danger-0.004
 paint-0.003
 ago-0.003
Token he
Token ID339
Feature activation-3.03e-02

Pos logit contributions
 nine+0.011
+0.010
 Danger+0.010
 Jen+0.010
 Ab+0.010
Neg logit contributions
ingu-0.016
tto-0.016
ascal-0.015
affle-0.015
ravings-0.015
Token a
Token ID257
Feature activation-3.24e-03

Pos logit contributions
ingu+0.054
tto+0.052
ascal+0.050
 pistol+0.050
 brand+0.049
Neg logit contributions
 Danger-0.029
 nine-0.028
-0.027
 thirteen-0.025
 Ab-0.025
Token naughty
Token ID45128
Feature activation-1.21e-02

Pos logit contributions
ingu+0.006
tto+0.006
ravings+0.006
zed+0.006
scar+0.005
Neg logit contributions
 nine-0.004
-0.004
 Danger-0.004
 paint-0.004
 arc-0.004
Token cat
Token ID3797
Feature activation-1.12e-02

Pos logit contributions
ingu+0.022
tto+0.022
 brand+0.020
ravings+0.020
ascal+0.020
Neg logit contributions
 Danger-0.016
 nine-0.016
-0.016
 Ab-0.015
 Jen-0.015
Token named
Token ID3706
Feature activation+1.95e-02

Pos logit contributions
ingu+0.023
tto+0.022
ascal+0.021
ravings+0.021
 pistol+0.021
Neg logit contributions
 Danger-0.013
 nine-0.013
-0.013
 Ab-0.012
 thirteen-0.012
Token Wh
Token ID854
Feature activation-2.82e-02

Pos logit contributions
 Danger+0.031
 nine+0.031
+0.030
 thirteen+0.029
 Ab+0.028
Neg logit contributions
ingu-0.032
tto-0.031
 pistol-0.029
ravings-0.029
ascal-0.029
Tokenisk
Token ID1984
Feature activation-2.61e-01

Pos logit contributions
 brand+0.028
 pistol+0.025
ingu+0.024
tto+0.024
pron+0.023
Neg logit contributions
 nine-0.063
 Danger-0.061
-0.059
 Jen-0.058
 are-0.057
Tokeners
Token ID364
Feature activation-3.23e-02

Pos logit contributions
ingu+0.320
tto+0.305
ascal+0.282
ravings+0.274
 pistol+0.273
Neg logit contributions
 Danger-0.523
 nine-0.513
-0.510
 Ab-0.485
 thirteen-0.483
Token.
Token ID13
Feature activation-5.31e-03

Pos logit contributions
ingu+0.074
tto+0.072
 brand+0.070
affle+0.070
ravings+0.070
Neg logit contributions
 nine-0.030
 Danger-0.029
-0.029
 Ab-0.025
 Jen-0.023
Token Wh
Token ID854
Feature activation-2.58e-02

Pos logit contributions
ingu+0.010
tto+0.009
ascal+0.009
ravings+0.009
 pistol+0.009
Neg logit contributions
 Danger-0.007
 nine-0.007
-0.007
 Ab-0.007
 thirteen-0.007
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
 brand+0.030
pron+0.029
 pistol+0.028
zed+0.026
 handsome+0.025
Neg logit contributions
 nine-0.050
 are-0.048
 Danger-0.048
-0.047
 Jen-0.046
Tokeners
Token ID364
Feature activation-3.12e-02

Pos logit contributions
ingu+0.359
tto+0.337
 pistol+0.326
 brand+0.325
ravings+0.324
Neg logit contributions
 Danger-0.475
 nine-0.474
-0.460
 thirteen-0.439
 Ab-0.438
Token Ch
Token ID609
Feature activation-5.59e-03

Pos logit contributions
 Danger+0.076
 thirteen+0.074
 nine+0.074
 arc+0.072
adies+0.067
Neg logit contributions
ingu-0.079
tto-0.075
 pistol-0.072
ascal-0.071
ravings-0.070
Tokenir
Token ID343
Feature activation+1.48e-01

Pos logit contributions
ingu+0.011
tto+0.011
ascal+0.010
affle+0.010
ravings+0.010
Neg logit contributions
 Danger-0.007
 nine-0.007
-0.007
 thirteen-0.006
 arc-0.006
Tokenpy
Token ID9078
Feature activation+1.55e-03

Pos logit contributions
 Danger+0.270
 nine+0.241
+0.238
 arc+0.236
 thirteen+0.231
Neg logit contributions
ingu-0.213
ascal-0.199
tto-0.197
affle-0.191
ongo-0.181
Token and
Token ID290
Feature activation-7.04e-03

Pos logit contributions
 Danger+0.003
 nine+0.002
 thirteen+0.002
 Ab+0.002
+0.002
Neg logit contributions
ingu-0.002
tto-0.002
 pistol-0.002
ascal-0.002
affle-0.002
Token Wh
Token ID854
Feature activation-2.27e-02

Pos logit contributions
ingu+0.012
 pistol+0.012
tto+0.012
 brand+0.011
ascal+0.011
Neg logit contributions
 Danger-0.010
 nine-0.009
-0.009
 thirteen-0.009
 arc-0.009
Tokenisk
Token ID1984
Feature activation-2.61e-01

Pos logit contributions
ingu+0.022
tto+0.020
ascal+0.019
affle+0.017
ravings+0.017
Neg logit contributions
 Danger-0.052
 nine-0.051
-0.051
 thirteen-0.049
 arc-0.048
Tokeners
Token ID364
Feature activation-2.95e-02

Pos logit contributions
ingu+0.286
tto+0.278
ascal+0.250
affle+0.239
zed+0.239
Neg logit contributions
 Danger-0.550
-0.530
 nine-0.530
 arc-0.517
 Ab-0.503
Token knew
Token ID2993
Feature activation+1.21e-02

Pos logit contributions
ingu+0.045
 pistol+0.043
tto+0.042
zed+0.041
 brand+0.040
Neg logit contributions
 Danger-0.048
 nine-0.046
 Ab-0.044
 Jen-0.043
 arc-0.043
Token that
Token ID326
Feature activation-8.20e-02

Pos logit contributions
 Danger+0.020
 nine+0.019
+0.019
 thirteen+0.018
 arc+0.018
Neg logit contributions
ingu-0.019
tto-0.018
 pistol-0.018
 brand-0.017
ascal-0.017
Token poison
Token ID8764
Feature activation+6.41e-03

Pos logit contributions
 pistol+0.133
ingu+0.123
 brand+0.122
tto+0.120
zed+0.116
Neg logit contributions
 nine-0.129
 Danger-0.129
 thirteen-0.123
 arc-0.120
adies-0.111
Token was
Token ID373
Feature activation-2.17e-02

Pos logit contributions
 Danger+0.009
 nine+0.009
+0.009
 Ab+0.008
 thirteen+0.008
Neg logit contributions
ingu-0.011
tto-0.011
ascal-0.011
 pistol-0.010
ravings-0.010
Token Ch
Token ID609
Feature activation-1.46e-02

Pos logit contributions
 Danger+0.012
 nine+0.012
 thirteen+0.012
 arc+0.011
+0.011
Neg logit contributions
ingu-0.013
 pistol-0.013
tto-0.012
 brand-0.012
ascal-0.011
Tokenir
Token ID343
Feature activation+1.41e-01

Pos logit contributions
ingu+0.030
tto+0.029
ascal+0.029
affle+0.028
ravings+0.028
Neg logit contributions
 Danger-0.017
 nine-0.017
-0.016
 thirteen-0.015
 Ab-0.015
Tokenpy
Token ID9078
Feature activation-1.93e-03

Pos logit contributions
 Danger+0.287
+0.266
 nine+0.262
 arc+0.252
 Ab+0.252
Neg logit contributions
ingu-0.180
ascal-0.170
affle-0.160
tto-0.159
ravings-0.155
Token and
Token ID290
Feature activation-1.68e-02

Pos logit contributions
ingu+0.003
tto+0.003
ascal+0.003
 pistol+0.003
ravings+0.003
Neg logit contributions
 Danger-0.003
 nine-0.003
-0.003
 Ab-0.002
 thirteen-0.002
Token Wh
Token ID854
Feature activation-2.59e-02

Pos logit contributions
ingu+0.031
 pistol+0.029
tto+0.029
ascal+0.028
ravings+0.028
Neg logit contributions
 Danger-0.024
 nine-0.023
-0.023
 thirteen-0.021
 arc-0.021
Tokenisk
Token ID1984
Feature activation-2.61e-01

Pos logit contributions
ingu+0.015
tto+0.013
ascal+0.012
ravings+0.011
affle+0.010
Neg logit contributions
 Danger-0.069
 nine-0.068
-0.068
 thirteen-0.065
 Ab-0.065
Tokeners
Token ID364
Feature activation-3.14e-02

Pos logit contributions
ingu+0.267
tto+0.256
ascal+0.228
zed+0.221
Years+0.217
Neg logit contributions
 Danger-0.568
-0.551
 nine-0.548
 arc-0.533
 Ab-0.528
Token became
Token ID2627
Feature activation-3.26e-02

Pos logit contributions
ingu+0.058
tto+0.055
 pistol+0.053
ascal+0.052
ravings+0.052
Neg logit contributions
 Danger-0.044
 nine-0.042
-0.040
 thirteen-0.039
 Ab-0.038
Token good
Token ID922
Feature activation-3.83e-02

Pos logit contributions
ingu+0.053
tto+0.050
ascal+0.048
ravings+0.047
 pistol+0.047
Neg logit contributions
 nine-0.053
 Danger-0.052
-0.052
 Ab-0.049
 thirteen-0.048
Token friends
Token ID2460
Feature activation-2.96e-02

Pos logit contributions
ingu+0.053
tto+0.051
 brand+0.049
pron+0.048
ravings+0.046
Neg logit contributions
 nine-0.071
 Danger-0.069
-0.069
 Ab-0.066
 paint-0.064
Token,
Token ID11
Feature activation+6.72e-03

Pos logit contributions
ingu+0.066
tto+0.064
affle+0.061
ascal+0.061
ravings+0.061
Neg logit contributions
-0.031
 nine-0.030
 Danger-0.030
 Ab-0.026
 thirteen-0.026
Token j
Token ID474
Feature activation-3.46e-02

Pos logit contributions
ingu+0.005
tto+0.005
ravings+0.005
zed+0.005
scar+0.005
Neg logit contributions
 nine-0.004
-0.004
 Danger-0.004
 arc-0.003
 Ab-0.003
Tokenolly
Token ID5098
Feature activation-2.00e-02

Pos logit contributions
ingu+0.039
tto+0.037
 brand+0.035
ascal+0.035
 pistol+0.035
Neg logit contributions
 Danger-0.072
 nine-0.070
-0.069
 Ab-0.066
 arc-0.065
Token cat
Token ID3797
Feature activation-8.04e-03

Pos logit contributions
ingu+0.034
tto+0.032
ravings+0.031
ascal+0.031
 brand+0.031
Neg logit contributions
 Danger-0.030
 nine-0.030
-0.030
 Ab-0.028
 thirteen-0.027
Token named
Token ID3706
Feature activation+2.32e-02

Pos logit contributions
ingu+0.016
tto+0.015
ascal+0.015
ravings+0.015
 pistol+0.015
Neg logit contributions
 Danger-0.010
 nine-0.010
-0.009
 Ab-0.009
 thirteen-0.009
Token Wh
Token ID854
Feature activation-2.65e-02

Pos logit contributions
 Danger+0.034
 nine+0.034
+0.033
 Ab+0.031
 thirteen+0.031
Neg logit contributions
ingu-0.041
tto-0.039
ascal-0.038
ravings-0.037
 pistol-0.037
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
 brand+0.026
 pistol+0.024
ingu+0.023
tto+0.022
pron+0.021
Neg logit contributions
 nine-0.058
 Danger-0.056
-0.055
 Jen-0.053
 thirteen-0.052
Tokeners
Token ID364
Feature activation-3.10e-02

Pos logit contributions
ingu+0.310
tto+0.297
ascal+0.271
ravings+0.261
affle+0.261
Neg logit contributions
 Danger-0.532
 nine-0.521
-0.519
 Ab-0.492
 thirteen-0.491
Token.
Token ID13
Feature activation-4.22e-03

Pos logit contributions
ingu+0.069
tto+0.067
ravings+0.065
ascal+0.065
affle+0.065
Neg logit contributions
 nine-0.030
 Danger-0.030
-0.030
 Ab-0.026
 thirteen-0.025
Token Wh
Token ID854
Feature activation-2.53e-02

Pos logit contributions
ingu+0.008
tto+0.008
ascal+0.007
ravings+0.007
 pistol+0.007
Neg logit contributions
 Danger-0.006
 nine-0.006
-0.006
 Ab-0.005
 thirteen-0.005
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
 brand+0.030
 pistol+0.029
pron+0.028
 handsome+0.026
zed+0.025
Neg logit contributions
 nine-0.049
 Danger-0.047
-0.046
 are-0.046
 Jen-0.044
Tokeners
Token ID364
Feature activation-3.00e-02

Pos logit contributions
ingu+0.348
tto+0.327
 pistol+0.312
ascal+0.312
ravings+0.311
Neg logit contributions
 Danger-0.488
 nine-0.485
-0.473
 thirteen-0.451
 Ab-0.451
Token was
Token ID373
Feature activation-2.22e-02

Pos logit contributions
ingu+0.028
 brand+0.028
 pistol+0.028
tto+0.027
ravings+0.026
Neg logit contributions
 Danger-0.029
 nine-0.027
-0.026
 thirteen-0.025
 arc-0.025
Token heading
Token ID9087
Feature activation-4.43e-02

Pos logit contributions
ingu+0.037
tto+0.036
 brand+0.035
 pistol+0.035
ravings+0.034
Neg logit contributions
 Danger-0.034
 nine-0.032
-0.032
 thirteen-0.030
 Ab-0.030
Token straight
Token ID3892
Feature activation-1.67e-02

Pos logit contributions
 brand+0.061
 pistol+0.061
ingu+0.059
tto+0.058
 hockey+0.056
Neg logit contributions
 Danger-0.078
-0.073
 nine-0.073
 thirteen-0.072
 arc-0.071
Token towards
Token ID3371
Feature activation+4.11e-02

Pos logit contributions
ingu+0.031
tto+0.030
 pistol+0.029
ascal+0.029
ravings+0.029
Neg logit contributions
 Danger-0.022
 nine-0.022
-0.021
 thirteen-0.020
 Ab-0.020
Token Wh
Token ID854
Feature activation-2.75e-02

Pos logit contributions
 Danger+0.055
 nine+0.053
 thirteen+0.051
+0.051
 arc+0.048
Neg logit contributions
ingu-0.075
tto-0.072
 pistol-0.072
 brand-0.070
ravings-0.069
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
ingu+0.030
 brand+0.028
tto+0.028
 pistol+0.028
ascal+0.026
Neg logit contributions
 Danger-0.059
 nine-0.058
-0.057
 thirteen-0.054
 Ab-0.053
Tokeners
Token ID364
Feature activation-3.00e-02

Pos logit contributions
tto+0.261
ingu+0.254
zed+0.226
scar+0.215
ascal+0.211
Neg logit contributions
 Danger-0.565
 nine-0.552
 arc-0.550
-0.535
 Ab-0.528
Token.
Token ID13
Feature activation-1.44e-03

Pos logit contributions
ingu+0.052
 pistol+0.051
tto+0.050
ravings+0.049
 brand+0.048
Neg logit contributions
 Danger-0.042
 nine-0.040
 thirteen-0.039
 arc-0.038
 Ab-0.038
Token She
Token ID1375
Feature activation+2.24e-02

Pos logit contributions
ingu+0.003
tto+0.003
 brand+0.003
ravings+0.003
 pistol+0.003
Neg logit contributions
 Danger-0.002
 nine-0.002
 thirteen-0.001
-0.001
 arc-0.001
Token ran
Token ID4966
Feature activation+1.79e-02

Pos logit contributions
+0.029
 nine+0.028
 Danger+0.028
 Ab+0.026
 Jen+0.024
Neg logit contributions
ingu-0.045
tto-0.043
ascal-0.042
ravings-0.042
affle-0.041
Token as
Token ID355
Feature activation-7.56e-02

Pos logit contributions
 Danger+0.028
 arc+0.026
 thirteen+0.025
 nine+0.025
+0.025
Neg logit contributions
tto-0.029
ingu-0.028
 pistol-0.028
 brand-0.027
Years-0.027
Token,
Token ID11
Feature activation+7.25e-03

Pos logit contributions
ingu+0.021
tto+0.021
ascal+0.020
affle+0.020
ravings+0.020
Neg logit contributions
 Danger-0.012
 nine-0.012
-0.012
 Ab-0.011
 Jen-0.011
Token and
Token ID290
Feature activation-1.74e-02

Pos logit contributions
+0.011
 nine+0.010
 Danger+0.010
 Ab+0.010
 Jen+0.010
Neg logit contributions
ingu-0.013
ascal-0.013
tto-0.013
affle-0.012
ravings-0.012
Token he
Token ID339
Feature activation-2.78e-02

Pos logit contributions
ascal+0.037
ingu+0.035
affle+0.035
tto+0.034
ravings+0.034
Neg logit contributions
-0.022
 Ab-0.020
 Jen-0.020
 nine-0.018
 Danger-0.017
Token and
Token ID290
Feature activation-1.72e-02

Pos logit contributions
ascal+0.051
ingu+0.051
tto+0.050
ravings+0.050
affle+0.049
Neg logit contributions
-0.040
 nine-0.036
 Danger-0.034
 Ab-0.033
 paint-0.032
Token Wh
Token ID854
Feature activation-2.65e-02

Pos logit contributions
ascal+0.032
ingu+0.032
 brand+0.031
tto+0.031
ravings+0.031
Neg logit contributions
 Jen-0.024
 Ab-0.023
-0.023
 nine-0.022
 K-0.021
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
ingu+0.023
 brand+0.023
pron+0.023
 pistol+0.022
tto+0.021
Neg logit contributions
 Danger-0.060
 nine-0.060
-0.059
 are-0.056
 Ab-0.056
Tokeners
Token ID364
Feature activation-2.87e-02

Pos logit contributions
ingu+0.331
tto+0.313
ascal+0.294
 pistol+0.290
ravings+0.289
Neg logit contributions
 Danger-0.508
 nine-0.502
-0.493
 Ab-0.470
 thirteen-0.469
Token played
Token ID2826
Feature activation-8.40e-02

Pos logit contributions
ingu+0.048
tto+0.045
 pistol+0.044
 brand+0.043
ravings+0.043
Neg logit contributions
 Danger-0.045
 nine-0.043
-0.043
 thirteen-0.041
 Ab-0.040
Token with
Token ID351
Feature activation-2.31e-02

Pos logit contributions
ingu+0.207
ascal+0.204
tto+0.202
scar+0.196
ravings+0.192
Neg logit contributions
 nine-0.070
-0.066
 Danger-0.065
 paint-0.060
 are-0.060
Token the
Token ID262
Feature activation-8.20e-03

Pos logit contributions
tto+0.059
ascal+0.059
ingu+0.058
pron+0.057
ravings+0.057
Neg logit contributions
 nine-0.017
 Danger-0.015
-0.015
 Jen-0.015
 are-0.014
Token new
Token ID649
Feature activation-3.48e-02

Pos logit contributions
ingu+0.013
tto+0.012
 pistol+0.012
 brand+0.012
ravings+0.011
Neg logit contributions
 Danger-0.014
 nine-0.014
-0.013
 Ab-0.013
 thirteen-0.013
TokenI
Token ID40
Feature activation-3.08e-02

Pos logit contributions
tto+0.044
ingu+0.043
ascal+0.041
pron+0.041
scar+0.040
Neg logit contributions
 Danger-0.042
 nine-0.041
-0.037
 thirteen-0.037
 Ab-0.037
Token'm
Token ID1101
Feature activation+6.80e-02

Pos logit contributions
tto+0.063
ingu+0.061
 pistol+0.058
scar+0.057
ravings+0.057
Neg logit contributions
 Danger-0.037
 nine-0.037
 thirteen-0.035
 arc-0.034
 Ab-0.030
Token sorry
Token ID7926
Feature activation-1.11e-02

Pos logit contributions
 Danger+0.123
 nine+0.116
+0.114
 thirteen+0.111
 arc+0.109
Neg logit contributions
ingu-0.098
tto-0.094
 brand-0.091
ascal-0.088
ravings-0.087
Token,
Token ID11
Feature activation+1.19e-02

Pos logit contributions
ingu+0.025
tto+0.024
ascal+0.023
ravings+0.023
 pistol+0.023
Neg logit contributions
 Danger-0.011
 nine-0.011
-0.011
 Ab-0.010
 thirteen-0.010
Token Wh
Token ID854
Feature activation-2.49e-02

Pos logit contributions
 Danger+0.017
 nine+0.017
 thirteen+0.015
 Ab+0.015
+0.015
Neg logit contributions
ingu-0.021
 pistol-0.020
 brand-0.020
pron-0.019
ravings-0.018
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
ingu+0.032
tto+0.030
 pistol+0.029
 brand+0.029
ascal+0.028
Neg logit contributions
 Danger-0.048
 nine-0.048
-0.047
 Ab-0.045
 thirteen-0.044
Tokeners
Token ID364
Feature activation-2.90e-02

Pos logit contributions
ingu+0.302
tto+0.292
ascal+0.264
affle+0.255
 pistol+0.255
Neg logit contributions
 Danger-0.534
 nine-0.526
-0.516
 Ab-0.500
 arc-0.494
Token.
Token ID13
Feature activation+3.38e-03

Pos logit contributions
ingu+0.057
tto+0.055
 pistol+0.053
ravings+0.053
ascal+0.052
Neg logit contributions
 Danger-0.037
 nine-0.035
-0.034
 thirteen-0.032
 Ab-0.032
Token Let
Token ID3914
Feature activation+2.82e-02

Pos logit contributions
 nine+0.004
 Danger+0.003
 thirteen+0.003
 arc+0.003
 Ab+0.003
Neg logit contributions
ingu-0.007
 pistol-0.007
tto-0.007
 brand-0.007
ascal-0.007
Token's
Token ID338
Feature activation+8.34e-03

Pos logit contributions
+0.026
 Danger+0.024
 nine+0.023
 Ab+0.020
 thirteen+0.019
Neg logit contributions
ingu-0.067
tto-0.065
ascal-0.064
ravings-0.063
affle-0.063
Token go
Token ID467
Feature activation+1.15e-02

Pos logit contributions
 Danger+0.011
 nine+0.011
 thirteen+0.011
 ago+0.009
 arc+0.009
Neg logit contributions
ingu-0.016
tto-0.015
 pistol-0.015
ravings-0.014
 brand-0.014
Token ink
Token ID16882
Feature activation+1.98e-03

Pos logit contributions
 nine+0.104
 Danger+0.097
+0.094
 Ab+0.092
 Jen+0.089
Neg logit contributions
ingu-0.200
tto-0.193
ascal-0.191
ravings-0.184
affle-0.180
Token.
Token ID13
Feature activation+6.40e-05

Pos logit contributions
 nine+0.002
+0.002
 Danger+0.002
 thirteen+0.002
 Ab+0.002
Neg logit contributions
ingu-0.004
tto-0.004
ascal-0.004
affle-0.004
ravings-0.004
Token Mr
Token ID1770
Feature activation-5.57e-02

Pos logit contributions
 nine+0.000
 Danger+0.000
 thirteen+0.000
 arc+0.000
 paint+0.000
Neg logit contributions
ingu-0.000
tto-0.000
 pistol-0.000
ravings-0.000
 brand-0.000
Token.
Token ID13
Feature activation-5.48e-04

Pos logit contributions
ingu+0.128
tto+0.124
 brand+0.124
pron+0.124
ravings+0.121
Neg logit contributions
-0.050
 nine-0.050
 Danger-0.049
 Ab-0.044
 thirteen-0.042
Token Wh
Token ID854
Feature activation-2.54e-02

Pos logit contributions
ingu+0.001
 pistol+0.001
tto+0.001
ascal+0.001
ravings+0.001
Neg logit contributions
 Danger-0.001
 nine-0.001
-0.001
 thirteen-0.001
 arc-0.001
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
 brand+0.023
ingu+0.023
pron+0.022
 pistol+0.021
tto+0.020
Neg logit contributions
 nine-0.056
-0.056
 Danger-0.055
 Ab-0.053
 Jen-0.053
Tokeners
Token ID364
Feature activation-2.69e-02

Pos logit contributions
ingu+0.327
tto+0.311
ascal+0.290
 pistol+0.286
ravings+0.285
Neg logit contributions
 Danger-0.512
 nine-0.505
-0.496
 Ab-0.473
 thirteen-0.472
Token went
Token ID1816
Feature activation-5.92e-03

Pos logit contributions
ingu+0.045
tto+0.044
 pistol+0.042
ravings+0.041
ascal+0.041
Neg logit contributions
 Danger-0.042
 nine-0.040
-0.039
 thirteen-0.037
 Ab-0.037
Token to
Token ID284
Feature activation+9.55e-04

Pos logit contributions
ingu+0.010
tto+0.010
 pistol+0.010
 brand+0.010
ravings+0.009
Neg logit contributions
 Danger-0.009
 nine-0.008
-0.008
 thirteen-0.008
 arc-0.008
Token the
Token ID262
Feature activation-7.95e-03

Pos logit contributions
 Danger+0.001
 nine+0.001
 thirteen+0.001
+0.001
 arc+0.001
Neg logit contributions
ingu-0.002
 pistol-0.002
tto-0.002
 brand-0.002
ravings-0.002
Token store
Token ID3650
Feature activation+2.79e-05

Pos logit contributions
ingu+0.013
 pistol+0.013
 brand+0.013
ravings+0.012
tto+0.012
Neg logit contributions
 Danger-0.013
 nine-0.012
 thirteen-0.012
 Ab-0.012
-0.012
Token Wh
Token ID854
Feature activation-2.82e-02

Pos logit contributions
 Danger+0.031
 nine+0.031
+0.030
 thirteen+0.029
 Ab+0.028
Neg logit contributions
ingu-0.032
tto-0.031
 pistol-0.029
ravings-0.029
ascal-0.029
Tokenisk
Token ID1984
Feature activation-2.61e-01

Pos logit contributions
 brand+0.028
 pistol+0.025
ingu+0.024
tto+0.024
pron+0.023
Neg logit contributions
 nine-0.063
 Danger-0.061
-0.059
 Jen-0.058
 are-0.057
Tokeners
Token ID364
Feature activation-3.23e-02

Pos logit contributions
ingu+0.320
tto+0.305
ascal+0.282
ravings+0.274
 pistol+0.273
Neg logit contributions
 Danger-0.523
 nine-0.513
-0.510
 Ab-0.485
 thirteen-0.483
Token.
Token ID13
Feature activation-5.31e-03

Pos logit contributions
ingu+0.074
tto+0.072
 brand+0.070
affle+0.070
ravings+0.070
Neg logit contributions
 nine-0.030
 Danger-0.029
-0.029
 Ab-0.025
 Jen-0.023
Token Wh
Token ID854
Feature activation-2.58e-02

Pos logit contributions
ingu+0.010
tto+0.009
ascal+0.009
ravings+0.009
 pistol+0.009
Neg logit contributions
 Danger-0.007
 nine-0.007
-0.007
 Ab-0.007
 thirteen-0.007
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
 brand+0.030
pron+0.029
 pistol+0.028
zed+0.026
 handsome+0.025
Neg logit contributions
 nine-0.050
 are-0.048
 Danger-0.048
-0.047
 Jen-0.046
Tokeners
Token ID364
Feature activation-3.12e-02

Pos logit contributions
ingu+0.359
tto+0.337
 pistol+0.326
 brand+0.325
ravings+0.324
Neg logit contributions
 Danger-0.475
 nine-0.474
-0.460
 thirteen-0.439
 Ab-0.438
Token loved
Token ID6151
Feature activation-7.23e-02

Pos logit contributions
ingu+0.057
 brand+0.055
ravings+0.054
ascal+0.053
 pistol+0.052
Neg logit contributions
-0.045
 are-0.042
 nine-0.042
 Danger-0.041
 paint-0.039
Token to
Token ID284
Feature activation-3.23e-03

Pos logit contributions
ingu+0.176
tto+0.173
ascal+0.165
scar+0.162
ouse+0.160
Neg logit contributions
 paint-0.060
 nine-0.059
 Jen-0.055
 Danger-0.054
 Ab-0.052
Token play
Token ID711
Feature activation-6.03e-02

Pos logit contributions
ingu+0.006
tto+0.006
 pistol+0.006
ravings+0.006
ascal+0.006
Neg logit contributions
 Danger-0.004
 nine-0.004
-0.004
 thirteen-0.004
 Ab-0.004
Token with
Token ID351
Feature activation-2.78e-02

Pos logit contributions
ingu+0.149
tto+0.142
scar+0.141
ascal+0.141
ongo+0.140
Neg logit contributions
 paint-0.049
 nine-0.046
 Danger-0.043
-0.041
 are-0.039
Token a
Token ID257
Feature activation-4.95e-03

Pos logit contributions
ingu+0.056
tto+0.054
ascal+0.051
 pistol+0.051
 brand+0.051
Neg logit contributions
 Danger-0.032
 nine-0.030
-0.029
 thirteen-0.028
 Ab-0.027
Token smart
Token ID4451
Feature activation-6.54e-02

Pos logit contributions
ingu+0.009
tto+0.009
ravings+0.009
zed+0.009
scar+0.008
Neg logit contributions
 nine-0.007
-0.006
 Danger-0.006
 Ab-0.006
 paint-0.006
Token cat
Token ID3797
Feature activation-1.08e-02

Pos logit contributions
ingu+0.114
tto+0.110
ravings+0.104
ascal+0.104
 brand+0.104
Neg logit contributions
 nine-0.096
 Danger-0.096
-0.092
 Ab-0.088
 thirteen-0.086
Token named
Token ID3706
Feature activation+2.02e-02

Pos logit contributions
ingu+0.020
tto+0.020
ascal+0.019
 pistol+0.019
ravings+0.019
Neg logit contributions
 Danger-0.015
 nine-0.014
-0.014
 thirteen-0.013
 Ab-0.013
Token Wh
Token ID854
Feature activation-2.86e-02

Pos logit contributions
 Danger+0.029
 nine+0.029
+0.028
 thirteen+0.027
 arc+0.026
Neg logit contributions
ingu-0.035
tto-0.034
 pistol-0.032
ravings-0.032
ascal-0.032
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
ingu+0.025
 brand+0.024
 pistol+0.023
tto+0.022
ravings+0.021
Neg logit contributions
 nine-0.066
 Danger-0.065
-0.064
 Ab-0.061
 Jen-0.061
Tokeners
Token ID364
Feature activation-3.05e-02

Pos logit contributions
ingu+0.306
tto+0.294
ascal+0.268
affle+0.258
ravings+0.257
Neg logit contributions
 Danger-0.533
 nine-0.522
-0.520
 Ab-0.493
 thirteen-0.493
Token.
Token ID13
Feature activation-5.73e-03

Pos logit contributions
ingu+0.069
tto+0.067
ravings+0.064
ascal+0.064
 brand+0.064
Neg logit contributions
 nine-0.029
 Danger-0.029
-0.029
 Ab-0.025
 thirteen-0.024
Token Wh
Token ID854
Feature activation-2.68e-02

Pos logit contributions
ingu+0.011
tto+0.010
ascal+0.010
ravings+0.010
 pistol+0.010
Neg logit contributions
 Danger-0.008
 nine-0.008
-0.008
 Ab-0.007
 thirteen-0.007
Tokenisk
Token ID1984
Feature activation-2.59e-01

Pos logit contributions
 brand+0.029
 pistol+0.028
pron+0.028
ingu+0.026
zed+0.024
Neg logit contributions
 nine-0.054
 Danger-0.053
 are-0.052
-0.052
 Jen-0.050
Tokeners
Token ID364
Feature activation-3.03e-02

Pos logit contributions
ingu+0.350
tto+0.329
 pistol+0.316
ravings+0.315
ascal+0.315
Neg logit contributions
 Danger-0.482
 nine-0.479
-0.467
 thirteen-0.445
 Ab-0.445
Token Wh
Token ID854
Feature activation-2.65e-02

Pos logit contributions
 Danger+0.034
 nine+0.034
+0.033
 Ab+0.031
 thirteen+0.031
Neg logit contributions
ingu-0.041
tto-0.039
ascal-0.038
ravings-0.037
 pistol-0.037
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
 brand+0.026
 pistol+0.024
ingu+0.023
tto+0.022
pron+0.021
Neg logit contributions
 nine-0.058
 Danger-0.056
-0.055
 Jen-0.053
 thirteen-0.052
Tokeners
Token ID364
Feature activation-3.10e-02

Pos logit contributions
ingu+0.310
tto+0.297
ascal+0.271
ravings+0.261
affle+0.261
Neg logit contributions
 Danger-0.532
 nine-0.521
-0.519
 Ab-0.492
 thirteen-0.491
Token.
Token ID13
Feature activation-4.22e-03

Pos logit contributions
ingu+0.069
tto+0.067
ravings+0.065
ascal+0.065
affle+0.065
Neg logit contributions
 nine-0.030
 Danger-0.030
-0.030
 Ab-0.026
 thirteen-0.025
Token Wh
Token ID854
Feature activation-2.53e-02

Pos logit contributions
ingu+0.008
tto+0.008
ascal+0.007
ravings+0.007
 pistol+0.007
Neg logit contributions
 Danger-0.006
 nine-0.006
-0.006
 Ab-0.005
 thirteen-0.005
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
 brand+0.030
 pistol+0.029
pron+0.028
 handsome+0.026
zed+0.025
Neg logit contributions
 nine-0.049
 Danger-0.047
-0.046
 are-0.046
 Jen-0.044
Tokeners
Token ID364
Feature activation-3.00e-02

Pos logit contributions
ingu+0.348
tto+0.327
 pistol+0.312
ascal+0.312
ravings+0.311
Neg logit contributions
 Danger-0.488
 nine-0.485
-0.473
 thirteen-0.451
 Ab-0.451
Token loved
Token ID6151
Feature activation-7.29e-02

Pos logit contributions
ingu+0.051
ravings+0.050
 brand+0.049
ascal+0.048
 pistol+0.048
Neg logit contributions
-0.048
 are-0.044
 nine-0.043
 Danger-0.042
 paint-0.041
Token to
Token ID284
Feature activation-2.06e-03

Pos logit contributions
ingu+0.175
tto+0.172
ascal+0.163
scar+0.160
affle+0.159
Neg logit contributions
 paint-0.063
 nine-0.060
 Danger-0.058
 Jen-0.058
 Ab-0.056
Token eat
Token ID4483
Feature activation-8.21e-03

Pos logit contributions
ingu+0.004
tto+0.004
 pistol+0.004
ascal+0.004
ravings+0.004
Neg logit contributions
 Danger-0.003
 nine-0.003
-0.003
 thirteen-0.003
 Ab-0.003
Token tuna
Token ID38883
Feature activation-1.20e-01

Pos logit contributions
ingu+0.014
tto+0.013
ascal+0.013
ravings+0.012
scar+0.012
Neg logit contributions
 nine-0.013
 Danger-0.013
-0.012
 Ab-0.012
 paint-0.012
Token his
Token ID465
Feature activation-5.90e-02

Pos logit contributions
 Danger+0.016
 nine+0.016
+0.016
 Ab+0.015
 Jen+0.014
Neg logit contributions
ingu-0.021
tto-0.020
pron-0.019
ravings-0.019
 brand-0.019
Token paw
Token ID41827
Feature activation-5.29e-02

Pos logit contributions
ingu+0.113
tto+0.112
scar+0.105
ascal+0.101
Matthew+0.101
Neg logit contributions
 nine-0.078
 paint-0.075
 Danger-0.073
 Jen-0.070
-0.070
Token again
Token ID757
Feature activation+3.60e-04

Pos logit contributions
ingu+0.109
tto+0.106
ascal+0.102
ravings+0.100
affle+0.099
Neg logit contributions
-0.061
 Danger-0.061
 nine-0.061
 Ab-0.054
 thirteen-0.054
Token.
Token ID13
Feature activation-6.66e-04

Pos logit contributions
+0.000
 nine+0.000
 Danger+0.000
 Ab+0.000
 paint+0.000
Neg logit contributions
ingu-0.001
tto-0.001
ascal-0.001
affle-0.001
ravings-0.001
Token Wh
Token ID854
Feature activation-2.61e-02

Pos logit contributions
tto+0.001
ingu+0.001
ascal+0.001
pron+0.001
affle+0.001
Neg logit contributions
-0.001
 Danger-0.001
 nine-0.001
 Jen-0.001
 Ab-0.001
Tokenisk
Token ID1984
Feature activation-2.60e-01

Pos logit contributions
 brand+0.022
pron+0.022
tto+0.022
ingu+0.022
 pistol+0.021
Neg logit contributions
 nine-0.059
 Danger-0.059
-0.057
 Ab-0.054
 thirteen-0.054
Tokeners
Token ID364
Feature activation-3.02e-02

Pos logit contributions
ingu+0.360
tto+0.337
ravings+0.326
 pistol+0.326
ascal+0.324
Neg logit contributions
 Danger-0.475
 nine-0.474
-0.464
 thirteen-0.441
 Ab-0.438
Token loved
Token ID6151
Feature activation-7.31e-02

Pos logit contributions
ingu+0.054
tto+0.052
ascal+0.051
ravings+0.050
 pistol+0.050
Neg logit contributions
 nine-0.043
 Danger-0.042
-0.042
 Ab-0.039
 thirteen-0.038
Token playing
Token ID2712
Feature activation-8.59e-02

Pos logit contributions
ingu+0.171
tto+0.167
ouse+0.164
uddle+0.162
affle+0.156
Neg logit contributions
 Jen-0.076
 Ab-0.067
 nine-0.066
 paint-0.066
 K-0.063
Token in
Token ID287
Feature activation+1.08e-03

Pos logit contributions
ingu+0.202
tto+0.188
ascal+0.187
ravings+0.179
ongo+0.177
Neg logit contributions
-0.084
 nine-0.083
 paint-0.079
 Danger-0.079
 are-0.073
Token the
Token ID262
Feature activation-9.43e-03

Pos logit contributions
 nine+0.001
 Danger+0.001
+0.001
 Ab+0.001
 Jen+0.001
Neg logit contributions
ingu-0.003
tto-0.002
ascal-0.002
ravings-0.002
affle-0.002
Token.
Token ID13
Feature activation-4.26e-03

Pos logit contributions
tto+0.233
Matthew+0.230
scar+0.229
ascal+0.228
 brand+0.226
Neg logit contributions
-0.133
 nine-0.130
 are-0.129
 Danger-0.125
 paint-0.120
Token One
Token ID1881
Feature activation+7.38e-02

Pos logit contributions
ingu+0.010
tto+0.010
ascal+0.010
ravings+0.009
 brand+0.009
Neg logit contributions
 Danger-0.004
 nine-0.004
-0.003
 Ab-0.003
 thirteen-0.003
Token day
Token ID1110
Feature activation-2.84e-02

Pos logit contributions
+0.093
 Danger+0.093
 nine+0.092
 Ab+0.084
 Jen+0.082
Neg logit contributions
ingu-0.146
tto-0.137
ascal-0.136
 brand-0.135
ravings-0.135
Token,
Token ID11
Feature activation+4.75e-03

Pos logit contributions
ingu+0.059
tto+0.057
 pistol+0.056
ascal+0.054
 brand+0.054
Neg logit contributions
 Danger-0.032
 nine-0.031
-0.030
 thirteen-0.029
 Ab-0.028
Token Wh
Token ID854
Feature activation-2.46e-02

Pos logit contributions
 nine+0.006
 Danger+0.006
+0.006
 Ab+0.006
 Jen+0.005
Neg logit contributions
ingu-0.009
tto-0.009
ascal-0.009
ravings-0.009
affle-0.008
Tokenisk
Token ID1984
Feature activation-2.59e-01

Pos logit contributions
 brand+0.027
 pistol+0.025
pron+0.025
tto+0.023
ingu+0.023
Neg logit contributions
 nine-0.051
 Danger-0.050
-0.048
 are-0.046
 Jen-0.046
Tokeners
Token ID364
Feature activation-2.98e-02

Pos logit contributions
ingu+0.334
tto+0.316
ascal+0.297
 pistol+0.294
ravings+0.293
Neg logit contributions
 Danger-0.503
 nine-0.498
-0.489
 Ab-0.466
 thirteen-0.465
Token saw
Token ID2497
Feature activation-1.51e-02

Pos logit contributions
ingu+0.053
tto+0.051
 pistol+0.049
ascal+0.048
ravings+0.048
Neg logit contributions
 Danger-0.044
 nine-0.043
-0.041
 thirteen-0.040
 Ab-0.039
Token a
Token ID257
Feature activation-4.39e-03

Pos logit contributions
ingu+0.039
tto+0.038
ascal+0.038
ravings+0.038
pron+0.038
Neg logit contributions
 nine-0.011
 Jen-0.009
 Danger-0.009
 Ab-0.008
-0.008
Token can
Token ID460
Feature activation+5.09e-02

Pos logit contributions
ingu+0.008
tto+0.008
zed+0.008
ascal+0.008
ravings+0.007
Neg logit contributions
-0.006
 Danger-0.006
 nine-0.006
 paint-0.006
 arc-0.005
Token of
Token ID286
Feature activation+8.68e-02

Pos logit contributions
 Danger+0.050
+0.048
 nine+0.044
 Ab+0.037
 Jen+0.037
Neg logit contributions
ingu-0.118
tto-0.113
ascal-0.112
ravings-0.112
 brand-0.109
Token A
Token ID317
Feature activation+2.00e-02

Pos logit contributions
 Danger+0.004
+0.004
 nine+0.004
 Ab+0.004
 thirteen+0.004
Neg logit contributions
ingu-0.005
tto-0.005
ascal-0.005
ravings-0.005
affle-0.004
Token little
Token ID1310
Feature activation+1.18e-02

Pos logit contributions
 nine+0.032
 Danger+0.032
+0.031
 Ab+0.029
 thirteen+0.028
Neg logit contributions
ingu-0.034
tto-0.032
ascal-0.031
ravings-0.030
affle-0.029
Token cat
Token ID3797
Feature activation-8.75e-03

Pos logit contributions
 Danger+0.018
 nine+0.017
 thirteen+0.016
+0.016
 Ab+0.016
Neg logit contributions
 pistol-0.020
 brand-0.018
ingu-0.018
 hockey-0.018
tto-0.017
Token named
Token ID3706
Feature activation+1.99e-02

Pos logit contributions
tto+0.014
ingu+0.014
 pistol+0.014
affle+0.013
scar+0.013
Neg logit contributions
 Danger-0.014
 nine-0.013
 thirteen-0.013
 arc-0.012
 Ab-0.012
Token Wh
Token ID854
Feature activation-2.78e-02

Pos logit contributions
 nine+0.034
 arc+0.033
 Danger+0.032
 thirteen+0.032
 ago+0.030
Neg logit contributions
ingu-0.028
 pistol-0.026
tto-0.026
ascal-0.024
scar-0.024
Tokenisk
Token ID1984
Feature activation-2.59e-01

Pos logit contributions
ingu+0.022
tto+0.019
 brand+0.019
 pistol+0.018
pron+0.018
Neg logit contributions
 Danger-0.068
 nine-0.067
-0.067
 Ab-0.063
 thirteen-0.063
Tokeners
Token ID364
Feature activation-2.66e-02

Pos logit contributions
tto+0.265
ingu+0.265
affle+0.228
ascal+0.226
 pistol+0.222
Neg logit contributions
 Danger-0.560
 nine-0.548
-0.545
 arc-0.526
 Ab-0.522
Token also
Token ID635
Feature activation+6.75e-02

Pos logit contributions
ingu+0.047
tto+0.045
 pistol+0.045
ravings+0.043
ascal+0.043
Neg logit contributions
 Danger-0.038
 nine-0.036
 thirteen-0.035
 arc-0.034
-0.034
Token wanted
Token ID2227
Feature activation+1.52e-02

Pos logit contributions
 Danger+0.097
 nine+0.095
+0.092
 thirteen+0.087
 Ab+0.087
Neg logit contributions
ingu-0.121
tto-0.117
ascal-0.111
 pistol-0.111
ravings-0.111
Token the
Token ID262
Feature activation-7.78e-03

Pos logit contributions
 Danger+0.019
 nine+0.019
+0.018
 Ab+0.017
 Jen+0.016
Neg logit contributions
ingu-0.031
tto-0.030
ascal-0.029
ravings-0.029
affle-0.028
Token ball
Token ID2613
Feature activation-2.38e-02

Pos logit contributions
ingu+0.013
tto+0.012
 pistol+0.012
ravings+0.012
 brand+0.011
Neg logit contributions
 Danger-0.013
 nine-0.012
-0.012
 thirteen-0.011
 Ab-0.011
Token song
Token ID3496
Feature activation-4.32e-02

Pos logit contributions
 Danger+0.039
 nine+0.038
+0.037
 thirteen+0.036
 Ab+0.035
Neg logit contributions
ingu-0.028
tto-0.026
 pistol-0.025
 brand-0.025
ascal-0.025
Token.
Token ID13
Feature activation-2.28e-03

Pos logit contributions
ingu+0.070
 pistol+0.068
 brand+0.067
tto+0.067
pron+0.065
Neg logit contributions
 Danger-0.068
 nine-0.063
 thirteen-0.061
-0.061
 Ab-0.059
Token
Token ID198
Feature activation-3.10e-02

Pos logit contributions
ingu+0.004
tto+0.004
 pistol+0.004
ascal+0.004
ravings+0.004
Neg logit contributions
 Danger-0.003
 nine-0.003
-0.003
 thirteen-0.003
 Ab-0.003
Token
Token ID198
Feature activation-3.07e-02

Pos logit contributions
ingu+0.074
ravings+0.072
ascal+0.070
 pistol+0.069
 brand+0.069
Neg logit contributions
-0.031
 Danger-0.027
 nine-0.027
 Jen-0.024
 Ab-0.023
TokenWh
Token ID1199
Feature activation-2.94e-02

Pos logit contributions
ingu+0.059
tto+0.056
ascal+0.055
ravings+0.054
 pistol+0.054
Neg logit contributions
 Danger-0.041
-0.041
 nine-0.041
 thirteen-0.036
 Ab-0.036
Tokenisk
Token ID1984
Feature activation-2.59e-01

Pos logit contributions
 pistol+0.026
ingu+0.026
 brand+0.026
pron+0.025
tto+0.025
Neg logit contributions
 Danger-0.066
 nine-0.066
-0.064
 thirteen-0.061
 Jen-0.060
Tokeners
Token ID364
Feature activation-2.91e-02

Pos logit contributions
ingu+0.282
tto+0.275
ascal+0.243
affle+0.236
 pistol+0.231
Neg logit contributions
 Danger-0.553
-0.537
 nine-0.537
 Ab-0.513
 arc-0.508
Token wanted
Token ID2227
Feature activation+1.40e-02

Pos logit contributions
ingu+0.048
tto+0.045
ascal+0.043
 pistol+0.043
ravings+0.041
Neg logit contributions
 Danger-0.047
 nine-0.044
 thirteen-0.043
-0.041
 Ab-0.041
Token to
Token ID284
Feature activation-9.49e-05

Pos logit contributions
 Danger+0.022
 nine+0.021
+0.020
 thirteen+0.020
 arc+0.020
Neg logit contributions
ingu-0.023
tto-0.022
 pistol-0.022
ravings-0.021
 brand-0.021
Token get
Token ID651
Feature activation-2.06e-02

Pos logit contributions
ingu+0.000
 pistol+0.000
pron+0.000
 brand+0.000
tto+0.000
Neg logit contributions
 thirteen-0.000
 nine-0.000
 ago-0.000
 Danger-0.000
 Ab-0.000
Token closer
Token ID5699
Feature activation+1.21e-01

Pos logit contributions
 pistol+0.032
 brand+0.031
 handsome+0.031
tto+0.031
ingu+0.031
Neg logit contributions
 Danger-0.033
 arc-0.031
 thirteen-0.031
 ago-0.030
 nine-0.029
Token scared
Token ID12008
Feature activation+5.05e-02

Pos logit contributions
ingu+0.013
tto+0.012
 pistol+0.012
ascal+0.012
ravings+0.012
Neg logit contributions
 Danger-0.012
 nine-0.012
-0.012
 thirteen-0.011
 Ab-0.011
Token.
Token ID13
Feature activation+7.28e-03

Pos logit contributions
 Danger+0.072
 nine+0.070
+0.067
 thirteen+0.066
 arc+0.064
Neg logit contributions
ingu-0.086
 pistol-0.082
ascal-0.082
tto-0.081
ravings-0.080
Token
Token ID198
Feature activation-1.02e-02

Pos logit contributions
 Danger+0.009
 nine+0.009
+0.009
 thirteen+0.008
 Ab+0.008
Neg logit contributions
ingu-0.014
tto-0.014
ascal-0.013
 pistol-0.013
ravings-0.013
Token
Token ID198
Feature activation-9.99e-03

Pos logit contributions
ingu+0.021
tto+0.020
ravings+0.020
 pistol+0.020
ascal+0.020
Neg logit contributions
 Danger-0.012
-0.012
 nine-0.012
 Ab-0.011
 Jen-0.010
TokenThe
Token ID464
Feature activation+3.82e-02

Pos logit contributions
tto+0.018
ingu+0.017
ascal+0.016
scar+0.016
ravings+0.015
Neg logit contributions
 Danger-0.014
 nine-0.014
 arc-0.013
 thirteen-0.013
 Ab-0.013
Token fireworks
Token ID26056
Feature activation+1.40e-01

Pos logit contributions
+0.061
 Danger+0.061
 Ab+0.058
 nine+0.058
 thirteen+0.056
Neg logit contributions
 pistol-0.060
ingu-0.060
tto-0.057
ascal-0.056
affle-0.056
Token were
Token ID547
Feature activation+5.82e-02

Pos logit contributions
 Danger+0.210
 nine+0.205
+0.197
 Ab+0.191
 thirteen+0.190
Neg logit contributions
ingu-0.237
tto-0.230
 pistol-0.228
ascal-0.218
 brand-0.217
Token not
Token ID407
Feature activation-1.64e-02

Pos logit contributions
 nine+0.089
 Danger+0.088
+0.086
 thirteen+0.081
 Ab+0.081
Neg logit contributions
ingu-0.100
tto-0.096
ascal-0.091
ravings-0.091
 pistol-0.090
Token pretty
Token ID2495
Feature activation+2.86e-02

Pos logit contributions
ingu+0.029
tto+0.028
ascal+0.027
ravings+0.027
affle+0.026
Neg logit contributions
 nine-0.024
 Danger-0.024
-0.023
 Ab-0.022
 thirteen-0.021
Token anymore
Token ID7471
Feature activation-5.53e-03

Pos logit contributions
 Danger+0.053
+0.051
 nine+0.049
 thirteen+0.046
 Ab+0.046
Neg logit contributions
 pistol-0.037
ravings-0.037
ingu-0.037
ascal-0.035
ishing-0.034
Token.
Token ID13
Feature activation+8.05e-03

Pos logit contributions
ingu+0.011
tto+0.011
ascal+0.011
 pistol+0.011
ravings+0.011
Neg logit contributions
 Danger-0.006
 nine-0.006
-0.006
 thirteen-0.006
 Ab-0.006
Token blue
Token ID4171
Feature activation+5.31e-02

Pos logit contributions
ingu+0.010
tto+0.010
ascal+0.009
ravings+0.009
affle+0.009
Neg logit contributions
 nine-0.008
 Danger-0.008
-0.008
 thirteen-0.007
 arc-0.007
Token shirt
Token ID10147
Feature activation-9.28e-02

Pos logit contributions
 Danger+0.097
 nine+0.095
+0.094
 Ab+0.090
 thirteen+0.089
Neg logit contributions
ingu-0.075
tto-0.071
 pistol-0.067
ascal-0.067
ravings-0.066
Token.
Token ID13
Feature activation-7.14e-03

Pos logit contributions
ingu+0.180
tto+0.171
 pistol+0.169
ravings+0.167
 brand+0.166
Neg logit contributions
 Danger-0.122
 nine-0.114
-0.113
 Ab-0.108
 thirteen-0.106
Token They
Token ID1119
Feature activation-1.65e-02

Pos logit contributions
ingu+0.014
tto+0.013
 pistol+0.013
ravings+0.013
ascal+0.012
Neg logit contributions
 Danger-0.009
 nine-0.009
-0.009
 thirteen-0.009
 Ab-0.008
Token make
Token ID787
Feature activation-5.50e-02

Pos logit contributions
ingu+0.032
 pistol+0.030
tto+0.029
affle+0.028
 brand+0.028
Neg logit contributions
 Danger-0.021
 nine-0.020
 Ab-0.019
 Jen-0.018
 thirteen-0.018
Token two
Token ID734
Feature activation+1.38e-01

Pos logit contributions
tto+0.124
ascal+0.122
ingu+0.121
ravings+0.118
scar+0.115
Neg logit contributions
 nine-0.056
-0.055
 Danger-0.054
 thirteen-0.048
 arc-0.046
Token teams
Token ID3466
Feature activation+1.29e-02

Pos logit contributions
 nine+0.202
 Danger+0.201
+0.200
 thirteen+0.184
 Ab+0.181
Neg logit contributions
ingu-0.242
tto-0.238
ascal-0.227
ravings-0.224
 pistol-0.220
Token with
Token ID351
Feature activation-2.21e-02

Pos logit contributions
 Danger+0.019
 Ab+0.018
 nine+0.017
 thirteen+0.017
+0.017
Neg logit contributions
ingu-0.022
 pistol-0.022
tto-0.021
 brand-0.020
ravings-0.020
Token other
Token ID584
Feature activation+1.08e-01

Pos logit contributions
ingu+0.041
tto+0.039
 pistol+0.038
ascal+0.038
 brand+0.038
Neg logit contributions
 Danger-0.030
 nine-0.029
-0.029
 Ab-0.027
 thirteen-0.027
Token kids
Token ID3988
Feature activation+4.11e-02

Pos logit contributions
+0.148
 nine+0.148
 Danger+0.144
 thirteen+0.132
 arc+0.129
Neg logit contributions
tto-0.204
ingu-0.200
ascal-0.191
ravings-0.188
scar-0.186
Token.
Token ID13
Feature activation-5.41e-03

Pos logit contributions
 Danger+0.058
 nine+0.054
 thirteen+0.052
 Ab+0.052
+0.051
Neg logit contributions
ingu-0.074
 pistol-0.070
tto-0.069
ascal-0.067
ravings-0.067
Token smiled
Token ID13541
Feature activation+4.22e-02

Pos logit contributions
 Danger+0.059
 nine+0.057
+0.054
 thirteen+0.053
 Ab+0.052
Neg logit contributions
ingu-0.064
tto-0.062
 pistol-0.058
ascal-0.058
 brand-0.058
Token back
Token ID736
Feature activation-1.70e-02

Pos logit contributions
+0.044
 nine+0.041
 Ab+0.037
 Danger+0.037
 thirteen+0.034
Neg logit contributions
ingu-0.095
tto-0.095
affle-0.093
scar-0.090
ascal-0.090
Token and
Token ID290
Feature activation-1.26e-02

Pos logit contributions
ingu+0.028
tto+0.027
 pistol+0.027
 brand+0.027
ravings+0.026
Neg logit contributions
 Danger-0.027
 nine-0.024
 thirteen-0.024
-0.023
 arc-0.022
Token immediately
Token ID3393
Feature activation-1.06e-02

Pos logit contributions
ingu+0.023
tto+0.022
ascal+0.021
 pistol+0.021
ravings+0.021
Neg logit contributions
 Danger-0.018
 nine-0.018
-0.017
 Ab-0.016
 thirteen-0.016
Token the
Token ID262
Feature activation-5.58e-03

Pos logit contributions
ingu+0.019
tto+0.018
ascal+0.017
 pistol+0.017
ravings+0.017
Neg logit contributions
 Danger-0.016
 nine-0.015
-0.015
 Ab-0.014
 thirteen-0.014
Token two
Token ID734
Feature activation+1.42e-01

Pos logit contributions
 pistol+0.009
ingu+0.009
 brand+0.009
pron+0.009
tto+0.008
Neg logit contributions
 Danger-0.009
 nine-0.008
-0.008
 thirteen-0.008
 Ab-0.007
Token of
Token ID286
Feature activation+8.93e-02

Pos logit contributions
 Danger+0.203
 nine+0.197
+0.190
 thirteen+0.181
 Ab+0.179
Neg logit contributions
ingu-0.257
tto-0.244
 pistol-0.235
ascal-0.235
 brand-0.233
Token them
Token ID606
Feature activation-3.93e-04

Pos logit contributions
 Danger+0.124
 nine+0.120
+0.119
 thirteen+0.110
 Ab+0.109
Neg logit contributions
ingu-0.165
tto-0.158
ascal-0.152
 pistol-0.150
ravings-0.150
Token were
Token ID547
Feature activation+5.19e-02

Pos logit contributions
ingu+0.001
tto+0.001
 pistol+0.001
 brand+0.001
ravings+0.001
Neg logit contributions
 Danger-0.001
 nine-0.001
-0.001
 thirteen-0.001
 Ab-0.001
Token having
Token ID1719
Feature activation-1.26e-03

Pos logit contributions
 Danger+0.081
 nine+0.081
+0.079
 Ab+0.074
 thirteen+0.074
Neg logit contributions
ingu-0.086
tto-0.083
ascal-0.079
 pistol-0.079
ravings-0.078
Token a
Token ID257
Feature activation+1.54e-03

Pos logit contributions
ingu+0.002
tto+0.002
ascal+0.002
ravings+0.002
 pistol+0.002
Neg logit contributions
-0.002
 nine-0.002
 Danger-0.002
 Ab-0.002
 thirteen-0.002
Token was
Token ID373
Feature activation-1.90e-02

Pos logit contributions
ingu+0.071
tto+0.069
 pistol+0.065
ascal+0.064
 brand+0.064
Neg logit contributions
 Danger-0.069
 nine-0.066
 thirteen-0.062
-0.061
 arc-0.061
Token so
Token ID523
Feature activation-7.06e-02

Pos logit contributions
ingu+0.030
tto+0.029
ascal+0.027
 brand+0.027
 pistol+0.027
Neg logit contributions
 Danger-0.032
 nine-0.031
-0.030
 thirteen-0.029
 Ab-0.028
Token fat
Token ID3735
Feature activation+1.43e-02

Pos logit contributions
ingu+0.093
tto+0.093
 brand+0.088
ravings+0.084
ascal+0.083
Neg logit contributions
 Danger-0.134
 nine-0.129
 thirteen-0.123
-0.121
 arc-0.121
Token that
Token ID326
Feature activation-8.14e-02

Pos logit contributions
 Danger+0.021
 nine+0.020
+0.020
 thirteen+0.018
 Ab+0.018
Neg logit contributions
ingu-0.025
tto-0.024
 pistol-0.023
ascal-0.023
ravings-0.023
Token the
Token ID262
Feature activation-4.42e-03

Pos logit contributions
ingu+0.119
tto+0.113
 pistol+0.110
 brand+0.107
ravings+0.106
Neg logit contributions
 Danger-0.145
 nine-0.140
-0.131
 thirteen-0.131
 arc-0.129
Token rain
Token ID6290
Feature activation+1.35e-01

Pos logit contributions
 pistol+0.008
ingu+0.008
 brand+0.007
tto+0.007
pron+0.007
Neg logit contributions
 Danger-0.007
 nine-0.006
-0.006
 thirteen-0.006
 arc-0.005
Token couldn
Token ID3521
Feature activation-3.57e-02

Pos logit contributions
 Danger+0.202
 nine+0.199
+0.195
 Ab+0.182
 thirteen+0.182
Neg logit contributions
ingu-0.233
tto-0.223
ascal-0.214
 pistol-0.212
ravings-0.211
Token't
Token ID470
Feature activation+7.53e-02

Pos logit contributions
tto+0.068
zed+0.065
ingu+0.065
 pistol+0.064
scar+0.063
Neg logit contributions
 nine-0.045
 Danger-0.041
 thirteen-0.040
 arc-0.040
 Ab-0.039
Token reach
Token ID3151
Feature activation+2.43e-03

Pos logit contributions
 nine+0.100
 Danger+0.097
 thirteen+0.097
 ago+0.088
 Flowers+0.086
Neg logit contributions
Years-0.125
ingu-0.124
tto-0.124
zed-0.123
 pistol-0.121
Token him
Token ID683
Feature activation-8.24e-02

Pos logit contributions
 Danger+0.003
 nine+0.003
+0.003
 thirteen+0.003
 arc+0.003
Neg logit contributions
ingu-0.004
tto-0.004
 pistol-0.004
 brand-0.004
ravings-0.004
Token.
Token ID13
Feature activation-4.42e-04

Pos logit contributions
ingu+0.159
tto+0.152
 pistol+0.150
 brand+0.148
ravings+0.146
Neg logit contributions
 Danger-0.106
 nine-0.105
 thirteen-0.095
-0.095
 Ab-0.091
Token ever
Token ID1683
Feature activation+5.91e-02

Pos logit contributions
ingu+0.285
tto+0.275
 brand+0.272
 pistol+0.269
ravings+0.262
Neg logit contributions
 Danger-0.199
 nine-0.187
 thirteen-0.172
 arc-0.170
 Ab-0.168
Token!"
Token ID2474
Feature activation+2.51e-02

Pos logit contributions
 Danger+0.096
 nine+0.085
 thirteen+0.077
 Ab+0.077
+0.077
Neg logit contributions
ingu-0.099
 brand-0.096
tto-0.092
 pistol-0.091
ravings-0.089
Token
Token ID198
Feature activation-2.05e-02

Pos logit contributions
 Danger+0.038
 nine+0.038
 thirteen+0.036
+0.035
 arc+0.034
Neg logit contributions
ingu-0.043
tto-0.040
 pistol-0.039
ascal-0.038
ravings-0.038
Token
Token ID198
Feature activation-2.05e-02

Pos logit contributions
ingu+0.043
ravings+0.041
tto+0.041
 pistol+0.041
ascal+0.040
Neg logit contributions
-0.024
 Danger-0.024
 nine-0.023
 Ab-0.021
 Jen-0.020
TokenThe
Token ID464
Feature activation+2.43e-02

Pos logit contributions
ingu+0.033
tto+0.032
ascal+0.030
Years+0.030
scar+0.030
Neg logit contributions
 Danger-0.032
 nine-0.032
 Ab-0.030
 thirteen-0.030
 arc-0.030
Token two
Token ID734
Feature activation+1.42e-01

Pos logit contributions
 Danger+0.038
 nine+0.037
+0.037
 thirteen+0.034
 Ab+0.034
Neg logit contributions
ingu-0.041
tto-0.040
ascal-0.038
ravings-0.037
 pistol-0.037
Token children
Token ID1751
Feature activation+5.04e-02

Pos logit contributions
 nine+0.242
 Danger+0.242
+0.238
 Ab+0.223
 thirteen+0.223
Neg logit contributions
ingu-0.213
tto-0.208
ascal-0.196
ravings-0.195
 pistol-0.193
Token spent
Token ID3377
Feature activation-7.65e-02

Pos logit contributions
 Danger+0.086
 nine+0.079
 thirteen+0.078
 arc+0.076
 Jen+0.072
Neg logit contributions
ingu-0.078
tto-0.070
 pistol-0.066
affle-0.064
scar-0.064
Token the
Token ID262
Feature activation-1.05e-02

Pos logit contributions
ingu+0.212
ascal+0.211
ravings+0.203
tto+0.200
pron+0.200
Neg logit contributions
 nine-0.050
-0.047
 Jen-0.038
 Ab-0.038
 are-0.037
Token rest
Token ID1334
Feature activation-3.64e-02

Pos logit contributions
ingu+0.020
ascal+0.019
ravings+0.019
tto+0.019
 pistol+0.019
Neg logit contributions
-0.014
 nine-0.013
 Danger-0.013
 Ab-0.012
 thirteen-0.012
Token of
Token ID286
Feature activation+9.05e-02

Pos logit contributions
ingu+0.085
tto+0.083
ascal+0.080
 pistol+0.080
ravings+0.080
Neg logit contributions
 Danger-0.032
 nine-0.032
-0.031
 Ab-0.027
 thirteen-0.027
Token,
Token ID11
Feature activation+1.62e-02

Pos logit contributions
 Danger+0.077
 nine+0.072
+0.070
 thirteen+0.068
 Ab+0.067
Neg logit contributions
ingu-0.087
ravings-0.084
 brand-0.083
 pistol-0.083
tto-0.082
Token but
Token ID475
Feature activation-2.29e-02

Pos logit contributions
 Danger+0.025
 nine+0.023
+0.023
 arc+0.022
 thirteen+0.022
Neg logit contributions
ingu-0.026
 pistol-0.025
 brand-0.025
tto-0.025
pron-0.024
Token she
Token ID673
Feature activation+2.73e-02

Pos logit contributions
ingu+0.043
tto+0.042
ascal+0.041
ravings+0.040
 pistol+0.040
Neg logit contributions
 Danger-0.031
 nine-0.030
-0.030
 Ab-0.027
 thirteen-0.027
Token stumbled
Token ID24241
Feature activation+3.24e-02

Pos logit contributions
+0.035
 nine+0.034
 Danger+0.033
 Ab+0.031
 Jen+0.031
Neg logit contributions
ingu-0.053
 brand-0.051
ravings-0.050
ascal-0.049
 pistol-0.049
Token on
Token ID319
Feature activation+1.24e-02

Pos logit contributions
 Danger+0.047
 nine+0.041
 thirteen+0.040
 arc+0.040
+0.039
Neg logit contributions
ingu-0.060
tto-0.059
 pistol-0.055
ascal-0.055
 brand-0.054
Token a
Token ID257
Feature activation+1.89e-03

Pos logit contributions
 nine+0.012
 Danger+0.012
+0.011
 Ab+0.010
 thirteen+0.010
Neg logit contributions
ingu-0.029
tto-0.028
ascal-0.027
affle-0.027
ravings-0.027
Token rock
Token ID3881
Feature activation-1.36e-02

Pos logit contributions
 Danger+0.002
 nine+0.002
+0.002
 Ab+0.002
 thirteen+0.002
Neg logit contributions
ingu-0.004
tto-0.004
ascal-0.003
ravings-0.003
 pistol-0.003
Token and
Token ID290
Feature activation-1.14e-02

Pos logit contributions
 pistol+0.021
tto+0.020
ingu+0.020
ravings+0.020
pron+0.019
Neg logit contributions
 Danger-0.021
 nine-0.020
 Ab-0.019
 thirteen-0.019
 Flowers-0.019
Token fell
Token ID3214
Feature activation+2.14e-02

Pos logit contributions
ingu+0.019
tto+0.018
 pistol+0.017
ravings+0.017
 brand+0.017
Neg logit contributions
 Danger-0.018
 nine-0.017
-0.017
 arc-0.016
 thirteen-0.016
Token down
Token ID866
Feature activation-1.62e-02

Pos logit contributions
 Danger+0.033
+0.030
 nine+0.030
 thirteen+0.028
 arc+0.028
Neg logit contributions
ingu-0.037
tto-0.036
 pistol-0.036
ascal-0.034
 brand-0.034
Token.
Token ID13
Feature activation+4.62e-03

Pos logit contributions
 pistol+0.023
tto+0.022
zed+0.021
 brand+0.021
 hockey+0.021
Neg logit contributions
 Danger-0.027
 arc-0.025
 thirteen-0.025
 nine-0.024
-0.023
Token
Token ID198
Feature activation-2.01e-02

Pos logit contributions
 Danger+0.004
 nine+0.004
+0.004
 thirteen+0.004
 Ab+0.004
Neg logit contributions
ingu-0.006
tto-0.005
 pistol-0.005
ascal-0.005
ravings-0.005
Token
Token ID198
Feature activation-1.98e-02

Pos logit contributions
ingu+0.045
ravings+0.044
tto+0.044
ascal+0.043
 pistol+0.043
Neg logit contributions
-0.020
 Danger-0.020
 nine-0.019
 Jen-0.017
 Ab-0.017
TokenThey
Token ID2990
Feature activation-9.48e-03

Pos logit contributions
tto+0.027
ingu+0.026
ascal+0.025
Years+0.025
scar+0.025
Neg logit contributions
 Danger-0.036
 Ab-0.035
 nine-0.034
 thirteen-0.034
 Am-0.032
Token started
Token ID2067
Feature activation+4.91e-02

Pos logit contributions
ingu+0.017
tto+0.016
 pistol+0.015
ascal+0.015
ravings+0.015
Neg logit contributions
 Danger-0.014
 nine-0.013
-0.013
 Ab-0.012
 thirteen-0.012
Token to
Token ID284
Feature activation+4.96e-03

Pos logit contributions
 nine+0.059
 Danger+0.058
+0.057
 thirteen+0.051
 Ab+0.051
Neg logit contributions
ingu-0.101
tto-0.099
ascal-0.095
affle-0.094
ravings-0.092
Token scoop
Token ID23529
Feature activation+1.22e-02

Pos logit contributions
 Danger+0.006
 nine+0.006
+0.006
 thirteen+0.005
 Ab+0.005
Neg logit contributions
ingu-0.010
tto-0.009
 pistol-0.009
ascal-0.009
ravings-0.009
Token more
Token ID517
Feature activation+3.85e-02

Pos logit contributions
 Danger+0.015
 nine+0.015
+0.015
 Ab+0.013
 thirteen+0.013
Neg logit contributions
ingu-0.024
tto-0.023
ascal-0.022
ravings-0.022
 pistol-0.022
Token sauce
Token ID10746
Feature activation-8.52e-02

Pos logit contributions
 Danger+0.069
 nine+0.068
+0.067
 thirteen+0.064
 Ab+0.063
Neg logit contributions
ingu-0.055
tto-0.053
ascal-0.050
ravings-0.049
 pistol-0.049
Token from
Token ID422
Feature activation+5.32e-02

Pos logit contributions
ingu+0.167
tto+0.160
 pistol+0.156
ravings+0.153
ascal+0.153
Neg logit contributions
 Danger-0.109
 nine-0.104
-0.098
 Ab-0.096
 thirteen-0.092
Token the
Token ID262
Feature activation-6.39e-03

Pos logit contributions
 Danger+0.070
 nine+0.069
+0.067
 Ab+0.062
 thirteen+0.062
Neg logit contributions
ingu-0.102
tto-0.098
ascal-0.094
 pistol-0.094
ravings-0.094
Token bowl
Token ID9396
Feature activation-3.99e-02

Pos logit contributions
ingu+0.010
tto+0.010
 pistol+0.009
ascal+0.009
ravings+0.009
Neg logit contributions
 Danger-0.010
 nine-0.010
-0.010
 Ab-0.010
 thirteen-0.009
Token check
Token ID2198
Feature activation-5.48e-02

Pos logit contributions
 Danger+0.022
 nine+0.022
 thirteen+0.021
 Ab+0.019
 arc+0.019
Neg logit contributions
ingu-0.035
 pistol-0.034
tto-0.034
 brand-0.032
affle-0.032
Token it
Token ID340
Feature activation+1.83e-03

Pos logit contributions
ingu+0.093
 pistol+0.092
tto+0.085
affle+0.084
 brand+0.083
Neg logit contributions
 Danger-0.080
 arc-0.075
-0.074
 thirteen-0.074
 nine-0.071
Token out
Token ID503
Feature activation+1.21e-02

Pos logit contributions
 Danger+0.003
 nine+0.002
 thirteen+0.002
 Ab+0.002
+0.002
Neg logit contributions
ingu-0.003
tto-0.003
 pistol-0.003
 brand-0.003
affle-0.003
Token,"
Token ID553
Feature activation+6.68e-02

Pos logit contributions
 Danger+0.016
 arc+0.014
 nine+0.014
 thirteen+0.014
 Sylv+0.013
Neg logit contributions
ingu-0.022
 brand-0.021
 pistol-0.020
tto-0.020
udd-0.019
Token Ben
Token ID3932
Feature activation-8.45e-02

Pos logit contributions
 Danger+0.102
 nine+0.100
 thirteen+0.097
 arc+0.090
+0.089
Neg logit contributions
ingu-0.111
 pistol-0.106
tto-0.103
scar-0.099
 hockey-0.099
Token said
Token ID531
Feature activation+1.88e-02

Pos logit contributions
ingu+0.149
tto+0.142
 pistol+0.137
ascal+0.135
ravings+0.133
Neg logit contributions
 Danger-0.125
 nine-0.122
 thirteen-0.114
-0.113
 arc-0.110
Token.
Token ID13
Feature activation+1.05e-02

Pos logit contributions
 Danger+0.025
 nine+0.024
 thirteen+0.023
+0.022
 arc+0.021
Neg logit contributions
ingu-0.035
tto-0.034
 pistol-0.034
ascal-0.033
 brand-0.032
Token "
Token ID366
Feature activation-1.81e-02

Pos logit contributions
 Danger+0.014
 nine+0.014
+0.013
 Ab+0.012
 thirteen+0.012
Neg logit contributions
ingu-0.020
tto-0.020
ascal-0.019
ravings-0.019
 brand-0.019
TokenBut
Token ID1537
Feature activation+8.43e-02

Pos logit contributions
ingu+0.033
tto+0.032
ascal+0.032
 pistol+0.031
Years+0.031
Neg logit contributions
 nine-0.024
 Danger-0.023
 Ab-0.022
-0.022
 thirteen-0.021
Token be
Token ID307
Feature activation+3.08e-04

Pos logit contributions
 Danger+0.115
 nine+0.111
 thirteen+0.104
+0.100
adies+0.095
Neg logit contributions
 pistol-0.143
ingu-0.143
 brand-0.140
tto-0.129
 hockey-0.129
Token quiet
Token ID5897
Feature activation-5.59e-03

Pos logit contributions
 nine+0.001
+0.000
 Danger+0.000
 thirteen+0.000
 Jen+0.000
Neg logit contributions
ingu-0.001
tto-0.000
ascal-0.000
ravings-0.000
 pistol-0.000
Token together
Token ID1978
Feature activation+4.18e-03

Pos logit contributions
ingu+0.171
tto+0.162
ravings+0.159
 brand+0.157
 pistol+0.157
Neg logit contributions
 Danger-0.082
 nine-0.077
-0.074
 thirteen-0.071
 Ab-0.070
Token."
Token ID526
Feature activation+2.70e-02

Pos logit contributions
 Danger+0.004
 nine+0.004
+0.004
 thirteen+0.004
 Ab+0.004
Neg logit contributions
ingu-0.009
tto-0.009
ravings-0.009
 pistol-0.008
ascal-0.008
Token
Token ID198
Feature activation-1.64e-02

Pos logit contributions
 Danger+0.035
 nine+0.035
+0.033
 thirteen+0.032
 Ab+0.031
Neg logit contributions
ingu-0.052
tto-0.050
 pistol-0.048
ravings-0.048
ascal-0.048
Token
Token ID198
Feature activation-1.60e-02

Pos logit contributions
ingu+0.042
ascal+0.042
ravings+0.041
 pistol+0.041
affle+0.040
Neg logit contributions
-0.013
 Jen-0.010
 Danger-0.009
 Ab-0.009
 nine-0.009
TokenAfter
Token ID3260
Feature activation+8.24e-02

Pos logit contributions
ingu+0.029
tto+0.027
ascal+0.027
 pistol+0.026
ravings+0.026
Neg logit contributions
 Danger-0.023
 nine-0.023
-0.023
 Ab-0.021
 thirteen-0.021
Token they
Token ID484
Feature activation+1.42e-02

Pos logit contributions
 Danger+0.104
 nine+0.103
+0.100
 Ab+0.093
 thirteen+0.091
Neg logit contributions
ingu-0.163
tto-0.157
ascal-0.152
ravings-0.151
 pistol-0.150
Token drank
Token ID24070
Feature activation-3.50e-02

Pos logit contributions
 Danger+0.022
 nine+0.022
 thirteen+0.021
+0.020
 arc+0.020
Neg logit contributions
ingu-0.023
tto-0.022
 brand-0.021
ravings-0.020
ascal-0.020
Token juice
Token ID13135
Feature activation+1.01e-02

Pos logit contributions
ingu+0.072
tto+0.070
 pistol+0.067
ascal+0.067
ravings+0.067
Neg logit contributions
 Danger-0.041
 nine-0.040
-0.039
 thirteen-0.036
 Ab-0.035
Token,
Token ID11
Feature activation+1.55e-02

Pos logit contributions
+0.008
 nine+0.008
 Danger+0.007
 Ab+0.007
 are+0.006
Neg logit contributions
ingu-0.024
ascal-0.024
tto-0.024
affle-0.023
ravings-0.023
Token Tim
Token ID5045
Feature activation+3.18e-02

Pos logit contributions
 Danger+0.022
+0.021
 thirteen+0.021
 nine+0.020
 arc+0.018
Neg logit contributions
ingu-0.029
 pistol-0.028
 brand-0.027
tto-0.027
pron-0.026
Tokenmy
Token ID1820
Feature activation-6.13e-03

Pos logit contributions
+0.015
 nine+0.013
 paint+0.007
 Jen+0.007
ill+0.006
Neg logit contributions
 brand-0.086
tto-0.086
zed-0.086
ravings-0.084
affle-0.084
Token
Token ID198
Feature activation-1.81e-02

Pos logit contributions
ingu+0.039
tto+0.037
ascal+0.037
ravings+0.037
 pistol+0.037
Neg logit contributions
-0.021
 nine-0.020
 Danger-0.020
 Ab-0.018
 Jen-0.018
Token"
Token ID1
Feature activation+6.00e-02

Pos logit contributions
ingu+0.028
tto+0.028
Years+0.026
scar+0.026
ascal+0.025
Neg logit contributions
 Danger-0.029
 Ab-0.027
 nine-0.026
 arc-0.026
 paint-0.026
TokenReally
Token ID26392
Feature activation+4.68e-03

Pos logit contributions
 Danger+0.078
 nine+0.076
+0.074
 Ab+0.069
 thirteen+0.069
Neg logit contributions
ingu-0.117
tto-0.113
ascal-0.109
 pistol-0.108
ravings-0.107
Token?
Token ID30
Feature activation-1.79e-02

Pos logit contributions
 Danger+0.007
 nine+0.006
+0.006
 thirteen+0.006
 Ab+0.006
Neg logit contributions
ingu-0.009
tto-0.008
ascal-0.008
 pistol-0.008
 brand-0.008
Token Did
Token ID7731
Feature activation+6.69e-02

Pos logit contributions
ingu+0.032
 pistol+0.030
 hockey+0.030
 brand+0.030
tto+0.029
Neg logit contributions
 nine-0.021
 arc-0.020
 Danger-0.020
 thirteen-0.020
 paint-0.019
Token you
Token ID345
Feature activation+7.03e-02

Pos logit contributions
 nine+0.079
 Danger+0.079
 arc+0.074
 thirteen+0.072
+0.070
Neg logit contributions
ingu-0.133
tto-0.122
 pistol-0.119
 brand-0.118
 hockey-0.115
Token ever
Token ID1683
Feature activation+6.78e-02

Pos logit contributions
 Danger+0.079
 nine+0.078
 Ab+0.071
+0.071
 thirteen+0.070
Neg logit contributions
ingu-0.147
tto-0.141
 pistol-0.138
ascal-0.136
 brand-0.136
Token lose
Token ID4425
Feature activation-3.33e-02

Pos logit contributions
 Danger+0.081
 nine+0.080
+0.072
 Ab+0.072
 thirteen+0.071
Neg logit contributions
ingu-0.138
tto-0.130
 pistol-0.127
 brand-0.127
ascal-0.126
Token your
Token ID534
Feature activation+2.10e-02

Pos logit contributions
ingu+0.061
 pistol+0.058
tto+0.058
 brand+0.057
ascal+0.056
Neg logit contributions
 Danger-0.047
-0.044
 nine-0.044
 thirteen-0.042
 Ab-0.041
Token boats
Token ID16659
Feature activation+7.35e-02

Pos logit contributions
 nine+0.032
 Danger+0.031
+0.031
 paint+0.029
 arc+0.028
Neg logit contributions
ingu-0.036
tto-0.035
ascal-0.033
ravings-0.032
scar-0.032
Token?"
Token ID1701
Feature activation+2.16e-02

Pos logit contributions
+0.082
 nine+0.081
 Danger+0.077
 paint+0.070
 thirteen+0.069
Neg logit contributions
ingu-0.153
tto-0.151
ascal-0.146
affle-0.142
ravings-0.141
Token.
Token ID13
Feature activation+1.72e-03

Pos logit contributions
ingu+0.014
 pistol+0.013
tto+0.013
 brand+0.013
ascal+0.013
Neg logit contributions
 Danger-0.010
 nine-0.009
-0.009
 Ab-0.009
 thirteen-0.009
Token She
Token ID1375
Feature activation+2.60e-02

Pos logit contributions
 Danger+0.002
+0.002
 nine+0.002
 thirteen+0.001
 arc+0.001
Neg logit contributions
ingu-0.004
ravings-0.004
tto-0.004
affle-0.003
 brand-0.003
Token had
Token ID550
Feature activation+1.93e-02

Pos logit contributions
 nine+0.033
+0.032
 Danger+0.031
 Ab+0.028
 paint+0.028
Neg logit contributions
ingu-0.051
tto-0.050
ascal-0.049
ravings-0.049
 pistol-0.048
Token many
Token ID867
Feature activation+9.77e-03

Pos logit contributions
 Danger+0.029
+0.026
 nine+0.026
 thirteen+0.025
 Ab+0.025
Neg logit contributions
ingu-0.035
tto-0.032
 brand-0.032
ravings-0.031
pron-0.031
Token colors
Token ID7577
Feature activation+7.74e-02

Pos logit contributions
 Danger+0.012
 nine+0.012
+0.011
 Ab+0.011
 thirteen+0.011
Neg logit contributions
ingu-0.020
tto-0.019
ascal-0.018
 pistol-0.018
ravings-0.018
Token and
Token ID290
Feature activation-1.28e-02

Pos logit contributions
 Danger+0.103
 nine+0.097
+0.095
 Ab+0.089
 thirteen+0.088
Neg logit contributions
ingu-0.149
tto-0.141
 brand-0.138
 pistol-0.137
ascal-0.136
Token made
Token ID925
Feature activation-6.65e-02

Pos logit contributions
ingu+0.025
tto+0.023
 brand+0.023
 pistol+0.022
ascal+0.022
Neg logit contributions
 Danger-0.017
 nine-0.016
-0.016
 thirteen-0.015
 Ab-0.015
Token pretty
Token ID2495
Feature activation+2.17e-02

Pos logit contributions
ingu+0.121
 brand+0.113
tto+0.111
ascal+0.109
ravings+0.108
Neg logit contributions
 Danger-0.094
-0.090
 nine-0.090
 thirteen-0.084
 Ab-0.083
Token pictures
Token ID5986
Feature activation+6.70e-02

Pos logit contributions
 Danger+0.037
 nine+0.034
+0.034
 thirteen+0.032
 Ab+0.031
Neg logit contributions
ingu-0.036
 brand-0.034
ascal-0.031
 pistol-0.031
udd-0.031
Token of
Token ID286
Feature activation+9.34e-02

Pos logit contributions
 Danger+0.110
 nine+0.099
 Ab+0.097
 thirteen+0.094
+0.092
Neg logit contributions
 brand-0.106
ingu-0.106
 pistol-0.095
pron-0.094
ravings-0.093
Token flowers
Token ID12734
Feature activation+1.25e-01

Pos logit contributions
 Danger+0.126
+0.120
 nine+0.120
 thirteen+0.111
 Ab+0.106
Neg logit contributions
ingu-0.177
 brand-0.165
 pistol-0.163
ascal-0.162
tto-0.161
Token
Token ID198
Feature activation-2.16e-02

Pos logit contributions
ingu+0.045
tto+0.043
ravings+0.043
 pistol+0.042
ascal+0.042
Neg logit contributions
 Danger-0.025
-0.025
 nine-0.025
 Ab-0.023
 Jen-0.022
TokenBen
Token ID11696
Feature activation-5.18e-02

Pos logit contributions
tto+0.026
Matthew+0.025
Mic+0.025
Years+0.025
Jeremy+0.024
Neg logit contributions
 Danger-0.039
 thirteen-0.038
 Ab-0.038
 arc-0.037
 nine-0.037
Token and
Token ID290
Feature activation-1.24e-02

Pos logit contributions
ingu+0.095
tto+0.091
ascal+0.088
ravings+0.088
 brand+0.087
Neg logit contributions
-0.072
 nine-0.071
 Danger-0.071
 thirteen-0.065
 Ab-0.064
Token Mia
Token ID32189
Feature activation+2.75e-02

Pos logit contributions
ingu+0.023
 pistol+0.021
tto+0.021
ascal+0.020
ravings+0.020
Neg logit contributions
 Danger-0.017
-0.016
 nine-0.015
 thirteen-0.015
 arc-0.015
Token thought
Token ID1807
Feature activation+2.87e-03

Pos logit contributions
 Danger+0.053
 nine+0.050
 thirteen+0.048
 Ab+0.048
 Jen+0.048
Neg logit contributions
ingu-0.036
 pistol-0.031
tto-0.031
ascal-0.029
 brand-0.028
Token about
Token ID546
Feature activation-6.27e-02

Pos logit contributions
 Danger+0.004
 nine+0.004
+0.004
 Ab+0.003
 thirteen+0.003
Neg logit contributions
ingu-0.006
tto-0.005
ascal-0.005
ravings-0.005
 pistol-0.005
Token it
Token ID340
Feature activation-1.27e-03

Pos logit contributions
ingu+0.125
tto+0.121
 pistol+0.118
 brand+0.116
ascal+0.116
Neg logit contributions
 Danger-0.076
 nine-0.075
-0.072
 thirteen-0.068
 Ab-0.066
Token.
Token ID13
Feature activation+1.97e-03

Pos logit contributions
ingu+0.002
 pistol+0.002
tto+0.002
 brand+0.002
ravings+0.002
Neg logit contributions
 Danger-0.002
 nine-0.002
 thirteen-0.002
 Ab-0.002
-0.002
Token They
Token ID1119
Feature activation-1.40e-02

Pos logit contributions
 Danger+0.002
 nine+0.002
+0.002
 thirteen+0.002
 Ab+0.002
Neg logit contributions
ingu-0.004
 pistol-0.003
tto-0.003
ascal-0.003
ravings-0.003
Token liked
Token ID8288
Feature activation-4.14e-02

Pos logit contributions
ingu+0.024
tto+0.023
 pistol+0.022
ascal+0.022
ravings+0.022
Neg logit contributions
 Danger-0.021
 nine-0.021
-0.020
 Ab-0.019
 thirteen-0.019
Token their
Token ID511
Feature activation-8.15e-04

Pos logit contributions
tto+0.091
ingu+0.090
ascal+0.086
affle+0.084
scar+0.084
Neg logit contributions
 nine-0.044
 Danger-0.043
-0.041
 Jen-0.040
 Ab-0.039
Token told
Token ID1297
Feature activation+3.81e-02

Pos logit contributions
+0.029
 nine+0.026
 Danger+0.024
 Ab+0.023
 paint+0.021
Neg logit contributions
ravings-0.053
ingu-0.053
ascal-0.052
affle-0.051
tto-0.050
Token him
Token ID683
Feature activation-7.65e-02

Pos logit contributions
 Danger+0.041
 nine+0.040
+0.039
 Ab+0.036
 thirteen+0.035
Neg logit contributions
ingu-0.082
tto-0.081
ascal-0.078
ravings-0.077
 pistol-0.077
Token about
Token ID546
Feature activation-6.17e-02

Pos logit contributions
ingu+0.118
tto+0.111
 pistol+0.107
ascal+0.104
ravings+0.104
Neg logit contributions
 Danger-0.130
 nine-0.128
-0.122
 arc-0.120
 thirteen-0.119
Token the
Token ID262
Feature activation-2.65e-03

Pos logit contributions
ingu+0.133
tto+0.129
ascal+0.124
ravings+0.123
affle+0.122
Neg logit contributions
 Danger-0.067
 nine-0.066
-0.064
 Ab-0.060
 thirteen-0.057
Token loud
Token ID7812
Feature activation+4.15e-02

Pos logit contributions
ingu+0.004
tto+0.004
ascal+0.004
 pistol+0.004
ravings+0.004
Neg logit contributions
 Danger-0.004
 nine-0.004
-0.004
 Ab-0.004
 thirteen-0.004
Token sound
Token ID2128
Feature activation-2.54e-02

Pos logit contributions
 Danger+0.064
 nine+0.063
+0.062
 Ab+0.058
 thirteen+0.058
Neg logit contributions
ingu-0.070
tto-0.067
ascal-0.064
 pistol-0.064
ravings-0.064
Token and
Token ID290
Feature activation-1.05e-02

Pos logit contributions
 pistol+0.043
ingu+0.043
 brand+0.042
tto+0.041
ravings+0.041
Neg logit contributions
 Danger-0.036
 nine-0.035
 Ab-0.033
 thirteen-0.032
 arc-0.031
Token the
Token ID262
Feature activation-2.37e-03

Pos logit contributions
ingu+0.019
tto+0.018
ascal+0.018
ravings+0.018
affle+0.017
Neg logit contributions
 nine-0.015
 Danger-0.015
-0.014
 Ab-0.013
 thirteen-0.013
Token barking
Token ID48961
Feature activation-5.30e-02

Pos logit contributions
ingu+0.004
tto+0.004
ascal+0.004
ravings+0.004
affle+0.004
Neg logit contributions
 Danger-0.003
 nine-0.003
-0.003
 paint-0.003
 thirteen-0.003
Token dog
Token ID3290
Feature activation-4.69e-02

Pos logit contributions
ingu+0.095
tto+0.091
ascal+0.086
ravings+0.085
 brand+0.085
Neg logit contributions
 Danger-0.078
 nine-0.076
-0.076
 Ab-0.070
 thirteen-0.069
Token.
Token ID13
Feature activation+4.43e-03

Pos logit contributions
ingu+0.093
tto+0.090
ascal+0.087
ravings+0.086
 pistol+0.085
Neg logit contributions
 Danger-0.058
 nine-0.057
-0.056
 Ab-0.051
 thirteen-0.051
Token Do
Token ID2141
Feature activation+6.67e-02

Pos logit contributions
ingu+0.068
 pistol+0.067
tto+0.066
 brand+0.063
 hockey+0.063
Neg logit contributions
 nine-0.039
 thirteen-0.034
 Danger-0.032
 arc-0.032
 paint-0.032
Token you
Token ID345
Feature activation+6.24e-02

Pos logit contributions
 Danger+0.050
+0.049
 nine+0.047
 thirteen+0.038
 Ab+0.038
Neg logit contributions
ingu-0.166
tto-0.163
ravings-0.159
ascal-0.159
 pistol-0.157
Token want
Token ID765
Feature activation+7.36e-02

Pos logit contributions
 Danger+0.068
 nine+0.067
 thirteen+0.064
 Ab+0.061
 arc+0.060
Neg logit contributions
ingu-0.129
affle-0.124
tto-0.121
ascal-0.118
 pistol-0.115
Token to
Token ID284
Feature activation+6.60e-04

Pos logit contributions
 Danger+0.105
 nine+0.103
+0.100
 thirteen+0.095
 Ab+0.095
Neg logit contributions
ingu-0.133
tto-0.127
 pistol-0.123
ascal-0.121
ravings-0.121
Token play
Token ID711
Feature activation-5.83e-02

Pos logit contributions
 Danger+0.001
 nine+0.001
 thirteen+0.001
+0.001
 Ab+0.001
Neg logit contributions
ingu-0.001
 pistol-0.001
tto-0.001
 brand-0.001
affle-0.001
Token with
Token ID351
Feature activation-2.19e-02

Pos logit contributions
ingu+0.129
tto+0.126
ascal+0.123
ravings+0.122
scar+0.119
Neg logit contributions
 Danger-0.059
 nine-0.059
-0.058
 arc-0.051
 paint-0.050
Token me
Token ID502
Feature activation-5.02e-03

Pos logit contributions
ingu+0.040
tto+0.039
ascal+0.038
ravings+0.037
pron+0.037
Neg logit contributions
 Danger-0.031
 nine-0.031
-0.030
 Ab-0.028
 thirteen-0.027
Token?"
Token ID1701
Feature activation+1.36e-02

Pos logit contributions
ingu+0.011
tto+0.011
ascal+0.010
ravings+0.010
 brand+0.010
Neg logit contributions
 nine-0.005
 Danger-0.005
-0.005
 Ab-0.004
 thirteen-0.004
Token Carl
Token ID8124
Feature activation-7.30e-02

Pos logit contributions
+0.017
 Danger+0.017
 nine+0.017
 Ab+0.016
 Jen+0.016
Neg logit contributions
ingu-0.027
tto-0.026
ravings-0.025
ascal-0.025
 brand-0.024
Token looked
Token ID3114
Feature activation-5.74e-02

Pos logit contributions
ingu+0.134
tto+0.129
ravings+0.125
ascal+0.125
 pistol+0.123
Neg logit contributions
 Danger-0.100
-0.099
 nine-0.099
 Ab-0.092
 thirteen-0.090
Token at
Token ID379
Feature activation+7.16e-02

Pos logit contributions
ingu+0.115
tto+0.112
ascal+0.109
ravings+0.108
affle+0.105
Neg logit contributions
 nine-0.070
-0.069
 Danger-0.068
 Ab-0.063
 thirteen-0.061
Token.
Token ID13
Feature activation+4.52e-04

Pos logit contributions
 Danger+0.070
 nine+0.069
 thirteen+0.067
 arc+0.064
+0.062
Neg logit contributions
ingu-0.074
 pistol-0.074
ascal-0.068
tto-0.068
 brand-0.067
Token "
Token ID366
Feature activation-2.86e-02

Pos logit contributions
 Danger+0.001
 nine+0.001
+0.001
 thirteen+0.001
 Ab+0.001
Neg logit contributions
ingu-0.001
tto-0.001
ascal-0.001
 pistol-0.001
ravings-0.001
TokenThere
Token ID1858
Feature activation+4.76e-02

Pos logit contributions
ingu+0.048
tto+0.047
ascal+0.046
 pistol+0.045
scar+0.043
Neg logit contributions
 nine-0.042
 Danger-0.041
 Ab-0.040
 thirteen-0.038
-0.038
Token's
Token ID338
Feature activation+1.05e-02

Pos logit contributions
 Danger+0.053
 nine+0.052
+0.046
 thirteen+0.046
 Ab+0.045
Neg logit contributions
ingu-0.101
tto-0.098
 pistol-0.094
ravings-0.093
 brand-0.092
Token a
Token ID257
Feature activation-3.14e-03

Pos logit contributions
 Danger+0.015
 arc+0.014
 nine+0.014
 thirteen+0.013
 Ab+0.013
Neg logit contributions
 pistol-0.017
 brand-0.017
ingu-0.017
tto-0.016
 hockey-0.015
Token dog
Token ID3290
Feature activation-4.96e-02

Pos logit contributions
ingu+0.005
tto+0.005
ascal+0.005
ravings+0.005
affle+0.005
Neg logit contributions
 nine-0.005
 Danger-0.005
-0.005
 Ab-0.004
 thirteen-0.004
Token!
Token ID0
Feature activation-3.14e-02

Pos logit contributions
ingu+0.084
tto+0.083
 pistol+0.083
ravings+0.079
affle+0.078
Neg logit contributions
 Danger-0.068
 nine-0.067
 thirteen-0.067
 Ab-0.066
 arc-0.062
Token It
Token ID632
Feature activation+1.04e-02

Pos logit contributions
 pistol+0.052
ingu+0.051
tto+0.049
ascal+0.048
 hockey+0.047
Neg logit contributions
 nine-0.045
 thirteen-0.042
 arc-0.042
 paint-0.039
 ind-0.037
Token might
Token ID1244
Feature activation-2.90e-02

Pos logit contributions
 nine+0.014
 Danger+0.013
 Ab+0.012
 arc+0.012
 thirteen+0.012
Neg logit contributions
tto-0.019
ingu-0.019
 pistol-0.019
affle-0.018
ascal-0.018
Token bite
Token ID13197
Feature activation+8.42e-03

Pos logit contributions
 pistol+0.050
tto+0.050
ingu+0.048
 brand+0.047
affle+0.046
Neg logit contributions
 nine-0.040
 Danger-0.038
 thirteen-0.037
 Ab-0.037
 arc-0.036
Token us
Token ID514
Feature activation+2.58e-02

Pos logit contributions
 Danger+0.012
 nine+0.011
+0.011
 Ab+0.010
 thirteen+0.010
Neg logit contributions
ingu-0.015
tto-0.015
 pistol-0.014
ravings-0.014
ascal-0.014
TokenBut
Token ID1537
Feature activation+7.11e-02

Pos logit contributions
tto+0.038
Years+0.036
ingu+0.035
Days+0.034
scar+0.034
Neg logit contributions
 nine-0.047
 Danger-0.046
 thirteen-0.046
 arc-0.045
 Ab-0.045
Token she
Token ID673
Feature activation+1.97e-02

Pos logit contributions
 Danger+0.130
 thirteen+0.122
+0.112
 arc+0.112
 nine+0.103
Neg logit contributions
zed-0.094
 brand-0.092
ingu-0.088
 pistol-0.086
Years-0.086
Token didn
Token ID1422
Feature activation-3.64e-02

Pos logit contributions
+0.028
 nine+0.026
 Danger+0.026
 Ab+0.025
 Jen+0.023
Neg logit contributions
ingu-0.037
 brand-0.035
 pistol-0.035
ascal-0.034
ravings-0.034
Token't
Token ID470
Feature activation+8.16e-02

Pos logit contributions
tto+0.069
ingu+0.066
zed+0.063
 pistol+0.063
 brand+0.063
Neg logit contributions
 nine-0.045
 arc-0.042
 thirteen-0.042
 Ab-0.042
 Danger-0.039
Token know
Token ID760
Feature activation+4.11e-02

Pos logit contributions
 Danger+0.086
 nine+0.085
 thirteen+0.081
+0.078
 arc+0.074
Neg logit contributions
ingu-0.171
tto-0.165
ascal-0.162
ravings-0.161
 pistol-0.159
Token how
Token ID703
Feature activation-1.66e-01

Pos logit contributions
 Danger+0.076
 nine+0.072
+0.072
 thirteen+0.070
 arc+0.068
Neg logit contributions
ingu-0.054
 brand-0.052
 pistol-0.049
tto-0.049
ascal-0.048
Token to
Token ID284
Feature activation+2.54e-04

Pos logit contributions
ingu+0.239
 brand+0.238
tto+0.233
 pistol+0.232
ravings+0.227
Neg logit contributions
 nine-0.277
 Danger-0.273
 thirteen-0.267
 arc-0.256
-0.246
Token mind
Token ID2000
Feature activation-2.61e-02

Pos logit contributions
 thirteen+0.000
 nine+0.000
 Danger+0.000
 ago+0.000
 Ab+0.000
Neg logit contributions
ingu-0.000
tto-0.000
 pistol-0.000
ascal-0.000
ravings-0.000
Token her
Token ID607
Feature activation-1.18e-02

Pos logit contributions
ingu+0.045
 pistol+0.043
ravings+0.042
ascal+0.042
 brand+0.042
Neg logit contributions
 Danger-0.038
 nine-0.037
 thirteen-0.035
-0.034
 arc-0.033
Token own
Token ID898
Feature activation+1.82e-02

Pos logit contributions
ingu+0.018
tto+0.017
ascal+0.016
 pistol+0.016
ravings+0.016
Neg logit contributions
 Danger-0.021
 nine-0.020
-0.020
 Ab-0.019
 thirteen-0.019
Token business
Token ID1597
Feature activation-9.34e-02

Pos logit contributions
 nine+0.031
 Danger+0.031
+0.030
 thirteen+0.030
 Ab+0.028
Neg logit contributions
ingu-0.026
 pistol-0.026
ravings-0.025
 brand-0.025
tto-0.025
Token did
Token ID750
Feature activation-2.50e-02

Pos logit contributions
ingu+0.165
tto+0.157
ascal+0.154
ravings+0.152
 pistol+0.149
Neg logit contributions
 Danger-0.127
 nine-0.125
-0.125
 Ab-0.114
 thirteen-0.112
Token not
Token ID407
Feature activation-2.88e-02

Pos logit contributions
ingu+0.040
tto+0.039
 pistol+0.037
ravings+0.037
ascal+0.037
Neg logit contributions
 Danger-0.040
 nine-0.039
-0.038
 Ab-0.037
 thirteen-0.036
Token like
Token ID588
Feature activation+2.68e-02

Pos logit contributions
ingu+0.061
tto+0.058
 pistol+0.058
ravings+0.057
affle+0.057
Neg logit contributions
 Danger-0.029
 nine-0.028
 thirteen-0.027
 Ab-0.026
-0.026
Token math
Token ID10688
Feature activation-1.48e-02

Pos logit contributions
 nine+0.034
 Danger+0.033
+0.033
 paint+0.029
 Jen+0.029
Neg logit contributions
tto-0.055
ingu-0.054
ascal-0.052
affle-0.051
scar-0.050
Token.
Token ID13
Feature activation-3.43e-05

Pos logit contributions
ingu+0.034
tto+0.034
ascal+0.033
affle+0.031
ravings+0.031
Neg logit contributions
-0.015
 nine-0.014
 Danger-0.013
 thirteen-0.011
 are-0.011
Token Max
Token ID5436
Feature activation-1.51e-01

Pos logit contributions
ingu+0.000
tto+0.000
ascal+0.000
ravings+0.000
 pistol+0.000
Neg logit contributions
 Danger-0.000
 nine-0.000
-0.000
 Ab-0.000
 thirteen-0.000
Token wanted
Token ID2227
Feature activation+1.62e-02

Pos logit contributions
ingu+0.283
tto+0.270
ascal+0.265
 brand+0.261
ravings+0.260
Neg logit contributions
-0.208
 nine-0.201
 Danger-0.201
 thirteen-0.180
 Ab-0.180
Token to
Token ID284
Feature activation+1.54e-04

Pos logit contributions
 nine+0.020
 Danger+0.019
+0.019
 thirteen+0.017
 Ab+0.017
Neg logit contributions
ingu-0.033
tto-0.033
ascal-0.032
affle-0.031
ravings-0.031
Token play
Token ID711
Feature activation-5.89e-02

Pos logit contributions
 Danger+0.000
 nine+0.000
 thirteen+0.000
 Ab+0.000
 arc+0.000
Neg logit contributions
ingu-0.000
ravings-0.000
tto-0.000
 pistol-0.000
affle-0.000
Token and
Token ID290
Feature activation-1.64e-02

Pos logit contributions
tto+0.128
ingu+0.127
ascal+0.124
scar+0.119
ravings+0.116
Neg logit contributions
 nine-0.066
-0.064
 Danger-0.063
 paint-0.057
 are-0.053
Token not
Token ID407
Feature activation-2.84e-02

Pos logit contributions
ingu+0.030
 brand+0.029
 pistol+0.029
ravings+0.028
zed+0.028
Neg logit contributions
 Danger-0.021
 nine-0.020
 thirteen-0.019
 Ab-0.019
 arc-0.019
Token wanted
Token ID2227
Feature activation+1.19e-02

Pos logit contributions
ingu+0.088
tto+0.085
 pistol+0.081
ascal+0.081
ravings+0.080
Neg logit contributions
 Danger-0.070
 nine-0.068
-0.065
 thirteen-0.062
 Ab-0.062
Token to
Token ID284
Feature activation-1.52e-03

Pos logit contributions
 Danger+0.018
 nine+0.017
+0.017
 arc+0.017
 thirteen+0.016
Neg logit contributions
ingu-0.020
tto-0.019
 pistol-0.019
 brand-0.018
ravings-0.018
Token go
Token ID467
Feature activation+7.31e-03

Pos logit contributions
ingu+0.003
tto+0.003
 pistol+0.003
ravings+0.003
 brand+0.003
Neg logit contributions
 nine-0.002
 Danger-0.002
 thirteen-0.002
 ago-0.002
 arc-0.002
Token on
Token ID319
Feature activation+5.03e-03

Pos logit contributions
 Danger+0.012
 thirteen+0.011
 nine+0.011
 arc+0.010
+0.010
Neg logit contributions
 pistol-0.012
ingu-0.012
 brand-0.011
tto-0.011
affle-0.011
Token an
Token ID281
Feature activation-4.65e-04

Pos logit contributions
 Danger+0.006
 nine+0.006
+0.005
 Ab+0.005
 thirteen+0.005
Neg logit contributions
ingu-0.011
tto-0.010
ascal-0.010
ravings-0.010
 pistol-0.010
Token adventure
Token ID8855
Feature activation-1.33e-01

Pos logit contributions
ingu+0.001
tto+0.001
ascal+0.001
 pistol+0.001
ravings+0.001
Neg logit contributions
 nine-0.001
-0.001
 Danger-0.001
 Ab-0.001
 thirteen-0.001
Token so
Token ID523
Feature activation-6.98e-02

Pos logit contributions
ingu+0.245
tto+0.237
 pistol+0.232
 brand+0.228
ravings+0.226
Neg logit contributions
 Danger-0.183
 nine-0.176
-0.166
 thirteen-0.162
 Ab-0.156
Token he
Token ID339
Feature activation-3.27e-02

Pos logit contributions
ingu+0.104
tto+0.099
 pistol+0.094
ascal+0.094
ravings+0.093
Neg logit contributions
 Danger-0.122
 nine-0.120
-0.117
 thirteen-0.112
 Ab-0.110
Token decided
Token ID3066
Feature activation+7.84e-02

Pos logit contributions
ingu+0.064
tto+0.061
ascal+0.060
ravings+0.059
 pistol+0.059
Neg logit contributions
 Danger-0.042
-0.041
 nine-0.041
 Ab-0.038
 thirteen-0.037
Token to
Token ID284
Feature activation-1.07e-03

Pos logit contributions
 Danger+0.117
 nine+0.114
+0.109
 thirteen+0.106
 arc+0.104
Neg logit contributions
ingu-0.135
tto-0.131
 pistol-0.126
 brand-0.125
ravings-0.123
Token climb
Token ID12080
Feature activation+6.56e-02

Pos logit contributions
ingu+0.002
tto+0.002
 pistol+0.002
zed+0.002
ravings+0.002
Neg logit contributions
 nine-0.001
 thirteen-0.001
 Danger-0.001
 arc-0.001
 ago-0.001
Token the
Token ID262
Feature activation-4.65e-03

Pos logit contributions
 Danger+0.073
 nine+0.070
+0.069
 thirteen+0.064
 Ab+0.062
Neg logit contributions
ingu-0.131
tto-0.126
 pistol-0.122
ascal-0.122
ravings-0.121
Token book
Token ID1492
Feature activation-1.00e-02

Pos logit contributions
ingu+0.008
 pistol+0.007
 brand+0.007
ravings+0.007
affle+0.007
Neg logit contributions
 Danger-0.007
-0.007
 Ab-0.007
 nine-0.007
 Jen-0.007
Token.
Token ID13
Feature activation+9.12e-03

Pos logit contributions
ingu+0.019
tto+0.018
 pistol+0.018
 brand+0.018
ravings+0.018
Neg logit contributions
 Danger-0.013
 nine-0.012
-0.012
 thirteen-0.012
 Ab-0.012
Token They
Token ID1119
Feature activation-7.73e-03

Pos logit contributions
 nine+0.011
 Danger+0.011
+0.010
 thirteen+0.010
 Ab+0.009
Neg logit contributions
ingu-0.018
ravings-0.017
tto-0.017
 brand-0.017
ascal-0.016
Token hugged
Token ID41130
Feature activation-2.64e-02

Pos logit contributions
ingu+0.013
tto+0.012
 pistol+0.011
ascal+0.011
 brand+0.011
Neg logit contributions
 Danger-0.012
 nine-0.012
 thirteen-0.011
-0.011
 Ab-0.011
Token each
Token ID1123
Feature activation-1.81e-01

Pos logit contributions
ingu+0.046
 pistol+0.042
ascal+0.042
tto+0.042
ravings+0.041
Neg logit contributions
 Danger-0.040
-0.038
 nine-0.038
 thirteen-0.036
 Ab-0.034
Token other
Token ID584
Feature activation+1.14e-01

Pos logit contributions
ingu+0.320
 pistol+0.291
tto+0.279
affle+0.276
ascal+0.273
Neg logit contributions
 Danger-0.258
 thirteen-0.247
 Ab-0.245
 arc-0.242
-0.241
Token.
Token ID13
Feature activation+9.25e-03

Pos logit contributions
 Danger+0.152
 nine+0.144
+0.134
 Ab+0.132
 thirteen+0.131
Neg logit contributions
ingu-0.222
tto-0.208
 pistol-0.205
 brand-0.202
ascal-0.200
Token
Token ID198
Feature activation-1.35e-02

Pos logit contributions
 Danger+0.011
 nine+0.011
 thirteen+0.011
+0.011
 Ab+0.010
Neg logit contributions
ingu-0.018
ravings-0.017
tto-0.017
 brand-0.017
ascal-0.017
Token
Token ID198
Feature activation-1.33e-02

Pos logit contributions
ingu+0.028
ravings+0.027
 pistol+0.027
ascal+0.027
tto+0.027
Neg logit contributions
-0.016
 Danger-0.016
 nine-0.015
 Jen-0.014
 Ab-0.014
Token"
Token ID1
Feature activation+6.30e-02

Pos logit contributions
tto+0.020
ingu+0.020
Years+0.019
pron+0.018
ascal+0.018
Neg logit contributions
 Danger-0.022
 Ab-0.022
 nine-0.021
 thirteen-0.021
 Jen-0.020
Token there
Token ID612
Feature activation+1.08e-02

Pos logit contributions
 Danger+0.011
 nine+0.011
+0.010
 thirteen+0.010
 Ab+0.010
Neg logit contributions
ingu-0.015
tto-0.015
 pistol-0.014
ascal-0.014
 brand-0.014
Token was
Token ID373
Feature activation-2.05e-02

Pos logit contributions
+0.011
 Ab+0.010
 are+0.010
 Danger+0.009
 nine+0.009
Neg logit contributions
ingu-0.025
ascal-0.025
ravings-0.025
 pistol-0.024
pron-0.024
Token a
Token ID257
Feature activation-9.64e-04

Pos logit contributions
ingu+0.041
tto+0.040
 brand+0.038
 pistol+0.038
ascal+0.038
Neg logit contributions
 Danger-0.025
 nine-0.024
-0.023
 thirteen-0.023
 Ab-0.022
Token dog
Token ID3290
Feature activation-5.04e-02

Pos logit contributions
ingu+0.002
tto+0.002
ravings+0.002
zed+0.002
scar+0.002
Neg logit contributions
 nine-0.001
-0.001
 Danger-0.001
 paint-0.001
 arc-0.001
Token named
Token ID3706
Feature activation+2.74e-02

Pos logit contributions
ingu+0.106
tto+0.102
ascal+0.098
ravings+0.098
 brand+0.097
Neg logit contributions
 Danger-0.057
 nine-0.057
-0.055
 Ab-0.050
 Jen-0.048
Token Max
Token ID5436
Feature activation-1.47e-01

Pos logit contributions
 Danger+0.044
+0.043
 nine+0.042
 Jen+0.040
 Ab+0.040
Neg logit contributions
ingu-0.046
ascal-0.044
tto-0.043
ravings-0.043
affle-0.042
Token.
Token ID13
Feature activation+1.34e-04

Pos logit contributions
ingu+0.370
tto+0.363
ravings+0.359
affle+0.353
 brand+0.352
Neg logit contributions
-0.111
 nine-0.109
 Danger-0.101
 Jen-0.086
 Ab-0.084
Token Max
Token ID5436
Feature activation-1.47e-01

Pos logit contributions
+0.000
 Danger+0.000
 nine+0.000
 Jen+0.000
 are+0.000
Neg logit contributions
ingu-0.000
ascal-0.000
tto-0.000
ravings-0.000
affle-0.000
Token loved
Token ID6151
Feature activation-7.15e-02

Pos logit contributions
ingu+0.314
ravings+0.311
ascal+0.304
 brand+0.294
ishing+0.289
Neg logit contributions
-0.204
 are-0.166
 have-0.164
 paint-0.144
 Jen-0.140
Token to
Token ID284
Feature activation+1.54e-03

Pos logit contributions
ingu+0.186
tto+0.182
ascal+0.176
ouse+0.175
imm+0.173
Neg logit contributions
 paint-0.052
 Jen-0.048
 nine-0.045
 Danger-0.043
 touch-0.040
Token chew
Token ID34722
Feature activation-1.20e-01

Pos logit contributions
 Danger+0.002
+0.002
 nine+0.002
 paint+0.002
 Ab+0.002
Neg logit contributions
ingu-0.003
tto-0.003
ascal-0.003
ravings-0.003
 brand-0.003