TOP ACTIVATIONS
MAX = 8.712

put the cheese and the ham on the bread . Mom
the ham . I like ham ." Ben said .
. He likes cheese and ham and lettuce too . He
's face . Leo bl ushes . He says , "
because I like cheese and ham and yellow and red .
. It had cheese and ham and lettuce . She did
I want to put the ham . I like ham ."
cheeks . That is a ham ster . A rabbit has
. It has cheese and ham and lettuce . It looks
to poke him . The ham ster bit her and ran
. It had cheese and ham and bread . He also
needs to do and fl ushes the toilet . He hears
tasty sandwich with cheese and ham . She feels hungry and
cheese and ol ives and ham . They see mom 's
a sandwich with cheese and ham . Lily has a bowl
He saw some cheese and ham . He took them and
and put their tooth br ushes away . They go to
hard and had cheese and ham on it . Lily did
ham ster cage . Their ham ster , Fl uffy ,
Do you like cheese and ham ?" L ila

MIN ACTIVATIONS
MIN = -13.608

, a group of mis chie vous mice came by and
so that no more mis chie vous mice could come in
the squirrel got a mis chie vous look in its eye
sweet tune , a mis chie vous fox appeared . "
and replied with a mis chie vous gl int in his
But then , a mis chie vous rabbit came and started
<|endoftext|> Peter was a mis chie vous 3 year old who
The little boy smiled mis chie v ously and said ,
always acted silly and mis chie vous . One
One day a mis chie vous monkey saw the bear
. He was a mis chie vous little baby and always
small boy with a mis chie vous tw inkle in his
went on with his mis chie vous ways , causing problems
old lady with a mis chie vous tw inkle in her
Suddenly , a mis chie vous bird flew by and
modest barn . Two mis chie vous kittens lived in the
at him with a mis chie vous grin . She said
With a mis chie vous gl int in her
The cat grinned mis chie v ously . " Never
One day , a mis chie vous young boy decided to

INTERVAL 3.132 - 8.712
CONTAINS 6.144%

's share our bread and cheese with it instead ." She
and then came back to play . But then
every day , Lily and her mom my would step outside
. They felt the warm sand under their feet .
flour , sugar and eggs inside it . She began to

INTERVAL -2.448 - 3.132
CONTAINS 84.126%

was amazed . After a while , Lucy
. <|endoftext|> Once upon a time , there was a little
squirrel said . " It is my home . I have
world , just waiting to be explored . And so ,
and did not want to touch the chest .

INTERVAL -8.028 - -2.448
CONTAINS 9.721%

a time there was a squirrel . It was very small
over to take a closer look . But when Molly got
Bob was so happy and he smiled for the first time
The old man was disappointed , he had hoped to
and walked back home to show it to his mom my

INTERVAL -13.608 - -8.028
CONTAINS 0.009%

he got to the river bank he was very amazed .
. They were no longer en vious of each other ,
Standing on the river bank was a duck . The
, but the turtle was en vious of the rabbit 's
pond . It was a tort oise ! The all igator
Token put
Token ID1234
Feature activation+1.21e+00

Pos logit contributions
 half+0.081
Mom+0.081
 sticker+0.077
 icing+0.075
 ribbon+0.074
Neg logit contributions
 vill-0.070
 current-0.066
vious-0.066
 challenged-0.066
 ot-0.065
Token the
Token ID262
Feature activation-6.78e-01

Pos logit contributions
Mom+0.044
 wrist+0.044
 ribbon+0.041
 bookmark+0.041
 sticker+0.040
Neg logit contributions
 vill-0.036
 ot-0.035
 current-0.033
 ships-0.033
 padd-0.032
Token cheese
Token ID9891
Feature activation+6.10e+00

Pos logit contributions
 vill+0.027
 ot+0.026
 current+0.025
 crocod+0.023
 eagle+0.023
Neg logit contributions
Mom-0.019
ushes-0.018
Her-0.017
 wrist-0.017
etti-0.016
Token and
Token ID290
Feature activation+1.62e+00

Pos logit contributions
Mom+0.202
 wrist+0.196
 icing+0.191
 bookmark+0.187
 Love+0.185
Neg logit contributions
 ot-0.202
 vill-0.198
 current-0.197
 padd-0.184
 ships-0.184
Token the
Token ID262
Feature activation-6.99e-01

Pos logit contributions
Mom+0.049
ushes+0.048
 wrist+0.047
 sticker+0.046
 bookmark+0.045
Neg logit contributions
 ot-0.058
 current-0.058
 vill-0.057
 padd-0.055
 challenged-0.055
Token ham
Token ID8891
Feature activation+8.42e+00

Pos logit contributions
 ot+0.029
 current+0.029
 vill+0.029
 eagle+0.026
 ranc+0.026
Neg logit contributions
Mom-0.018
ushes-0.017
Her-0.016
rap-0.015
 wrist-0.015
Token on
Token ID319
Feature activation+2.80e+00

Pos logit contributions
Mom+0.308
 wrist+0.279
 bookmark+0.274
 Love+0.273
 icing+0.272
Neg logit contributions
 ot-0.248
 current-0.242
 vill-0.233
 fishermen-0.225
 padd-0.220
Token the
Token ID262
Feature activation-7.30e-01

Pos logit contributions
 wrist+0.108
ushes+0.108
Mom+0.104
 Love+0.103
aps+0.103
Neg logit contributions
 ot-0.072
 current-0.072
 vill-0.071
 ships-0.064
 padd-0.061
Token bread
Token ID8509
Feature activation+3.34e+00

Pos logit contributions
 current+0.027
 vill+0.026
 ot+0.026
 ranc+0.025
 eagle+0.024
Neg logit contributions
ushes-0.023
Mom-0.023
 half-0.020
Anna-0.019
aps-0.019
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
Mom+0.115
Anna+0.104
 bookmark+0.104
Elsa+0.103
 icing+0.101
Neg logit contributions
 ot-0.111
 current-0.109
bank-0.104
 vill-0.103
 ships-0.103
Token Mom
Token ID11254
Feature activation+5.09e+00

Pos logit contributions
 half+0.059
Mom+0.059
 sticker+0.057
 wrist+0.056
 ribbon+0.056
Neg logit contributions
 current-0.049
 ot-0.048
 vill-0.048
 challenged-0.047
 ships-0.045
Token the
Token ID262
Feature activation-8.65e-01

Pos logit contributions
Mom+0.034
 wrist+0.034
ushes+0.033
 scalp+0.031
Her+0.030
Neg logit contributions
 ot-0.031
 vill-0.031
 ships-0.029
vious-0.028
 padd-0.028
Token ham
Token ID8891
Feature activation+8.19e+00

Pos logit contributions
 vill+0.034
 ot+0.033
 current+0.031
 eagle+0.030
vious+0.030
Neg logit contributions
Mom-0.026
ushes-0.024
Her-0.024
 wrist-0.022
Anna-0.022
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
Mom+0.291
 icing+0.261
ushes+0.255
 wrist+0.251
Her+0.250
Neg logit contributions
 ot-0.248
 vill-0.239
 fishermen-0.235
 current-0.229
vious-0.224
Token I
Token ID314
Feature activation+8.31e-01

Pos logit contributions
 half+0.044
 icing+0.043
 sticker+0.041
ushes+0.041
 ribbon+0.041
Neg logit contributions
 ot-0.025
 vill-0.024
 current-0.024
 ranc-0.023
vious-0.022
Token like
Token ID588
Feature activation+3.80e+00

Pos logit contributions
 half+0.029
Mom+0.029
 sticker+0.027
 cookie+0.026
 icing+0.026
Neg logit contributions
 vill-0.029
 challenged-0.027
 current-0.027
 ot-0.027
vious-0.027
Token ham
Token ID8891
Feature activation+8.31e+00

Pos logit contributions
Mom+0.129
ushes+0.118
 wrist+0.116
 ribbon+0.110
 half+0.110
Neg logit contributions
 vill-0.137
 ot-0.136
 ships-0.129
 challenged-0.127
 fishermen-0.124
Token."
Token ID526
Feature activation+2.82e+00

Pos logit contributions
Mom+0.307
 bookmark+0.282
 wrist+0.273
 ribbon+0.273
ushes+0.272
Neg logit contributions
 ot-0.243
 fishermen-0.232
 ranc-0.213
 vill-0.211
 ships-0.209
Token Ben
Token ID3932
Feature activation+2.26e+00

Pos logit contributions
 half+0.079
Mom+0.077
 sticker+0.075
ushes+0.074
 icing+0.073
Neg logit contributions
 vill-0.115
 ot-0.112
 challenged-0.111
 current-0.108
vious-0.105
Token said
Token ID531
Feature activation-6.08e-01

Pos logit contributions
 half+0.075
Mom+0.073
 sticker+0.067
 cookie+0.067
 ribbon+0.065
Neg logit contributions
 vill-0.084
 current-0.083
vious-0.080
 hurricane-0.079
roads-0.078
Token.
Token ID13
Feature activation+1.64e+00

Pos logit contributions
 vill+0.025
 challenged+0.024
 ot+0.024
 current+0.024
vious+0.023
Neg logit contributions
Mom-0.017
 half-0.016
 ribbon-0.016
 icing-0.015
 sticker-0.015
Token
Token ID198
Feature activation+1.87e+00

Pos logit contributions
 half+0.048
 icing+0.047
Mom+0.047
 sticker+0.047
 wrist+0.046
Neg logit contributions
 vill-0.062
 challenged-0.060
 current-0.059
 ot-0.059
vious-0.058
Token.
Token ID13
Feature activation+1.76e+00

Pos logit contributions
Mom+0.154
 half+0.139
ushes+0.136
 ribbon+0.135
 bookmark+0.134
Neg logit contributions
vious-0.153
 vill-0.153
 ot-0.152
 challenged-0.147
 current-0.146
Token He
Token ID679
Feature activation-2.45e-01

Pos logit contributions
 half+0.088
Mom+0.087
 ribbon+0.086
 sticker+0.086
 icing+0.086
Neg logit contributions
 vill-0.030
 current-0.028
vious-0.027
 challenged-0.027
 ot-0.027
Token likes
Token ID7832
Feature activation+3.80e+00

Pos logit contributions
 vill+0.009
 current+0.009
 challenged+0.009
 ot+0.009
vious+0.009
Neg logit contributions
 half-0.007
Mom-0.007
 sticker-0.007
 cookie-0.007
 icing-0.007
Token cheese
Token ID9891
Feature activation+5.96e+00

Pos logit contributions
Mom+0.115
 wrist+0.105
 half+0.103
 bookmark+0.103
 sticker+0.103
Neg logit contributions
 vill-0.144
 ot-0.142
 challenged-0.135
vious-0.135
 ships-0.135
Token and
Token ID290
Feature activation+1.82e+00

Pos logit contributions
Mom+0.220
ushes+0.200
 bookmark+0.199
 wrist+0.196
Elsa+0.194
Neg logit contributions
 ot-0.191
 vill-0.179
vious-0.175
 current-0.174
 fishermen-0.173
Token ham
Token ID8891
Feature activation+8.27e+00

Pos logit contributions
Mom+0.048
ushes+0.043
 sticker+0.041
 wrist+0.040
 bookmark+0.040
Neg logit contributions
 vill-0.076
 ot-0.076
 current-0.076
vious-0.073
 challenged-0.073
Token and
Token ID290
Feature activation+1.80e+00

Pos logit contributions
Mom+0.306
 bookmark+0.290
 ribbon+0.275
Elsa+0.275
Anna+0.270
Neg logit contributions
 ot-0.237
 fishermen-0.232
 current-0.217
vious-0.210
 vill-0.208
Token lettuce
Token ID39406
Feature activation+5.47e+00

Pos logit contributions
Mom+0.047
ushes+0.042
 sticker+0.039
 wrist+0.039
 half+0.038
Neg logit contributions
 ot-0.076
 vill-0.075
 current-0.075
vious-0.073
 challenged-0.073
Token too
Token ID1165
Feature activation+1.07e+00

Pos logit contributions
Mom+0.190
 bookmark+0.167
 wrist+0.165
 icing+0.160
ushes+0.159
Neg logit contributions
 ot-0.191
 current-0.182
vious-0.181
 vill-0.180
 challenged-0.179
Token.
Token ID13
Feature activation+1.78e+00

Pos logit contributions
Mom+0.034
 wrist+0.032
 bookmark+0.031
 ribbon+0.031
 half+0.031
Neg logit contributions
 vill-0.037
vious-0.037
 challenged-0.037
 current-0.036
 ot-0.035
Token He
Token ID679
Feature activation-1.94e-01

Pos logit contributions
 half+0.084
 ribbon+0.083
 icing+0.082
 sticker+0.082
 bookmark+0.081
Neg logit contributions
 vill-0.036
 ot-0.033
 current-0.033
 challenged-0.033
vious-0.032
Token's
Token ID338
Feature activation+2.73e+00

Pos logit contributions
Mom+0.012
 icing+0.011
ushes+0.010
 ribbon+0.010
mm+0.010
Neg logit contributions
 vill-0.010
vious-0.009
 ot-0.009
 challenged-0.009
 padd-0.009
Token face
Token ID1986
Feature activation+1.40e+00

Pos logit contributions
rap+0.086
ushes+0.083
Anna+0.083
Mom+0.081
 icing+0.076
Neg logit contributions
 ot-0.092
 current-0.090
 en-0.084
 ranc-0.083
 vill-0.083
Token.
Token ID13
Feature activation+1.58e+00

Pos logit contributions
Mom+0.047
ushes+0.047
 half+0.046
 wrist+0.046
Anna+0.046
Neg logit contributions
vious-0.041
 challenged-0.039
 vill-0.039
 current-0.039
 ot-0.038
Token Leo
Token ID19632
Feature activation+3.53e-01

Pos logit contributions
 half+0.059
 sticker+0.057
 icing+0.056
 ribbon+0.056
 wrist+0.055
Neg logit contributions
 vill-0.046
 challenged-0.045
 current-0.044
 ot-0.043
vious-0.041
Token bl
Token ID698
Feature activation-1.42e+00

Pos logit contributions
Mom+0.011
 half+0.010
ushes+0.010
 icing+0.010
 wrist+0.010
Neg logit contributions
 vill-0.013
vious-0.013
 ot-0.013
 challenged-0.013
 padd-0.012
Tokenushes
Token ID17237
Feature activation+8.25e+00

Pos logit contributions
vious+0.067
 bust+0.063
 vill+0.063
cient+0.062
 ot+0.061
Neg logit contributions
Mom-0.029
 half-0.025
 icing-0.023
 ribbon-0.023
 cookie-0.022
Token.
Token ID13
Feature activation+1.60e+00

Pos logit contributions
 wrist+0.340
 bookmark+0.297
Mom+0.296
 ribbon+0.285
ra+0.285
Neg logit contributions
vious-0.216
rified-0.206
 vill-0.205
 ships-0.196
 ot-0.193
Token He
Token ID679
Feature activation-3.61e-01

Pos logit contributions
 half+0.067
 sticker+0.065
 ribbon+0.065
Mom+0.065
 wrist+0.064
Neg logit contributions
 vill-0.041
 current-0.039
 challenged-0.039
 ot-0.039
vious-0.037
Token says
Token ID1139
Feature activation+6.44e-02

Pos logit contributions
 vill+0.013
 challenged+0.013
vious+0.012
 ot+0.012
 current+0.012
Neg logit contributions
Mom-0.012
 half-0.012
 sticker-0.011
 icing-0.011
 wrist-0.010
Token,
Token ID11
Feature activation+8.59e-01

Pos logit contributions
Mom+0.003
 half+0.002
 wrist+0.002
 ribbon+0.002
ushes+0.002
Neg logit contributions
 vill-0.002
 ot-0.002
 challenged-0.002
 current-0.002
 ships-0.002
Token "
Token ID366
Feature activation+6.37e-02

Pos logit contributions
 half+0.036
Mom+0.035
ushes+0.034
 icing+0.033
 ribbon+0.033
Neg logit contributions
 vill-0.022
 challenged-0.022
 ot-0.021
 current-0.021
 ranc-0.020
Token because
Token ID780
Feature activation-2.42e+00

Pos logit contributions
Mom+0.084
 half+0.076
 sticker+0.074
 icing+0.074
 ribbon+0.072
Neg logit contributions
 vill-0.108
 challenged-0.107
 current-0.104
vious-0.104
 ot-0.104
Token I
Token ID314
Feature activation+8.56e-01

Pos logit contributions
 vill+0.098
 ot+0.096
 challenged+0.095
 current+0.093
 ships+0.093
Neg logit contributions
Mom-0.064
 half-0.060
 wrist-0.060
 sticker-0.060
 ribbon-0.058
Token like
Token ID588
Feature activation+3.71e+00

Pos logit contributions
 half+0.025
Mom+0.025
 sticker+0.024
 cookie+0.022
 icing+0.022
Neg logit contributions
 vill-0.034
 challenged-0.032
 current-0.032
 ot-0.032
vious-0.032
Token cheese
Token ID9891
Feature activation+5.89e+00

Pos logit contributions
Mom+0.102
ushes+0.091
 half+0.089
 sticker+0.085
 ribbon+0.084
Neg logit contributions
 vill-0.155
 ot-0.155
 challenged-0.149
 ships-0.149
 current-0.148
Token and
Token ID290
Feature activation+1.57e+00

Pos logit contributions
Mom+0.191
 half+0.174
ushes+0.170
 wrist+0.165
 ribbon+0.161
Neg logit contributions
 ot-0.212
 vill-0.212
vious-0.208
 challenged-0.207
 current-0.205
Token ham
Token ID8891
Feature activation+8.24e+00

Pos logit contributions
Mom+0.045
ushes+0.044
 half+0.039
 sticker+0.039
 wrist+0.038
Neg logit contributions
 ot-0.063
 vill-0.062
 current-0.062
 ships-0.059
 challenged-0.058
Token and
Token ID290
Feature activation+1.58e+00

Pos logit contributions
Mom+0.290
 half+0.245
Anna+0.245
 bookmark+0.242
 ribbon+0.242
Neg logit contributions
 ot-0.277
 fishermen-0.271
 current-0.258
 vill-0.254
 ships-0.253
Token yellow
Token ID7872
Feature activation+3.76e+00

Pos logit contributions
Mom+0.043
ushes+0.041
 half+0.036
 wrist+0.036
 sticker+0.036
Neg logit contributions
 ot-0.066
 current-0.065
 vill-0.064
 ships-0.062
 challenged-0.061
Token and
Token ID290
Feature activation+1.58e+00

Pos logit contributions
Mom+0.118
Anna+0.103
ushes+0.103
 half+0.101
 bookmark+0.100
Neg logit contributions
 ot-0.144
 current-0.139
vious-0.138
 vill-0.137
 ships-0.133
Token red
Token ID2266
Feature activation+4.17e+00

Pos logit contributions
Mom+0.042
ushes+0.040
rap+0.037
 wrist+0.036
 half+0.035
Neg logit contributions
 ot-0.064
 current-0.063
 vill-0.063
 challenged-0.060
vious-0.060
Token.
Token ID13
Feature activation+1.48e+00

Pos logit contributions
Mom+0.132
ushes+0.116
Anna+0.116
 bookmark+0.114
 half+0.112
Neg logit contributions
 ot-0.157
 current-0.153
vious-0.151
 vill-0.149
 ships-0.144
Token.
Token ID13
Feature activation+1.54e+00

Pos logit contributions
Mom+0.140
ushes+0.130
Elsa+0.129
Anna+0.126
 bookmark+0.125
Neg logit contributions
 current-0.106
 ot-0.103
 challenged-0.102
vious-0.099
 vill-0.098
Token It
Token ID632
Feature activation+1.44e+00

Pos logit contributions
 half+0.055
 sticker+0.052
Mom+0.051
 icing+0.050
 ribbon+0.049
Neg logit contributions
 vill-0.050
 challenged-0.047
 ot-0.046
 current-0.046
vious-0.045
Token had
Token ID550
Feature activation+3.63e+00

Pos logit contributions
Mom+0.049
 half+0.048
 sticker+0.047
 icing+0.045
ushes+0.045
Neg logit contributions
 vill-0.049
 challenged-0.048
 ot-0.047
 current-0.046
vious-0.046
Token cheese
Token ID9891
Feature activation+5.84e+00

Pos logit contributions
Mom+0.114
 wrist+0.103
 sticker+0.101
 half+0.100
ushes+0.099
Neg logit contributions
 vill-0.133
vious-0.132
 current-0.130
 challenged-0.129
 ot-0.129
Token and
Token ID290
Feature activation+1.35e+00

Pos logit contributions
Mom+0.234
 wrist+0.212
 bookmark+0.207
Elsa+0.207
Anna+0.205
Neg logit contributions
 ot-0.165
 current-0.154
vious-0.149
 vill-0.147
 fishermen-0.146
Token ham
Token ID8891
Feature activation+8.23e+00

Pos logit contributions
Mom+0.036
ushes+0.034
 wrist+0.034
uggle+0.033
rap+0.032
Neg logit contributions
 ot-0.054
 current-0.053
 vill-0.052
 ships-0.049
 challenged-0.049
Token and
Token ID290
Feature activation+1.37e+00

Pos logit contributions
Mom+0.315
 bookmark+0.294
Anna+0.294
Elsa+0.282
 wrist+0.278
Neg logit contributions
 ot-0.230
 fishermen-0.218
 current-0.212
 challenged-0.196
 ships-0.194
Token lettuce
Token ID39406
Feature activation+5.34e+00

Pos logit contributions
Mom+0.035
ushes+0.034
 wrist+0.032
rap+0.031
uggle+0.030
Neg logit contributions
 ot-0.057
 current-0.056
 vill-0.054
 challenged-0.052
 ships-0.052
Token.
Token ID13
Feature activation+1.66e+00

Pos logit contributions
Mom+0.195
 bookmark+0.172
Anna+0.171
 wrist+0.169
Elsa+0.164
Neg logit contributions
 ot-0.178
 current-0.165
vious-0.164
 challenged-0.163
 vill-0.159
Token She
Token ID1375
Feature activation+1.15e+00

Pos logit contributions
 half+0.060
 sticker+0.059
 icing+0.056
Mom+0.056
 ribbon+0.055
Neg logit contributions
 vill-0.051
vious-0.049
 ot-0.049
 challenged-0.047
 current-0.047
Token did
Token ID750
Feature activation+3.40e+00

Pos logit contributions
Mom+0.048
 half+0.048
 sticker+0.046
 cookie+0.044
 icing+0.044
Neg logit contributions
 vill-0.031
 challenged-0.029
 current-0.029
 ot-0.029
vious-0.029
Token I
Token ID314
Feature activation+8.57e-01

Pos logit contributions
 half+0.034
 sticker+0.034
 icing+0.034
 ribbon+0.034
Mom+0.032
Neg logit contributions
 ot-0.024
 vill-0.023
cient-0.022
 current-0.022
 bust-0.020
Token want
Token ID765
Feature activation+6.92e-01

Pos logit contributions
Mom+0.026
 half+0.026
 icing+0.024
 wrist+0.024
 sticker+0.024
Neg logit contributions
 vill-0.032
 challenged-0.032
vious-0.031
 ot-0.031
 current-0.030
Token to
Token ID284
Feature activation-3.01e-01

Pos logit contributions
ushes+0.027
 wrist+0.027
Mom+0.027
kin+0.026
 scalp+0.026
Neg logit contributions
 vill-0.020
 ot-0.020
 padd-0.018
 ships-0.018
 fishermen-0.018
Token put
Token ID1234
Feature activation+1.00e+00

Pos logit contributions
 ot+0.010
 current+0.009
 challenged+0.009
 vill+0.009
 padd+0.009
Neg logit contributions
ushes-0.011
Mom-0.010
 half-0.009
Anna-0.009
 icing-0.009
Token the
Token ID262
Feature activation-8.65e-01

Pos logit contributions
Mom+0.034
 wrist+0.034
ushes+0.033
 scalp+0.031
Her+0.030
Neg logit contributions
 ot-0.031
 vill-0.031
 ships-0.029
vious-0.028
 padd-0.028
Token ham
Token ID8891
Feature activation+8.19e+00

Pos logit contributions
 vill+0.034
 ot+0.033
 current+0.031
 eagle+0.030
vious+0.030
Neg logit contributions
Mom-0.026
ushes-0.024
Her-0.024
 wrist-0.022
Anna-0.022
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
Mom+0.291
 icing+0.261
ushes+0.255
 wrist+0.251
Her+0.250
Neg logit contributions
 ot-0.248
 vill-0.239
 fishermen-0.235
 current-0.229
vious-0.224
Token I
Token ID314
Feature activation+8.31e-01

Pos logit contributions
 half+0.044
 icing+0.043
 sticker+0.041
ushes+0.041
 ribbon+0.041
Neg logit contributions
 ot-0.025
 vill-0.024
 current-0.024
 ranc-0.023
vious-0.022
Token like
Token ID588
Feature activation+3.80e+00

Pos logit contributions
 half+0.029
Mom+0.029
 sticker+0.027
 cookie+0.026
 icing+0.026
Neg logit contributions
 vill-0.029
 challenged-0.027
 current-0.027
 ot-0.027
vious-0.027
Token ham
Token ID8891
Feature activation+8.31e+00

Pos logit contributions
Mom+0.129
ushes+0.118
 wrist+0.116
 ribbon+0.110
 half+0.110
Neg logit contributions
 vill-0.137
 ot-0.136
 ships-0.129
 challenged-0.127
 fishermen-0.124
Token."
Token ID526
Feature activation+2.82e+00

Pos logit contributions
Mom+0.307
 bookmark+0.282
 wrist+0.273
 ribbon+0.273
ushes+0.272
Neg logit contributions
 ot-0.243
 fishermen-0.232
 ranc-0.213
 vill-0.211
 ships-0.209
Token cheeks
Token ID25839
Feature activation+1.17e+00

Pos logit contributions
Mom+0.035
 half+0.033
 sticker+0.031
ushes+0.030
 cookie+0.030
Neg logit contributions
 vill-0.048
 current-0.047
 ot-0.047
 challenged-0.046
vious-0.046
Token.
Token ID13
Feature activation+1.24e+00

Pos logit contributions
Mom+0.034
 half+0.032
ushes+0.031
 wrist+0.031
 sticker+0.031
Neg logit contributions
vious-0.044
 challenged-0.043
 ot-0.042
 vill-0.042
 current-0.041
Token That
Token ID1320
Feature activation-8.10e-01

Pos logit contributions
 half+0.044
Mom+0.042
 sticker+0.042
 icing+0.041
ushes+0.040
Neg logit contributions
 ot-0.039
vious-0.038
 vill-0.038
 current-0.037
 challenged-0.037
Token is
Token ID318
Feature activation+1.41e+00

Pos logit contributions
 vill+0.035
 challenged+0.034
 ot+0.034
 current+0.033
vious+0.033
Neg logit contributions
Mom-0.021
 half-0.020
ushes-0.019
 icing-0.019
 sticker-0.018
Token a
Token ID257
Feature activation+1.72e+00

Pos logit contributions
Mom+0.041
 wrist+0.038
ushes+0.037
 sticker+0.037
 half+0.036
Neg logit contributions
 ot-0.055
 challenged-0.054
 vill-0.054
 current-0.052
 fishermen-0.051
Token ham
Token ID8891
Feature activation+8.18e+00

Pos logit contributions
ushes+0.063
Mom+0.061
 half+0.060
 herself+0.059
 icing+0.058
Neg logit contributions
 ot-0.057
 vill-0.055
 current-0.053
 harbor-0.051
 eagle-0.051
Tokenster
Token ID1706
Feature activation-1.88e+00

Pos logit contributions
Mom+0.327
ushes+0.310
 half+0.298
 icing+0.292
 herself+0.283
Neg logit contributions
 ot-0.237
 vill-0.217
 fishermen-0.209
 current-0.205
 eagle-0.203
Token.
Token ID13
Feature activation+1.25e+00

Pos logit contributions
 ot+0.073
 vill+0.071
 challenged+0.069
vious+0.069
 current+0.067
Neg logit contributions
Mom-0.058
ushes-0.053
 half-0.052
 icing-0.049
 ribbon-0.048
Token A
Token ID317
Feature activation+9.70e-01

Pos logit contributions
 half+0.044
Mom+0.043
 ribbon+0.042
ushes+0.042
 sticker+0.042
Neg logit contributions
 ot-0.039
 vill-0.038
vious-0.038
 challenged-0.037
 current-0.036
Token rabbit
Token ID22746
Feature activation-3.51e+00

Pos logit contributions
Mom+0.033
ushes+0.031
 half+0.031
 herself+0.030
 icing+0.030
Neg logit contributions
 vill-0.034
 ot-0.033
 current-0.032
 challenged-0.032
 eagle-0.031
Token has
Token ID468
Feature activation+4.80e+00

Pos logit contributions
 vill+0.141
 ot+0.137
 challenged+0.137
vious+0.135
 current+0.131
Neg logit contributions
Mom-0.104
 half-0.098
ushes-0.091
 sticker-0.090
 icing-0.090
Token.
Token ID13
Feature activation+6.24e-01

Pos logit contributions
Mom+0.141
 half+0.132
 sticker+0.130
 ribbon+0.127
ushes+0.123
Neg logit contributions
 vill-0.218
 challenged-0.211
 current-0.209
vious-0.209
 ot-0.206
Token It
Token ID632
Feature activation+1.49e+00

Pos logit contributions
 half+0.018
 sticker+0.017
Mom+0.017
 ribbon+0.017
 icing+0.016
Neg logit contributions
 vill-0.025
 challenged-0.024
 current-0.024
 ot-0.023
vious-0.023
Token has
Token ID468
Feature activation+4.53e+00

Pos logit contributions
Mom+0.043
 wrist+0.040
ushes+0.039
 half+0.039
 sticker+0.038
Neg logit contributions
 vill-0.059
 challenged-0.056
 ot-0.056
vious-0.054
 current-0.054
Token cheese
Token ID9891
Feature activation+5.79e+00

Pos logit contributions
Mom+0.133
 wrist+0.130
ushes+0.121
 sticker+0.119
 half+0.118
Neg logit contributions
 vill-0.171
 ot-0.163
vious-0.163
 current-0.162
 challenged-0.158
Token and
Token ID290
Feature activation+1.10e+00

Pos logit contributions
Mom+0.221
ushes+0.202
 wrist+0.200
 half+0.194
Elsa+0.192
Neg logit contributions
 ot-0.171
 vill-0.161
 challenged-0.160
 current-0.160
 fishermen-0.159
Token ham
Token ID8891
Feature activation+8.08e+00

Pos logit contributions
Mom+0.029
ushes+0.029
rap+0.028
 wrist+0.027
uggle+0.026
Neg logit contributions
 ot-0.043
 current-0.042
 vill-0.041
 ships-0.040
 padd-0.040
Token and
Token ID290
Feature activation+1.09e+00

Pos logit contributions
Mom+0.305
 bookmark+0.280
Anna+0.280
 wrist+0.277
Elsa+0.273
Neg logit contributions
 fishermen-0.228
 ot-0.226
 challenged-0.204
 current-0.204
 ships-0.203
Token lettuce
Token ID39406
Feature activation+5.27e+00

Pos logit contributions
Mom+0.027
ushes+0.026
 wrist+0.024
rap+0.024
 half+0.024
Neg logit contributions
 ot-0.046
 current-0.045
 vill-0.045
 ships-0.043
 challenged-0.043
Token.
Token ID13
Feature activation+7.38e-01

Pos logit contributions
Mom+0.186
 wrist+0.162
 bookmark+0.161
Anna+0.160
 sticker+0.155
Neg logit contributions
 ot-0.180
 challenged-0.172
 current-0.168
 fishermen-0.167
 vill-0.165
Token It
Token ID632
Feature activation+1.53e+00

Pos logit contributions
 half+0.018
Mom+0.018
 sticker+0.018
 icing+0.017
 ribbon+0.017
Neg logit contributions
 vill-0.032
 challenged-0.031
 current-0.031
 ot-0.031
vious-0.030
Token looks
Token ID3073
Feature activation-1.76e+00

Pos logit contributions
Mom+0.046
 half+0.043
 wrist+0.042
 sticker+0.042
ushes+0.041
Neg logit contributions
 vill-0.059
 ot-0.057
 challenged-0.056
vious-0.055
 current-0.055
Token to
Token ID284
Feature activation-7.53e-01

Pos logit contributions
Mom+0.039
 icing+0.036
ushes+0.034
 wrist+0.034
mm+0.034
Neg logit contributions
 padd-0.025
 challenged-0.025
 vill-0.024
 ot-0.023
 current-0.023
Token poke
Token ID22620
Feature activation+1.73e-02

Pos logit contributions
 ot+0.027
 current+0.027
 challenged+0.026
 vill+0.026
 padd+0.025
Neg logit contributions
Mom-0.024
ushes-0.024
 icing-0.023
 half-0.023
 sticker-0.022
Token him
Token ID683
Feature activation+8.54e-01

Pos logit contributions
 sticker+0.001
Mom+0.001
 icing+0.001
ushes+0.001
 wrist+0.001
Neg logit contributions
 ot-0.001
 vill-0.001
vious-0.001
 current-0.001
 challenged-0.001
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
Mom+0.029
 icing+0.027
 sticker+0.026
ushes+0.025
Anna+0.025
Neg logit contributions
 challenged-0.030
 ot-0.029
 current-0.029
 vill-0.029
vious-0.028
Token The
Token ID383
Feature activation-6.60e-01

Pos logit contributions
 half+0.034
 sticker+0.033
Mom+0.032
 icing+0.032
 ribbon+0.031
Neg logit contributions
 vill-0.035
 challenged-0.034
 ot-0.033
 current-0.033
vious-0.032
Token ham
Token ID8891
Feature activation+8.07e+00

Pos logit contributions
 vill+0.026
 ot+0.026
 current+0.026
 challenged+0.024
vious+0.023
Neg logit contributions
Mom-0.019
ushes-0.019
 half-0.019
 icing-0.018
 wrist-0.017
Tokenster
Token ID1706
Feature activation-1.82e+00

Pos logit contributions
Mom+0.260
 half+0.237
 icing+0.236
 sticker+0.228
 wrist+0.228
Neg logit contributions
 current-0.282
 ot-0.280
 vill-0.279
 challenged-0.274
vious-0.261
Token bit
Token ID1643
Feature activation-1.02e+00

Pos logit contributions
 vill+0.060
 challenged+0.057
 current+0.057
 ot+0.056
vious+0.056
Neg logit contributions
Mom-0.065
 half-0.064
 sticker-0.062
 icing-0.060
 cookie-0.059
Token her
Token ID607
Feature activation+3.47e+00

Pos logit contributions
 vill+0.039
 current+0.038
 ot+0.038
 challenged+0.038
vious+0.037
Neg logit contributions
Mom-0.031
 half-0.031
 sticker-0.030
 wrist-0.028
 icing-0.028
Token and
Token ID290
Feature activation+9.10e-01

Pos logit contributions
Mom+0.123
Anna+0.115
ushes+0.108
 icing+0.103
 Love+0.102
Neg logit contributions
 ot-0.117
 current-0.115
 vill-0.108
 padd-0.106
 eagle-0.105
Token ran
Token ID4966
Feature activation-3.20e+00

Pos logit contributions
Mom+0.032
ushes+0.030
 sticker+0.030
 half+0.029
 wrist+0.029
Neg logit contributions
 current-0.030
 ot-0.029
 vill-0.029
 challenged-0.029
 padd-0.027
Token.
Token ID13
Feature activation+1.11e+00

Pos logit contributions
Mom+0.040
ushes+0.037
 icing+0.036
 sticker+0.035
 half+0.035
Neg logit contributions
 ot-0.039
 vill-0.039
 challenged-0.039
vious-0.039
 current-0.038
Token It
Token ID632
Feature activation+1.31e+00

Pos logit contributions
 half+0.052
 ribbon+0.051
 icing+0.051
Mom+0.051
 sticker+0.051
Neg logit contributions
 vill-0.022
 challenged-0.020
 current-0.020
 ot-0.020
vious-0.020
Token had
Token ID550
Feature activation+3.57e+00

Pos logit contributions
Mom+0.045
 half+0.044
 sticker+0.043
 icing+0.042
ushes+0.041
Neg logit contributions
 vill-0.045
 challenged-0.043
 ot-0.043
 current-0.042
vious-0.042
Token cheese
Token ID9891
Feature activation+5.73e+00

Pos logit contributions
Mom+0.107
 wrist+0.096
 sticker+0.095
 half+0.094
ushes+0.092
Neg logit contributions
 vill-0.137
vious-0.135
 challenged-0.135
 current-0.134
 ot-0.134
Token and
Token ID290
Feature activation+1.36e+00

Pos logit contributions
Mom+0.227
 wrist+0.207
ushes+0.203
 bookmark+0.202
Elsa+0.199
Neg logit contributions
 ot-0.169
 current-0.159
vious-0.156
 vill-0.154
 fishermen-0.152
Token ham
Token ID8891
Feature activation+8.05e+00

Pos logit contributions
Mom+0.036
ushes+0.035
 wrist+0.034
rap+0.032
 sticker+0.031
Neg logit contributions
 ot-0.055
 current-0.055
 vill-0.054
 challenged-0.051
vious-0.051
Token and
Token ID290
Feature activation+1.37e+00

Pos logit contributions
Mom+0.308
 bookmark+0.284
Anna+0.282
Elsa+0.275
 wrist+0.267
Neg logit contributions
 ot-0.238
 fishermen-0.228
 current-0.221
 challenged-0.211
 padd-0.208
Token bread
Token ID8509
Feature activation+3.11e+00

Pos logit contributions
Mom+0.035
ushes+0.033
 wrist+0.031
rap+0.030
 sticker+0.029
Neg logit contributions
 ot-0.059
 current-0.058
 vill-0.057
 challenged-0.055
vious-0.054
Token.
Token ID13
Feature activation+1.33e+00

Pos logit contributions
Mom+0.115
 bookmark+0.105
Elsa+0.104
 wrist+0.104
Anna+0.104
Neg logit contributions
 ot-0.101
 current-0.092
 fishermen-0.091
vious-0.090
 challenged-0.090
Token He
Token ID679
Feature activation-6.21e-01

Pos logit contributions
 half+0.060
 ribbon+0.059
Mom+0.059
 sticker+0.059
 icing+0.058
Neg logit contributions
 vill-0.029
vious-0.027
 challenged-0.027
 current-0.027
 ot-0.026
Token also
Token ID635
Feature activation+2.40e+00

Pos logit contributions
 vill+0.017
 challenged+0.017
 ot+0.016
 current+0.016
vious+0.016
Neg logit contributions
Mom-0.025
 half-0.025
 sticker-0.024
 icing-0.023
ushes-0.023
Token needs
Token ID2476
Feature activation+9.92e-01

Pos logit contributions
 vill+0.065
 challenged+0.063
vious+0.062
 current+0.062
 ot+0.061
Neg logit contributions
Mom-0.063
 half-0.062
 sticker-0.059
 icing-0.057
 cookie-0.057
Token to
Token ID284
Feature activation-6.60e-01

Pos logit contributions
Mom+0.032
ushes+0.030
 half+0.030
 wrist+0.029
 icing+0.028
Neg logit contributions
 vill-0.035
 ot-0.035
 challenged-0.035
 ships-0.034
 current-0.034
Token do
Token ID466
Feature activation+2.52e+00

Pos logit contributions
 ot+0.022
 current+0.021
 vill+0.021
 challenged+0.021
 ships+0.020
Neg logit contributions
Mom-0.022
ushes-0.022
 half-0.021
 icing-0.020
 bookmark-0.020
Token and
Token ID290
Feature activation+1.49e+00

Pos logit contributions
Mom+0.065
 half+0.063
 sticker+0.059
 ribbon+0.059
 icing+0.058
Neg logit contributions
 vill-0.107
 challenged-0.104
vious-0.102
 ot-0.101
 current-0.100
Token fl
Token ID781
Feature activation-2.05e+00

Pos logit contributions
Mom+0.045
 half+0.044
 sticker+0.042
 icing+0.041
 cookie+0.040
Neg logit contributions
 vill-0.057
 challenged-0.055
 current-0.055
 ot-0.055
vious-0.054
Tokenushes
Token ID17237
Feature activation+8.04e+00

Pos logit contributions
 vill+0.100
 challenged+0.097
 current+0.097
 ot+0.096
vious+0.096
Neg logit contributions
Mom-0.042
 half-0.042
 sticker-0.039
 icing-0.036
 cookie-0.035
Token the
Token ID262
Feature activation-1.17e+00

Pos logit contributions
 wrist+0.298
Mom+0.287
Elsa+0.272
 bookmark+0.271
 ribbon+0.263
Neg logit contributions
 ships-0.243
 ot-0.233
 vill-0.228
 current-0.216
vious-0.213
Token toilet
Token ID16146
Feature activation+4.05e-02

Pos logit contributions
 vill+0.042
 current+0.040
 challenged+0.039
 ot+0.039
vious+0.039
Neg logit contributions
Mom-0.039
 half-0.039
 sticker-0.037
 icing-0.036
 ribbon-0.035
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
Mom+0.001
 half+0.001
 sticker+0.001
 ribbon+0.001
 icing+0.001
Neg logit contributions
 vill-0.002
 challenged-0.002
vious-0.002
 current-0.002
 ot-0.002
Token He
Token ID679
Feature activation-4.84e-01

Pos logit contributions
 half+0.059
Mom+0.057
 sticker+0.057
 icing+0.056
 ribbon+0.056
Neg logit contributions
 vill-0.041
 challenged-0.039
 current-0.038
 ot-0.038
vious-0.037
Token hears
Token ID23180
Feature activation-9.61e-01

Pos logit contributions
 vill+0.019
 challenged+0.018
 current+0.018
 ot+0.018
vious+0.018
Neg logit contributions
 half-0.015
Mom-0.014
 sticker-0.014
 cookie-0.013
 icing-0.013
Token tasty
Token ID25103
Feature activation+3.69e+00

Pos logit contributions
Mom+0.060
 half+0.059
 herself+0.058
ushes+0.056
 icing+0.056
Neg logit contributions
 vill-0.059
 current-0.056
 ot-0.056
 challenged-0.054
 ranc-0.052
Token sandwich
Token ID20433
Feature activation+3.83e+00

Pos logit contributions
Mom+0.106
ushes+0.103
 half+0.092
 herself+0.091
Her+0.088
Neg logit contributions
 vill-0.150
 ot-0.150
 current-0.146
 challenged-0.136
 eagle-0.135
Token with
Token ID351
Feature activation+5.87e-01

Pos logit contributions
Mom+0.133
ushes+0.130
 wrist+0.119
 half+0.119
Elsa+0.118
Neg logit contributions
 ot-0.117
 challenged-0.115
 vill-0.114
vious-0.112
 current-0.111
Token cheese
Token ID9891
Feature activation+5.78e+00

Pos logit contributions
Mom+0.019
 wrist+0.018
Anna+0.017
ushes+0.017
 bookmark+0.017
Neg logit contributions
 ot-0.021
 vill-0.020
vious-0.020
 current-0.019
 padd-0.019
Token and
Token ID290
Feature activation+1.46e+00

Pos logit contributions
Mom+0.204
ushes+0.188
 wrist+0.178
 half+0.176
 sticker+0.172
Neg logit contributions
 ot-0.195
 current-0.186
 vill-0.186
 challenged-0.184
 fishermen-0.183
Token ham
Token ID8891
Feature activation+8.04e+00

Pos logit contributions
Mom+0.037
ushes+0.033
 wrist+0.031
 half+0.031
 sticker+0.031
Neg logit contributions
 vill-0.062
 ot-0.062
 current-0.061
 challenged-0.060
vious-0.059
Token.
Token ID13
Feature activation+1.82e+00

Pos logit contributions
Mom+0.288
 bookmark+0.258
Anna+0.257
 wrist+0.257
 ribbon+0.246
Neg logit contributions
 ot-0.252
 fishermen-0.249
 current-0.233
 vill-0.226
 challenged-0.226
Token She
Token ID1375
Feature activation+1.15e+00

Pos logit contributions
 half+0.061
 sticker+0.059
 icing+0.057
Mom+0.057
 ribbon+0.056
Neg logit contributions
 vill-0.064
 challenged-0.060
vious-0.060
 current-0.058
 ot-0.057
Token feels
Token ID5300
Feature activation-2.48e+00

Pos logit contributions
Mom+0.040
 half+0.039
 sticker+0.037
 icing+0.036
 cookie+0.036
Neg logit contributions
 vill-0.040
 challenged-0.038
 current-0.038
vious-0.038
 ot-0.038
Token hungry
Token ID14720
Feature activation-1.38e+00

Pos logit contributions
 vill+0.089
 ot+0.087
 current+0.085
vious+0.085
 challenged+0.084
Neg logit contributions
Mom-0.082
 half-0.079
 ribbon-0.076
 sticker-0.075
 wrist-0.073
Token and
Token ID290
Feature activation+1.60e+00

Pos logit contributions
vious+0.044
 vill+0.044
 current+0.042
 ot+0.042
 challenged+0.040
Neg logit contributions
Mom-0.049
ushes-0.048
 half-0.045
Elsa-0.045
 wrist-0.045
Token cheese
Token ID9891
Feature activation+5.71e+00

Pos logit contributions
Mom+0.009
 wrist+0.009
 ribbon+0.009
 bookmark+0.009
 sticker+0.009
Neg logit contributions
 ot-0.011
 vill-0.011
 ships-0.011
vious-0.011
 current-0.011
Token and
Token ID290
Feature activation+1.65e+00

Pos logit contributions
Mom+0.207
 wrist+0.202
 bookmark+0.189
ushes+0.186
Elsa+0.184
Neg logit contributions
 ot-0.184
 current-0.176
 vill-0.174
 fishermen-0.170
 challenged-0.167
Token ol
Token ID25776
Feature activation-6.04e-01

Pos logit contributions
Mom+0.047
ushes+0.044
 wrist+0.042
 bookmark+0.042
 sticker+0.041
Neg logit contributions
 current-0.064
 ot-0.063
 vill-0.062
 ships-0.060
 challenged-0.060
Tokenives
Token ID1083
Feature activation+2.73e+00

Pos logit contributions
vious+0.016
 ot+0.014
 vill+0.013
 fishermen+0.013
ules+0.013
Neg logit contributions
 wrist-0.027
Mom-0.027
 half-0.025
 sticker-0.023
 ribbon-0.023
Token and
Token ID290
Feature activation+1.62e+00

Pos logit contributions
 wrist+0.097
Mom+0.096
 bookmark+0.089
Elsa+0.089
Anna+0.087
Neg logit contributions
 ot-0.084
 fishermen-0.078
 vill-0.078
 current-0.077
 ships-0.076
Token ham
Token ID8891
Feature activation+8.00e+00

Pos logit contributions
Mom+0.046
ushes+0.041
 wrist+0.040
 half+0.039
rap+0.039
Neg logit contributions
 current-0.063
 ot-0.063
 vill-0.062
 challenged-0.060
vious-0.059
Token.
Token ID13
Feature activation+1.86e+00

Pos logit contributions
Mom+0.287
 bookmark+0.267
 wrist+0.263
Elsa+0.261
Anna+0.259
Neg logit contributions
 fishermen-0.248
 ot-0.246
 ships-0.227
 current-0.224
 vill-0.219
Token They
Token ID1119
Feature activation+4.21e-01

Pos logit contributions
 half+0.079
 sticker+0.077
 wrist+0.075
 ribbon+0.075
 bookmark+0.075
Neg logit contributions
 ot-0.048
 vill-0.045
 current-0.042
 challenged-0.041
vious-0.041
Token see
Token ID766
Feature activation+3.03e-01

Pos logit contributions
Mom+0.013
 half+0.013
 sticker+0.013
ushes+0.012
 cookie+0.012
Neg logit contributions
 vill-0.015
 challenged-0.015
 ot-0.015
 current-0.015
vious-0.015
Token mom
Token ID1995
Feature activation+2.81e+00

Pos logit contributions
Mom+0.009
 wrist+0.009
 ribbon+0.008
 sticker+0.008
 half+0.008
Neg logit contributions
 ot-0.011
 vill-0.011
vious-0.011
 ships-0.011
 current-0.011
Token's
Token ID338
Feature activation+2.45e+00

Pos logit contributions
Mom+0.090
 ribbon+0.089
 wrist+0.086
 sticker+0.084
 bookmark+0.084
Neg logit contributions
 vill-0.098
 ot-0.097
 challenged-0.096
vious-0.094
 ships-0.089
Token a
Token ID257
Feature activation+1.48e+00

Pos logit contributions
Mom+0.126
 half+0.121
 sticker+0.118
 ribbon+0.112
 wrist+0.111
Neg logit contributions
 vill-0.184
 challenged-0.178
 current-0.175
vious-0.175
 ot-0.174
Token sandwich
Token ID20433
Feature activation+3.59e+00

Pos logit contributions
 half+0.051
Mom+0.051
 sticker+0.050
 cookie+0.047
 icing+0.047
Neg logit contributions
 vill-0.051
 challenged-0.049
 current-0.048
vious-0.048
 ot-0.048
Token with
Token ID351
Feature activation+4.03e-01

Pos logit contributions
Mom+0.100
 half+0.097
 sticker+0.090
ushes+0.090
 icing+0.089
Neg logit contributions
 vill-0.142
 challenged-0.140
 ot-0.139
vious-0.138
 current-0.136
Token cheese
Token ID9891
Feature activation+5.65e+00

Pos logit contributions
Mom+0.012
 wrist+0.012
 sticker+0.011
ushes+0.011
 half+0.011
Neg logit contributions
 vill-0.015
vious-0.015
 ot-0.015
 challenged-0.014
 current-0.014
Token and
Token ID290
Feature activation+9.03e-01

Pos logit contributions
Mom+0.174
ushes+0.159
 half+0.155
 wrist+0.154
 sticker+0.149
Neg logit contributions
 ot-0.213
 vill-0.207
 current-0.203
 challenged-0.202
vious-0.199
Token ham
Token ID8891
Feature activation+7.99e+00

Pos logit contributions
Mom+0.022
 half+0.020
 sticker+0.020
ushes+0.019
 wrist+0.019
Neg logit contributions
 vill-0.039
 ot-0.039
 current-0.038
 challenged-0.038
vious-0.038
Token.
Token ID13
Feature activation+5.26e-01

Pos logit contributions
Mom+0.273
Anna+0.248
 wrist+0.245
 bookmark+0.244
 ribbon+0.240
Neg logit contributions
 ot-0.264
 fishermen-0.258
 vill-0.244
 current-0.243
 challenged-0.239
Token Lily
Token ID20037
Feature activation+3.76e+00

Pos logit contributions
 half+0.018
Mom+0.018
 sticker+0.017
 cookie+0.017
 icing+0.016
Neg logit contributions
 vill-0.018
 challenged-0.018
 current-0.017
 ot-0.017
vious-0.017
Token has
Token ID468
Feature activation+4.66e+00

Pos logit contributions
Mom+0.122
 half+0.121
 sticker+0.116
 icing+0.111
 cookie+0.110
Neg logit contributions
 vill-0.137
 challenged-0.131
 current-0.130
 ot-0.129
vious-0.129
Token a
Token ID257
Feature activation+1.60e+00

Pos logit contributions
Mom+0.151
 wrist+0.138
ushes+0.133
 sticker+0.133
 half+0.131
Neg logit contributions
 vill-0.165
vious-0.162
 challenged-0.160
 ot-0.152
 current-0.152
Token bowl
Token ID9396
Feature activation+3.21e+00

Pos logit contributions
Mom+0.055
 herself+0.052
 half+0.050
ushes+0.050
 ourselves+0.050
Neg logit contributions
 vill-0.055
 ot-0.052
 current-0.051
 challenged-0.050
 fearful-0.048
TokenHe
Token ID1544
Feature activation+4.21e-01

Pos logit contributions
 icing+0.029
 sticker+0.029
 cookie+0.028
 half+0.028
 ribbon+0.027
Neg logit contributions
 vill-0.046
 challenged-0.045
 current-0.044
 ot-0.044
vious-0.042
Token saw
Token ID2497
Feature activation-1.90e+00

Pos logit contributions
 half+0.015
Mom+0.015
 sticker+0.014
 ribbon+0.014
 cookie+0.013
Neg logit contributions
 vill-0.015
 current-0.014
vious-0.014
 ot-0.014
roads-0.013
Token some
Token ID617
Feature activation+7.59e-01

Pos logit contributions
 vill+0.096
 challenged+0.094
rated+0.092
 bust+0.091
vious+0.090
Neg logit contributions
 half-0.042
Mom-0.038
 sticker-0.034
 tape-0.033
 herself-0.032
Token cheese
Token ID9891
Feature activation+5.63e+00

Pos logit contributions
Mom+0.024
 half+0.023
 sticker+0.022
 icing+0.021
 wrist+0.021
Neg logit contributions
 vill-0.029
 current-0.028
 ot-0.028
 challenged-0.027
vious-0.027
Token and
Token ID290
Feature activation+1.07e+00

Pos logit contributions
Mom+0.180
 wrist+0.161
 half+0.161
ushes+0.160
 sticker+0.159
Neg logit contributions
 vill-0.208
 ot-0.207
 current-0.204
 challenged-0.200
vious-0.196
Token ham
Token ID8891
Feature activation+7.96e+00

Pos logit contributions
Mom+0.030
 half+0.030
 sticker+0.029
 cookie+0.027
 icing+0.027
Neg logit contributions
 vill-0.043
 challenged-0.042
 current-0.041
 ot-0.041
vious-0.041
Token.
Token ID13
Feature activation+8.93e-01

Pos logit contributions
Mom+0.264
 bookmark+0.242
 wrist+0.241
 ribbon+0.237
Anna+0.237
Neg logit contributions
 ot-0.275
 current-0.265
 fishermen-0.264
 vill-0.262
 challenged-0.258
Token He
Token ID679
Feature activation-6.71e-01

Pos logit contributions
Mom+0.039
 half+0.039
 sticker+0.038
 ribbon+0.037
 icing+0.037
Neg logit contributions
 vill-0.022
 ot-0.021
 current-0.021
 challenged-0.020
vious-0.020
Token took
Token ID1718
Feature activation-6.33e-01

Pos logit contributions
 vill+0.019
 challenged+0.018
 current+0.018
 ot+0.018
vious+0.018
Neg logit contributions
Mom-0.027
 half-0.027
 sticker-0.026
 cookie-0.025
 icing-0.025
Token them
Token ID606
Feature activation+3.22e-01

Pos logit contributions
 vill+0.024
 ot+0.023
vious+0.023
 current+0.023
 challenged+0.022
Neg logit contributions
Mom-0.019
 wrist-0.019
 sticker-0.018
 ribbon-0.017
ushes-0.017
Token and
Token ID290
Feature activation+1.07e+00

Pos logit contributions
Mom+0.012
 wrist+0.011
 icing+0.011
 sticker+0.011
Anna+0.011
Neg logit contributions
 ot-0.010
 vill-0.010
 challenged-0.010
 padd-0.009
 ships-0.009
Token and
Token ID290
Feature activation+1.48e+00

Pos logit contributions
Anna+0.177
 bookmark+0.177
Mom+0.176
Elsa+0.171
ushes+0.171
Neg logit contributions
 current-0.126
 padd-0.125
 ot-0.120
 overwhelmed-0.114
 challenged-0.113
Token put
Token ID1234
Feature activation+1.08e+00

Pos logit contributions
Mom+0.048
ushes+0.045
rap+0.043
Anna+0.043
 half+0.041
Neg logit contributions
 current-0.049
 padd-0.048
 ot-0.047
 challenged-0.045
 ships-0.045
Token their
Token ID511
Feature activation+3.51e+00

Pos logit contributions
 wrist+0.040
Mom+0.038
Her+0.036
 bookmark+0.036
Anna+0.034
Neg logit contributions
 ot-0.032
 ships-0.030
 vill-0.030
 padd-0.030
 current-0.028
Token tooth
Token ID16162
Feature activation+1.89e+00

Pos logit contributions
Mom+0.127
Anna+0.121
ushes+0.119
etti+0.115
rap+0.113
Neg logit contributions
 vill-0.101
 current-0.100
 ot-0.099
 fearful-0.096
 lonely-0.094
Tokenbr
Token ID1671
Feature activation+1.36e+00

Pos logit contributions
Mom+0.060
 Love+0.057
mm+0.056
 ourselves+0.054
 icing+0.054
Neg logit contributions
vious-0.058
 vill-0.056
 current-0.056
ling-0.055
 ot-0.055
Tokenushes
Token ID17237
Feature activation+7.94e+00

Pos logit contributions
 wrist+0.028
Mom+0.028
 cookie+0.025
 sticker+0.024
 ribbon+0.024
Neg logit contributions
vious-0.059
 vill-0.058
 ot-0.055
 bust-0.054
 challenged-0.054
Token away
Token ID1497
Feature activation+1.25e+00

Pos logit contributions
 wrist+0.334
 bookmark+0.299
Mom+0.298
 Love+0.295
Elsa+0.292
Neg logit contributions
 ot-0.183
vious-0.178
 vill-0.175
 ships-0.172
 padd-0.169
Token.
Token ID13
Feature activation+1.33e+00

Pos logit contributions
Mom+0.040
 wrist+0.036
 half+0.035
 bookmark+0.035
 sticker+0.035
Neg logit contributions
 ot-0.044
 vill-0.044
 current-0.043
 ships-0.042
vious-0.041
Token They
Token ID1119
Feature activation+1.87e-01

Pos logit contributions
 sticker+0.053
 half+0.052
 ribbon+0.052
 bookmark+0.051
 icing+0.051
Neg logit contributions
 challenged-0.035
 current-0.034
 ot-0.033
 vill-0.033
 padd-0.031
Token go
Token ID467
Feature activation+1.69e+00

Pos logit contributions
Mom+0.006
 half+0.006
ushes+0.005
 sticker+0.005
 icing+0.005
Neg logit contributions
 vill-0.007
 ot-0.007
vious-0.007
 current-0.006
 challenged-0.006
Token to
Token ID284
Feature activation-6.33e-01

Pos logit contributions
 half+0.055
 icing+0.054
Mom+0.054
 ribbon+0.053
 wrist+0.051
Neg logit contributions
 vill-0.057
 challenged-0.055
 padd-0.055
vious-0.053
 ot-0.053
Token hard
Token ID1327
Feature activation+2.21e+00

Pos logit contributions
Mom+0.038
 half+0.038
 sticker+0.037
 wrist+0.036
 icing+0.036
Neg logit contributions
 vill-0.037
 current-0.036
 ot-0.035
 challenged-0.035
 bust-0.034
Token and
Token ID290
Feature activation+1.24e+00

Pos logit contributions
Mom+0.060
 half+0.059
 sticker+0.056
 cookie+0.052
 icing+0.052
Neg logit contributions
 vill-0.092
 challenged-0.089
 current-0.089
 ot-0.088
vious-0.088
Token had
Token ID550
Feature activation+3.23e+00

Pos logit contributions
Mom+0.040
 half+0.040
 sticker+0.039
 icing+0.037
 wrist+0.037
Neg logit contributions
 vill-0.044
 challenged-0.043
 current-0.042
 ot-0.042
vious-0.042
Token cheese
Token ID9891
Feature activation+5.55e+00

Pos logit contributions
Mom+0.098
 half+0.089
 sticker+0.089
 wrist+0.087
 cookie+0.084
Neg logit contributions
 vill-0.123
vious-0.120
 challenged-0.119
 current-0.118
 ot-0.116
Token and
Token ID290
Feature activation+1.18e+00

Pos logit contributions
Mom+0.194
 wrist+0.171
 half+0.168
ushes+0.163
 sticker+0.163
Neg logit contributions
 ot-0.185
 vill-0.181
vious-0.180
 current-0.179
 challenged-0.176
Token ham
Token ID8891
Feature activation+7.93e+00

Pos logit contributions
Mom+0.032
 wrist+0.029
ushes+0.028
 sticker+0.028
 half+0.028
Neg logit contributions
 vill-0.047
 ot-0.047
 current-0.046
 challenged-0.044
 ships-0.044
Token on
Token ID319
Feature activation+2.30e+00

Pos logit contributions
Mom+0.272
 bookmark+0.237
Anna+0.237
 half+0.236
 wrist+0.235
Neg logit contributions
 ot-0.264
 current-0.254
 vill-0.253
 challenged-0.252
 fishermen-0.252
Token it
Token ID340
Feature activation+1.25e+00

Pos logit contributions
Mom+0.072
ushes+0.068
 wrist+0.068
 sticker+0.067
aps+0.066
Neg logit contributions
 vill-0.073
 current-0.070
 ot-0.069
 ships-0.065
 challenged-0.064
Token.
Token ID13
Feature activation+1.06e+00

Pos logit contributions
Mom+0.037
 half+0.034
 sticker+0.033
 icing+0.032
ushes+0.032
Neg logit contributions
 vill-0.048
 challenged-0.047
vious-0.047
 ot-0.046
 current-0.046
Token Lily
Token ID20037
Feature activation+4.06e+00

Pos logit contributions
 half+0.032
 sticker+0.032
 ribbon+0.031
 icing+0.030
Mom+0.030
Neg logit contributions
 vill-0.039
 ot-0.037
 challenged-0.037
vious-0.036
 current-0.035
Token did
Token ID750
Feature activation+3.17e+00

Pos logit contributions
Mom+0.154
 half+0.154
 sticker+0.149
 icing+0.143
 cookie+0.142
Neg logit contributions
 vill-0.124
 challenged-0.120
 ot-0.116
vious-0.116
 current-0.116
Token ham
Token ID8891
Feature activation+7.90e+00

Pos logit contributions
Mom+0.097
 half+0.090
Anna+0.084
Elsa+0.080
Her+0.079
Neg logit contributions
 ot-0.126
 vill-0.121
 ships-0.118
 current-0.116
 harbor-0.114
Tokenster
Token ID1706
Feature activation-2.03e+00

Pos logit contributions
Mom+0.283
 Love+0.253
 half+0.252
ushes+0.250
Anna+0.249
Neg logit contributions
 ot-0.237
 current-0.226
itive-0.223
 vill-0.213
 harbor-0.212
Token cage
Token ID17186
Feature activation-1.05e+00

Pos logit contributions
 ot+0.071
 current+0.067
 vill+0.067
 challenged+0.064
 ships+0.064
Neg logit contributions
Mom-0.068
ushes-0.062
Anna-0.060
 half-0.058
 icing-0.058
Token.
Token ID13
Feature activation+1.27e+00

Pos logit contributions
 vill+0.042
 current+0.040
 ot+0.040
 challenged+0.040
vious+0.040
Neg logit contributions
Mom-0.030
 half-0.029
 sticker-0.028
 wrist-0.027
 icing-0.026
Token Their
Token ID5334
Feature activation+2.12e+00

Pos logit contributions
 half+0.045
 ribbon+0.044
Mom+0.044
 sticker+0.044
 icing+0.044
Neg logit contributions
 vill-0.040
 ot-0.039
 challenged-0.038
 current-0.038
vious-0.037
Token ham
Token ID8891
Feature activation+7.92e+00

Pos logit contributions
Mom+0.071
Anna+0.066
Her+0.064
 half+0.063
Elsa+0.063
Neg logit contributions
 ot-0.075
 ships-0.074
 current-0.072
 vill-0.071
 harbor-0.068
Tokenster
Token ID1706
Feature activation-1.99e+00

Pos logit contributions
Mom+0.289
 bookmark+0.264
 icing+0.261
 half+0.261
 wrist+0.260
Neg logit contributions
 ot-0.230
 current-0.217
 vill-0.215
 challenged-0.204
 eagle-0.202
Token,
Token ID11
Feature activation+3.57e-01

Pos logit contributions
 vill+0.060
 challenged+0.059
 ot+0.059
 current+0.057
 ships+0.053
Neg logit contributions
Mom-0.075
 half-0.070
ushes-0.069
 sticker-0.069
 icing-0.068
Token Fl
Token ID1610
Feature activation+2.73e+00

Pos logit contributions
Mom+0.011
 half+0.011
 sticker+0.011
ushes+0.011
 wrist+0.011
Neg logit contributions
 vill-0.013
 ot-0.012
 current-0.012
 challenged-0.012
 ships-0.012
Tokenuffy
Token ID15352
Feature activation+8.82e-02

Pos logit contributions
Mom+0.108
 herself+0.096
 half+0.096
 ribbon+0.094
Her+0.093
Neg logit contributions
 ot-0.080
 vill-0.075
 current-0.074
 fishermen-0.072
 padd-0.070
Token,
Token ID11
Feature activation+3.64e-01

Pos logit contributions
Mom+0.003
ushes+0.003
 half+0.003
 sticker+0.003
 icing+0.003
Neg logit contributions
 vill-0.003
 challenged-0.003
 ot-0.003
 current-0.003
 padd-0.002
Token Do
Token ID2141
Feature activation+5.50e+00

Pos logit contributions
 half+0.043
Mom+0.041
 ribbon+0.040
 sticker+0.040
 icing+0.040
Neg logit contributions
 ot-0.036
 vill-0.035
vious-0.034
 challenged-0.033
 current-0.032
Token you
Token ID345
Feature activation-1.73e+00

Pos logit contributions
ushes+0.130
Mom+0.125
 sticker+0.124
 half+0.122
 icing+0.122
Neg logit contributions
 vill-0.242
 challenged-0.233
 ot-0.226
vious-0.219
 ships-0.215
Token like
Token ID588
Feature activation+3.78e+00

Pos logit contributions
vious+0.038
 challenged+0.036
 vill+0.035
 ot+0.033
 current+0.031
Neg logit contributions
Mom-0.081
 half-0.078
 sticker-0.076
 icing-0.076
 wrist-0.076
Token cheese
Token ID9891
Feature activation+5.65e+00

Pos logit contributions
ushes+0.122
Mom+0.121
 wrist+0.116
 scalp+0.112
kin+0.104
Neg logit contributions
 ot-0.134
 vill-0.130
 challenged-0.128
 ships-0.128
 eagle-0.121
Token and
Token ID290
Feature activation+1.42e+00

Pos logit contributions
Mom+0.235
 half+0.231
ushes+0.225
 icing+0.221
 ribbon+0.219
Neg logit contributions
 vill-0.143
 challenged-0.141
 ot-0.141
vious-0.137
 current-0.131
Token ham
Token ID8891
Feature activation+7.92e+00

Pos logit contributions
Mom+0.038
ushes+0.036
 wrist+0.033
 half+0.032
 sticker+0.032
Neg logit contributions
 ot-0.059
 vill-0.059
 current-0.057
 challenged-0.056
 ships-0.055
Token?"
Token ID1701
Feature activation+1.59e+00

Pos logit contributions
Mom+0.286
 half+0.279
 ribbon+0.277
ushes+0.273
 icing+0.273
Neg logit contributions
 ot-0.231
 fishermen-0.221
 challenged-0.214
 vill-0.209
 ranc-0.204
Token
Token ID198
Feature activation+1.80e+00

Pos logit contributions
Mom+0.036
 half+0.035
 sticker+0.033
 cookie+0.031
 icing+0.030
Neg logit contributions
 vill-0.074
 challenged-0.072
 current-0.072
vious-0.071
 ot-0.071
Token
Token ID198
Feature activation+1.75e+00

Pos logit contributions
 half+0.049
 icing+0.048
 sticker+0.047
 cookie+0.046
Mom+0.046
Neg logit contributions
 vill-0.074
 challenged-0.070
 ot-0.068
 current-0.068
vious-0.067
TokenL
Token ID43
Feature activation+1.07e+00

Pos logit contributions
 icing+0.041
 half+0.040
 cookie+0.040
 sticker+0.039
 wrist+0.037
Neg logit contributions
 vill-0.078
 challenged-0.074
 ot-0.073
 current-0.073
vious-0.073
Tokenila
Token ID10102
Feature activation-3.26e-01

Pos logit contributions
Mom+0.034
 half+0.034
 sticker+0.033
 cookie+0.031
 icing+0.031
Neg logit contributions
 vill-0.040
 challenged-0.038
 current-0.038
vious-0.038
 ot-0.037
Token,
Token ID11
Feature activation-7.60e-01

Pos logit contributions
 vill+0.038
 current+0.036
 challenged+0.036
 ot+0.036
vious+0.036
Neg logit contributions
 half-0.025
Mom-0.025
 sticker-0.024
 cookie-0.023
 icing-0.022
Token a
Token ID257
Feature activation+7.48e-01

Pos logit contributions
 vill+0.031
 challenged+0.030
 current+0.030
vious+0.030
 ot+0.029
Neg logit contributions
 half-0.021
Mom-0.021
 sticker-0.020
 cookie-0.019
 icing-0.019
Token group
Token ID1448
Feature activation-8.54e+00

Pos logit contributions
 half+0.028
Mom+0.028
 sticker+0.027
 icing+0.026
ushes+0.026
Neg logit contributions
 vill-0.023
 challenged-0.022
 current-0.022
 ot-0.022
vious-0.021
Token of
Token ID286
Feature activation+1.06e+00

Pos logit contributions
rated+0.399
 current+0.393
 vill+0.384
 bust+0.380
lves+0.378
Neg logit contributions
Mom-0.168
 half-0.161
 cookie-0.133
 tape-0.132
 sticker-0.131
Token mis
Token ID2984
Feature activation-6.27e+00

Pos logit contributions
 half+0.032
Mom+0.032
 sticker+0.030
 cookie+0.029
 icing+0.028
Neg logit contributions
 vill-0.040
 challenged-0.039
 current-0.039
vious-0.039
 ot-0.037
Tokenchie
Token ID3043
Feature activation-1.34e+01

Pos logit contributions
 current+0.157
 ot+0.145
 vill+0.142
 challenged+0.140
 ships+0.135
Neg logit contributions
 half-0.278
Mom-0.275
 sticker-0.250
ushes-0.245
 wrist-0.242
Tokenvous
Token ID31222
Feature activation-5.16e+00

Pos logit contributions
 current+0.403
 ot+0.357
 ranc+0.352
 harbor+0.350
 ships+0.341
Neg logit contributions
 half-0.534
Mom-0.528
 sticker-0.486
Anna-0.480
e-0.470
Token mice
Token ID10693
Feature activation-3.03e+00

Pos logit contributions
roads+0.178
 vill+0.176
 challenged+0.175
 current+0.173
ounded+0.170
Neg logit contributions
 half-0.160
 sticker-0.149
 cookie-0.149
Mom-0.144
 icing-0.144
Token came
Token ID1625
Feature activation-4.04e+00

Pos logit contributions
 vill+0.113
 current+0.111
vious+0.105
 bust+0.104
 ot+0.102
Neg logit contributions
 half-0.091
 sticker-0.085
Mom-0.084
 cookie-0.084
 ribbon-0.082
Token by
Token ID416
Feature activation-2.05e+00

Pos logit contributions
 vill+0.176
 current+0.171
vious+0.169
 challenged+0.166
 ot+0.164
Neg logit contributions
 half-0.102
Mom-0.097
 sticker-0.091
 cookie-0.086
 herself-0.084
Token and
Token ID290
Feature activation-3.83e-01

Pos logit contributions
 vill+0.084
vious+0.081
 challenged+0.080
 current+0.080
 ot+0.079
Neg logit contributions
 half-0.058
Mom-0.056
 sticker-0.053
 cookie-0.051
 ribbon-0.050
Token so
Token ID523
Feature activation-3.60e+00

Pos logit contributions
Mom+0.054
 half+0.054
 sticker+0.052
 cookie+0.048
 icing+0.047
Neg logit contributions
 vill-0.114
 challenged-0.110
vious-0.109
 current-0.109
 ot-0.109
Token that
Token ID326
Feature activation-2.30e+00

Pos logit contributions
 vill+0.109
 challenged+0.104
vious+0.104
 ot+0.102
 current+0.102
Neg logit contributions
Mom-0.140
 half-0.138
 sticker-0.134
 cookie-0.127
 icing-0.126
Token no
Token ID645
Feature activation-4.04e-02

Pos logit contributions
 vill+0.068
 challenged+0.065
 current+0.064
 ot+0.064
vious+0.063
Neg logit contributions
Mom-0.090
 half-0.090
 sticker-0.087
 icing-0.084
 cookie-0.084
Token more
Token ID517
Feature activation+3.67e+00

Pos logit contributions
 vill+0.001
 challenged+0.001
 ot+0.001
 current+0.001
vious+0.001
Neg logit contributions
Mom-0.001
 half-0.001
 sticker-0.001
ushes-0.001
 icing-0.001
Token mis
Token ID2984
Feature activation-5.97e+00

Pos logit contributions
 half+0.122
Mom+0.120
 sticker+0.118
 cookie+0.112
 icing+0.111
Neg logit contributions
 vill-0.131
 challenged-0.125
vious-0.123
 current-0.123
 ot-0.122
Tokenchie
Token ID3043
Feature activation-1.29e+01

Pos logit contributions
 current+0.153
 ships+0.150
 harbor+0.148
 vill+0.148
 challenged+0.147
Neg logit contributions
 half-0.250
Mom-0.239
 sticker-0.227
ra-0.216
ushes-0.214
Tokenvous
Token ID31222
Feature activation-4.66e+00

Pos logit contributions
 current+0.344
 ot+0.336
 harbor+0.330
 ships+0.322
 ranc+0.311
Neg logit contributions
 half-0.556
Mom-0.535
 sticker-0.524
Anna-0.500
 cookie-0.490
Token mice
Token ID10693
Feature activation-2.64e+00

Pos logit contributions
 vill+0.164
 challenged+0.162
vious+0.158
 current+0.153
 ot+0.152
Neg logit contributions
 half-0.152
 sticker-0.147
 cookie-0.143
Mom-0.142
 ribbon-0.139
Token could
Token ID714
Feature activation+3.29e+00

Pos logit contributions
 vill+0.102
 current+0.099
 ot+0.095
vious+0.095
 challenged+0.095
Neg logit contributions
 half-0.077
 sticker-0.075
Mom-0.073
 ribbon-0.071
 cookie-0.071
Token come
Token ID1282
Feature activation+5.35e-01

Pos logit contributions
Mom+0.091
 half+0.091
 sticker+0.086
 icing+0.083
 cookie+0.082
Neg logit contributions
 vill-0.134
 challenged-0.129
 current-0.129
 ot-0.128
vious-0.127
Token in
Token ID287
Feature activation-2.30e-01

Pos logit contributions
Mom+0.015
 half+0.015
 sticker+0.014
 icing+0.013
 cookie+0.013
Neg logit contributions
 vill-0.022
 challenged-0.021
 current-0.021
 ot-0.021
vious-0.021
Token the
Token ID262
Feature activation-1.68e+00

Pos logit contributions
 vill+0.010
 ot+0.010
 challenged+0.010
 current+0.010
vious+0.010
Neg logit contributions
Mom-0.007
 half-0.007
 sticker-0.007
ushes-0.006
 icing-0.006
Token squirrel
Token ID33039
Feature activation-4.39e+00

Pos logit contributions
 vill+0.048
 challenged+0.047
vious+0.046
 current+0.045
 ot+0.044
Neg logit contributions
Mom-0.067
 half-0.067
 sticker-0.064
 cookie-0.062
 ribbon-0.061
Token got
Token ID1392
Feature activation-4.83e-01

Pos logit contributions
 vill+0.155
 current+0.144
 Jon+0.143
 Anch+0.140
ules+0.139
Neg logit contributions
 half-0.146
Mom-0.135
 cookie-0.129
 gently-0.125
 sticker-0.123
Token a
Token ID257
Feature activation+9.66e-01

Pos logit contributions
 vill+0.017
 current+0.017
 challenged+0.016
vious+0.016
 ot+0.016
Neg logit contributions
 half-0.016
Mom-0.016
 sticker-0.015
 cookie-0.015
 icing-0.014
Token mis
Token ID2984
Feature activation-5.49e+00

Pos logit contributions
 half+0.031
 sticker+0.030
Mom+0.030
 cookie+0.029
 ribbon+0.028
Neg logit contributions
 vill-0.036
 challenged-0.035
vious-0.035
 current-0.034
 ot-0.034
Tokenchie
Token ID3043
Feature activation-1.25e+01

Pos logit contributions
 challenged+0.130
 ships+0.129
 current+0.128
 vill+0.127
 ot+0.123
Neg logit contributions
 half-0.243
Mom-0.237
 sticker-0.222
ushes-0.215
 wrist-0.210
Tokenvous
Token ID31222
Feature activation-4.28e+00

Pos logit contributions
 current+0.335
 harbor+0.334
 ships+0.323
 ranc+0.320
 ot+0.306
Neg logit contributions
 half-0.547
Mom-0.520
 sticker-0.499
 cookie-0.478
Anna-0.471
Token look
Token ID804
Feature activation-2.62e+00

Pos logit contributions
 bust+0.147
cient+0.144
roads+0.144
 vill+0.143
 challenged+0.142
Neg logit contributions
 half-0.148
 cookie-0.142
 sticker-0.141
 ribbon-0.134
Mom-0.125
Token in
Token ID287
Feature activation-2.28e-02

Pos logit contributions
 vill+0.125
 current+0.123
 bust+0.120
 challenged+0.118
 ot+0.115
Neg logit contributions
 half-0.059
 sticker-0.053
Mom-0.052
 cookie-0.049
 herself-0.047
Token its
Token ID663
Feature activation+2.42e+00

Pos logit contributions
 vill+0.001
 current+0.001
 challenged+0.001
 ot+0.001
vious+0.001
Neg logit contributions
Mom-0.001
 half-0.001
 sticker-0.001
 icing-0.001
 cookie-0.001
Token eye
Token ID4151
Feature activation-3.86e-02

Pos logit contributions
Mom+0.071
 half+0.068
 sticker+0.067
 icing+0.066
 cookie+0.063
Neg logit contributions
 vill-0.094
 current-0.093
 ot-0.092
 challenged-0.089
vious-0.089
Token sweet
Token ID6029
Feature activation+2.48e+00

Pos logit contributions
Mom+0.023
 half+0.022
ushes+0.021
 sticker+0.021
 icing+0.021
Neg logit contributions
 vill-0.025
 ot-0.024
 current-0.024
 challenged-0.023
vious-0.023
Token tune
Token ID14009
Feature activation-1.85e+00

Pos logit contributions
Mom+0.080
 half+0.078
 sticker+0.073
ushes+0.073
 icing+0.070
Neg logit contributions
 vill-0.094
 ot-0.090
 current-0.088
 challenged-0.088
vious-0.085
Token,
Token ID11
Feature activation-7.46e-01

Pos logit contributions
 vill+0.071
 challenged+0.068
 current+0.067
 ot+0.067
vious+0.067
Neg logit contributions
Mom-0.056
 half-0.056
 sticker-0.054
 cookie-0.051
 icing-0.051
Token a
Token ID257
Feature activation+7.10e-01

Pos logit contributions
 vill+0.033
 challenged+0.031
 current+0.031
 ot+0.031
vious+0.031
Neg logit contributions
Mom-0.019
 half-0.019
 sticker-0.018
 icing-0.017
 cookie-0.016
Token mis
Token ID2984
Feature activation-5.57e+00

Pos logit contributions
Mom+0.026
 half+0.026
 sticker+0.025
 cookie+0.024
 ribbon+0.024
Neg logit contributions
 vill-0.023
 challenged-0.022
vious-0.022
 current-0.022
 ot-0.021
Tokenchie
Token ID3043
Feature activation-1.24e+01

Pos logit contributions
 vill+0.115
 current+0.114
 challenged+0.114
 ot+0.110
 ships+0.105
Neg logit contributions
Mom-0.264
 half-0.262
 sticker-0.248
 wrist-0.241
 ribbon-0.241
Tokenvous
Token ID31222
Feature activation-4.20e+00

Pos logit contributions
 current+0.315
 harbor+0.297
 ot+0.293
 ranc+0.292
 ships+0.289
Neg logit contributions
Mom-0.541
 half-0.529
 sticker-0.497
Anna-0.496
e-0.471
Token fox
Token ID21831
Feature activation-4.99e+00

Pos logit contributions
 challenged+0.135
vious+0.135
roads+0.132
 vill+0.129
 ships+0.126
Neg logit contributions
 sticker-0.147
 half-0.145
 cookie-0.143
 ribbon-0.139
Mom-0.139
Token appeared
Token ID4120
Feature activation-1.04e+00

Pos logit contributions
 vill+0.149
 current+0.142
vious+0.142
 ot+0.133
 bust+0.131
Neg logit contributions
 half-0.186
Mom-0.182
 sticker-0.177
 ribbon-0.172
 cookie-0.169
Token.
Token ID13
Feature activation-5.65e-01

Pos logit contributions
 vill+0.043
 challenged+0.041
 current+0.041
 ot+0.041
vious+0.041
Neg logit contributions
Mom-0.029
 half-0.029
 sticker-0.028
 icing-0.026
 cookie-0.026
Token "
Token ID366
Feature activation-1.94e+00

Pos logit contributions
 vill+0.022
 current+0.021
 challenged+0.021
vious+0.021
 ot+0.021
Neg logit contributions
Mom-0.017
 half-0.017
 sticker-0.016
 cookie-0.016
 icing-0.015
Token and
Token ID290
Feature activation-2.66e-01

Pos logit contributions
Mom+0.033
 half+0.032
 sticker+0.028
 herself+0.028
 wrist+0.026
Neg logit contributions
 vill-0.060
 challenged-0.059
vious-0.059
 current-0.058
 ot-0.056
Token replied
Token ID8712
Feature activation-2.54e+00

Pos logit contributions
 vill+0.009
vious+0.009
 current+0.009
enced+0.009
 ot+0.008
Neg logit contributions
Mom-0.009
 half-0.009
 ribbon-0.008
 sticker-0.008
 herself-0.008
Token with
Token ID351
Feature activation-4.59e-01

Pos logit contributions
vious+0.106
 vill+0.106
 current+0.104
 challenged+0.103
 ot+0.102
Neg logit contributions
 half-0.067
Mom-0.066
 sticker-0.063
 cookie-0.060
 herself-0.057
Token a
Token ID257
Feature activation+5.27e-01

Pos logit contributions
 vill+0.020
 challenged+0.019
 current+0.019
 ot+0.019
vious+0.019
Neg logit contributions
 half-0.012
Mom-0.012
 sticker-0.011
 icing-0.010
 cookie-0.010
Token mis
Token ID2984
Feature activation-5.47e+00

Pos logit contributions
 half+0.014
 sticker+0.014
Mom+0.014
 cookie+0.013
 ribbon+0.013
Neg logit contributions
vious-0.022
 vill-0.021
 ot-0.021
 challenged-0.021
 current-0.021
Tokenchie
Token ID3043
Feature activation-1.23e+01

Pos logit contributions
 current+0.131
 ot+0.129
 challenged+0.128
 ships+0.126
 harbor+0.123
Neg logit contributions
 half-0.235
Mom-0.232
 sticker-0.222
ushes-0.218
 wrist-0.212
Tokenvous
Token ID31222
Feature activation-4.11e+00

Pos logit contributions
 current+0.319
 harbor+0.310
 ot+0.301
 ships+0.291
 ranc+0.288
Neg logit contributions
 half-0.541
Mom-0.521
 sticker-0.497
Anna-0.482
 cookie-0.474
Token gl
Token ID1278
Feature activation-4.63e+00

Pos logit contributions
lves+0.169
 challenged+0.165
vious+0.165
roads+0.162
 ships+0.162
Neg logit contributions
 half-0.109
 sticker-0.109
 cookie-0.106
 ribbon-0.100
 brush-0.095
Tokenint
Token ID600
Feature activation-2.98e+00

Pos logit contributions
 challenged+0.165
 vill+0.164
 current+0.162
 ot+0.159
 ships+0.151
Neg logit contributions
 sticker-0.150
 half-0.145
Mom-0.140
ushes-0.140
 ribbon-0.136
Token in
Token ID287
Feature activation-3.66e-02

Pos logit contributions
 vill+0.107
 challenged+0.106
lves+0.102
 current+0.101
 ot+0.100
Neg logit contributions
 half-0.095
Mom-0.090
 sticker-0.090
 ribbon-0.084
 icing-0.083
Token his
Token ID465
Feature activation+6.58e-01

Pos logit contributions
 vill+0.001
 challenged+0.001
vious+0.001
 current+0.001
 ot+0.001
Neg logit contributions
 half-0.001
Mom-0.001
 sticker-0.001
 ribbon-0.001
 cookie-0.001
TokenBut
Token ID1537
Feature activation+3.58e-01

Pos logit contributions
 sticker+0.003
 half+0.003
 icing+0.003
 cookie+0.002
 wrist+0.002
Neg logit contributions
 vill-0.004
 challenged-0.004
 ot-0.004
vious-0.004
 current-0.004
Token then
Token ID788
Feature activation+2.23e+00

Pos logit contributions
Mom+0.011
 half+0.011
 sticker+0.011
 icing+0.011
ushes+0.010
Neg logit contributions
 vill-0.013
 challenged-0.013
 ot-0.012
 current-0.012
vious-0.012
Token,
Token ID11
Feature activation-4.56e-01

Pos logit contributions
 half+0.060
Mom+0.058
 sticker+0.055
 cookie+0.052
 ribbon+0.051
Neg logit contributions
 vill-0.094
vious-0.092
 current-0.091
 challenged-0.091
 ot-0.090
Token a
Token ID257
Feature activation+9.05e-01

Pos logit contributions
 vill+0.019
 challenged+0.018
vious+0.018
 current+0.018
 ot+0.018
Neg logit contributions
 half-0.012
Mom-0.012
 sticker-0.012
 cookie-0.011
 ribbon-0.011
Token mis
Token ID2984
Feature activation-5.43e+00

Pos logit contributions
 half+0.033
Mom+0.032
 sticker+0.032
 cookie+0.031
 ribbon+0.030
Neg logit contributions
 challenged-0.029
 vill-0.028
vious-0.028
 current-0.027
 ot-0.027
Tokenchie
Token ID3043
Feature activation-1.23e+01

Pos logit contributions
 current+0.123
 challenged+0.121
 ot+0.119
 ships+0.118
 vill+0.118
Neg logit contributions
Mom-0.246
 half-0.245
 sticker-0.228
ushes-0.224
 wrist-0.221
Tokenvous
Token ID31222
Feature activation-4.14e+00

Pos logit contributions
 current+0.331
 ships+0.328
 harbor+0.327
 ranc+0.319
 ot+0.313
Neg logit contributions
Mom-0.510
 half-0.505
Anna-0.470
 sticker-0.458
e-0.439
Token rabbit
Token ID22746
Feature activation-4.32e+00

Pos logit contributions
 challenged+0.138
roads+0.134
 ships+0.132
vious+0.132
cient+0.128
Neg logit contributions
 cookie-0.141
 sticker-0.141
 half-0.140
Mom-0.132
 ribbon-0.132
Token came
Token ID1625
Feature activation-3.31e+00

Pos logit contributions
 vill+0.129
vious+0.126
 current+0.123
 bust+0.122
ounded+0.120
Neg logit contributions
 half-0.158
Mom-0.154
 cookie-0.144
 ribbon-0.144
 sticker-0.141
Token and
Token ID290
Feature activation+1.66e-01

Pos logit contributions
 vill+0.133
 current+0.128
vious+0.127
 challenged+0.126
 ot+0.125
Neg logit contributions
 half-0.097
Mom-0.096
 sticker-0.088
 ribbon-0.083
 cookie-0.083
Token started
Token ID2067
Feature activation+9.35e-01

Pos logit contributions
 half+0.006
Mom+0.005
 cookie+0.005
 ribbon+0.005
 gently+0.005
Neg logit contributions
vious-0.005
 vill-0.005
 current-0.005
 harbor-0.005
enced-0.005
Token<|endoftext|>
Token ID50256
Feature activation+3.72e-02

Pos logit contributions
 vill+0.008
 challenged+0.007
vious+0.007
 ot+0.007
 bust+0.007
Neg logit contributions
 sticker-0.007
 half-0.007
 icing-0.006
 ribbon-0.006
Mom-0.006
TokenPeter
Token ID19727
Feature activation-2.53e+00

Pos logit contributions
 half+0.001
 sticker+0.001
Mom+0.001
 icing+0.001
 ribbon+0.001
Neg logit contributions
 vill-0.001
 challenged-0.001
vious-0.001
 ot-0.001
 current-0.001
Token was
Token ID373
Feature activation-1.41e+00

Pos logit contributions
 vill+0.093
 current+0.091
vious+0.088
 ot+0.086
 challenged+0.085
Neg logit contributions
 half-0.080
Mom-0.079
 sticker-0.075
 cookie-0.071
 icing-0.071
Token a
Token ID257
Feature activation+7.74e-01

Pos logit contributions
 vill+0.054
 current+0.052
 ot+0.050
 challenged+0.050
vious+0.050
Neg logit contributions
Mom-0.044
 half-0.044
 sticker-0.042
 cookie-0.040
 icing-0.040
Token mis
Token ID2984
Feature activation-5.42e+00

Pos logit contributions
Mom+0.029
 half+0.028
 sticker+0.028
 cookie+0.027
 ribbon+0.026
Neg logit contributions
vious-0.024
 challenged-0.024
 vill-0.024
 current-0.023
roads-0.022
Tokenchie
Token ID3043
Feature activation-1.23e+01

Pos logit contributions
 current+0.123
 challenged+0.120
 ot+0.115
 vill+0.115
 ships+0.110
Neg logit contributions
Mom-0.249
 half-0.244
 sticker-0.230
 wrist-0.225
ushes-0.222
Tokenvous
Token ID31222
Feature activation-4.15e+00

Pos logit contributions
 current+0.313
 ot+0.267
 challenged+0.264
 harbor+0.259
 ranc+0.256
Neg logit contributions
Mom-0.550
 half-0.534
 sticker-0.521
Anna-0.501
 cookie-0.496
Token 3
Token ID513
Feature activation-5.42e+00

Pos logit contributions
roads+0.138
 challenged+0.137
vious+0.132
 current+0.131
 vill+0.128
Neg logit contributions
 half-0.140
 sticker-0.140
Mom-0.139
 cookie-0.139
 ribbon-0.131
Token year
Token ID614
Feature activation-5.95e+00

Pos logit contributions
 current+0.220
 bust+0.212
 challenged+0.206
ounded+0.203
cient+0.203
Neg logit contributions
Mom-0.152
 half-0.148
 cookie-0.138
 sticker-0.135
 wrist-0.129
Token old
Token ID1468
Feature activation-1.97e+00

Pos logit contributions
 challenged+0.211
 current+0.205
 vill+0.199
vious+0.195
 ot+0.193
Neg logit contributions
Mom-0.186
 sticker-0.182
 half-0.181
 icing-0.167
 cookie-0.165
Token who
Token ID508
Feature activation-4.11e+00

Pos logit contributions
vious+0.072
 current+0.072
 vill+0.071
 challenged+0.069
 bust+0.067
Neg logit contributions
Mom-0.060
 half-0.059
 sticker-0.059
 wrist-0.055
 cookie-0.055
Token The
Token ID383
Feature activation-1.27e+00

Pos logit contributions
 vill+0.004
 challenged+0.004
 current+0.004
vious+0.004
 ot+0.004
Neg logit contributions
Mom-0.002
 half-0.002
 sticker-0.002
 cookie-0.002
 icing-0.002
Token little
Token ID1310
Feature activation-2.52e+00

Pos logit contributions
 vill+0.040
 challenged+0.038
 current+0.038
vious+0.037
 ot+0.037
Neg logit contributions
Mom-0.048
 half-0.048
 sticker-0.047
 cookie-0.045
 icing-0.044
Token boy
Token ID2933
Feature activation-4.60e+00

Pos logit contributions
 vill+0.080
 challenged+0.078
 current+0.076
vious+0.076
 ot+0.074
Neg logit contributions
 half-0.094
Mom-0.091
 sticker-0.088
 cookie-0.087
 ribbon-0.085
Token smiled
Token ID13541
Feature activation+1.39e+00

Pos logit contributions
 vill+0.147
 current+0.144
vious+0.140
 ot+0.139
 harbor+0.132
Neg logit contributions
 half-0.171
Mom-0.168
 sticker-0.159
 cookie-0.153
 ribbon-0.152
Token mis
Token ID2984
Feature activation-5.37e+00

Pos logit contributions
Mom+0.034
 half+0.034
 sticker+0.032
 ribbon+0.029
 cookie+0.029
Neg logit contributions
 vill-0.062
 challenged-0.060
 current-0.059
vious-0.059
 ot-0.059
Tokenchie
Token ID3043
Feature activation-1.23e+01

Pos logit contributions
 current+0.138
 vill+0.136
 ot+0.132
 harbor+0.131
 challenged+0.131
Neg logit contributions
 half-0.231
Mom-0.226
 sticker-0.210
ushes-0.208
 wrist-0.204
Tokenv
Token ID85
Feature activation-8.45e-01

Pos logit contributions
 harbor+0.357
 current+0.354
 ranc+0.336
 ot+0.331
 ships+0.323
Neg logit contributions
 half-0.521
Mom-0.493
 sticker-0.462
 cookie-0.442
Anna-0.442
Tokenously
Token ID3481
Feature activation-4.25e+00

Pos logit contributions
 vill+0.027
 current+0.026
 challenged+0.026
 bust+0.025
 ot+0.025
Neg logit contributions
 half-0.033
Mom-0.032
 sticker-0.029
 cookie-0.028
 herself-0.028
Token and
Token ID290
Feature activation-8.37e-02

Pos logit contributions
 vill+0.198
vious+0.189
 current+0.188
 ot+0.186
 challenged+0.186
Neg logit contributions
 half-0.098
Mom-0.094
 sticker-0.089
 ribbon-0.083
 cookie-0.083
Token said
Token ID531
Feature activation-1.58e+00

Pos logit contributions
vious+0.003
 vill+0.003
 current+0.003
 ot+0.003
 challenged+0.003
Neg logit contributions
 half-0.003
Mom-0.003
 sticker-0.003
 ribbon-0.003
 cookie-0.003
Token,
Token ID11
Feature activation-9.59e-01

Pos logit contributions
 vill+0.058
 challenged+0.055
 current+0.054
 ot+0.054
vious+0.054
Neg logit contributions
Mom-0.052
 half-0.051
 sticker-0.049
 icing-0.047
 ribbon-0.047
Token always
Token ID1464
Feature activation-2.42e-01

Pos logit contributions
 vill+0.090
 current+0.087
 ot+0.084
vious+0.084
 challenged+0.081
Neg logit contributions
 half-0.097
Mom-0.096
 sticker-0.093
 cookie-0.089
 ribbon-0.087
Token acted
Token ID13134
Feature activation-3.94e+00

Pos logit contributions
 vill+0.007
 current+0.007
 ot+0.007
vious+0.007
 challenged+0.007
Neg logit contributions
 half-0.009
Mom-0.009
 sticker-0.009
 cookie-0.009
 ribbon-0.009
Token silly
Token ID14397
Feature activation-4.36e-01

Pos logit contributions
 vill+0.151
 current+0.145
 challenged+0.144
 ot+0.143
vious+0.141
Neg logit contributions
 half-0.121
Mom-0.119
 sticker-0.116
 cookie-0.108
 ribbon-0.108
Token and
Token ID290
Feature activation-5.16e-02

Pos logit contributions
 vill+0.019
 challenged+0.019
 current+0.018
 ot+0.018
vious+0.018
Neg logit contributions
Mom-0.011
 half-0.011
 sticker-0.010
 icing-0.009
 cookie-0.009
Token mis
Token ID2984
Feature activation-5.45e+00

Pos logit contributions
 vill+0.002
 current+0.002
 ot+0.002
 challenged+0.002
vious+0.002
Neg logit contributions
 half-0.002
Mom-0.002
 sticker-0.002
 cookie-0.001
 ribbon-0.001
Tokenchie
Token ID3043
Feature activation-1.23e+01

Pos logit contributions
 current+0.140
 vill+0.138
 ot+0.135
 ships+0.129
 harbor+0.128
Neg logit contributions
 half-0.235
Mom-0.231
 sticker-0.215
ushes-0.211
 wrist-0.211
Tokenvous
Token ID31222
Feature activation-4.03e+00

Pos logit contributions
 current+0.322
 harbor+0.301
 ot+0.296
 ranc+0.286
 vill+0.278
Neg logit contributions
 half-0.553
Mom-0.535
 sticker-0.515
Anna-0.498
 cookie-0.486
Token.
Token ID13
Feature activation-5.14e-01

Pos logit contributions
 vill+0.173
 challenged+0.167
 current+0.166
vious+0.165
 ot+0.163
Neg logit contributions
 half-0.102
 sticker-0.097
Mom-0.097
 cookie-0.092
 ribbon-0.089
Token
Token ID198
Feature activation+1.02e-01

Pos logit contributions
 vill+0.021
 challenged+0.020
 current+0.020
 ot+0.019
vious+0.019
Neg logit contributions
 half-0.015
Mom-0.015
 sticker-0.014
 icing-0.013
 ribbon-0.013
Token
Token ID198
Feature activation+5.02e-02

Pos logit contributions
 half+0.002
Mom+0.002
 sticker+0.002
 icing+0.002
 ribbon+0.002
Neg logit contributions
 vill-0.005
 challenged-0.004
 current-0.004
 ot-0.004
vious-0.004
TokenOne
Token ID3198
Feature activation+1.52e+00

Pos logit contributions
 half+0.001
Mom+0.001
 sticker+0.001
 icing+0.001
 cookie+0.001
Neg logit contributions
 vill-0.002
 challenged-0.002
 current-0.002
 ot-0.002
vious-0.002
Token
Token ID198
Feature activation-8.36e-03

Pos logit contributions
 half+0.000
Mom+0.000
 sticker+0.000
 icing+0.000
 ribbon+0.000
Neg logit contributions
 vill-0.001
 challenged-0.000
 current-0.000
 ot-0.000
vious-0.000
TokenOne
Token ID3198
Feature activation+1.49e+00

Pos logit contributions
 vill+0.000
 challenged+0.000
 current+0.000
 ot+0.000
vious+0.000
Neg logit contributions
Mom-0.000
 half-0.000
 sticker-0.000
 cookie-0.000
 icing-0.000
Token day
Token ID1110
Feature activation-4.84e-01

Pos logit contributions
Mom+0.047
 half+0.047
 sticker+0.045
 cookie+0.043
 icing+0.042
Neg logit contributions
 vill-0.055
 challenged-0.053
 current-0.053
vious-0.052
 ot-0.052
Token a
Token ID257
Feature activation+8.57e-01

Pos logit contributions
 vill+0.021
vious+0.021
 current+0.020
 challenged+0.020
 bust+0.020
Neg logit contributions
 half-0.012
Mom-0.012
 sticker-0.011
 cookie-0.011
 icing-0.010
Token mis
Token ID2984
Feature activation-5.39e+00

Pos logit contributions
Mom+0.031
 half+0.031
 sticker+0.030
 cookie+0.029
 ribbon+0.028
Neg logit contributions
 vill-0.028
 challenged-0.027
vious-0.026
 current-0.026
 ot-0.026
Tokenchie
Token ID3043
Feature activation-1.23e+01

Pos logit contributions
 current+0.109
 vill+0.108
 challenged+0.106
 ot+0.105
 ships+0.099
Neg logit contributions
 half-0.258
Mom-0.258
 sticker-0.246
 ribbon-0.235
 wrist-0.235
Tokenvous
Token ID31222
Feature activation-4.11e+00

Pos logit contributions
 current+0.302
 ot+0.283
 harbor+0.282
 ships+0.278
 ranc+0.273
Neg logit contributions
Mom-0.553
 half-0.549
 sticker-0.517
Anna-0.513
 cookie-0.493
Token monkey
Token ID21657
Feature activation-1.04e+00

Pos logit contributions
roads+0.133
vious+0.132
 challenged+0.131
 vill+0.126
 ships+0.124
Neg logit contributions
 cookie-0.146
 sticker-0.144
 half-0.142
 ribbon-0.134
Mom-0.134
Token saw
Token ID2497
Feature activation-2.71e+00

Pos logit contributions
 current+0.035
 vill+0.034
 daunting+0.033
 hurricane+0.032
 bust+0.032
Neg logit contributions
 half-0.036
Mom-0.032
 sticker-0.032
 cookie-0.031
 tape-0.030
Token the
Token ID262
Feature activation-2.14e+00

Pos logit contributions
 bust+0.133
 vill+0.132
rated+0.131
 current+0.131
vious+0.130
Neg logit contributions
 half-0.057
Mom-0.046
 herself-0.045
 cookie-0.044
 sticker-0.044
Token bear
Token ID6842
Feature activation-1.65e+00

Pos logit contributions
 vill+0.065
 ot+0.062
 current+0.062
 challenged+0.062
vious+0.061
Neg logit contributions
Mom-0.084
 half-0.082
 sticker-0.078
ushes-0.078
 icing-0.077
Token.
Token ID13
Feature activation-6.22e-01

Pos logit contributions
 vill+0.019
 ot+0.018
 challenged+0.018
 current+0.018
vious+0.017
Neg logit contributions
 half-0.024
Mom-0.023
 sticker-0.023
 icing-0.022
ushes-0.022
Token He
Token ID679
Feature activation-1.66e+00

Pos logit contributions
 vill+0.019
 ot+0.018
 challenged+0.018
 current+0.018
vious+0.018
Neg logit contributions
Mom-0.023
 half-0.023
 sticker-0.022
ushes-0.022
 ribbon-0.022
Token was
Token ID373
Feature activation-1.37e+00

Pos logit contributions
 vill+0.056
 current+0.054
 challenged+0.054
vious+0.053
 ot+0.053
Neg logit contributions
Mom-0.058
 half-0.058
 sticker-0.056
 cookie-0.054
 icing-0.053
Token a
Token ID257
Feature activation+7.05e-01

Pos logit contributions
 vill+0.063
 current+0.063
 challenged+0.062
vious+0.062
 ot+0.059
Neg logit contributions
 half-0.031
Mom-0.030
 sticker-0.030
 cookie-0.028
 icing-0.026
Token mis
Token ID2984
Feature activation-5.34e+00

Pos logit contributions
Mom+0.025
 half+0.025
 sticker+0.024
 cookie+0.023
 icing+0.023
Neg logit contributions
 vill-0.024
 challenged-0.023
 current-0.022
vious-0.022
 ot-0.022
Tokenchie
Token ID3043
Feature activation-1.22e+01

Pos logit contributions
 challenged+0.107
 vill+0.106
 current+0.106
 ot+0.098
vious+0.096
Neg logit contributions
Mom-0.255
 half-0.254
 sticker-0.242
 wrist-0.236
 icing-0.233
Tokenvous
Token ID31222
Feature activation-4.03e+00

Pos logit contributions
 current+0.274
 challenged+0.245
 vill+0.234
 ot+0.227
 padd+0.227
Neg logit contributions
Mom-0.581
 half-0.564
 sticker-0.560
 cookie-0.541
Anna-0.532
Token little
Token ID1310
Feature activation-2.92e+00

Pos logit contributions
roads+0.141
 challenged+0.139
vious+0.136
 vill+0.132
 current+0.132
Neg logit contributions
 cookie-0.136
Mom-0.133
 sticker-0.132
 half-0.132
 ribbon-0.123
Token baby
Token ID5156
Feature activation-6.32e-01

Pos logit contributions
 challenged+0.089
 vill+0.087
roads+0.083
vious+0.082
 current+0.080
Neg logit contributions
 half-0.109
 cookie-0.109
 sticker-0.109
Mom-0.107
 ribbon-0.100
Token and
Token ID290
Feature activation-9.94e-02

Pos logit contributions
 vill+0.026
 ot+0.025
 challenged+0.025
 current+0.025
vious+0.025
Neg logit contributions
 half-0.017
Mom-0.017
 sticker-0.017
 icing-0.016
ushes-0.016
Token always
Token ID1464
Feature activation-1.97e-01

Pos logit contributions
 vill+0.003
 current+0.003
vious+0.003
 challenged+0.003
 ot+0.003
Neg logit contributions
Mom-0.003
 half-0.003
 sticker-0.003
 cookie-0.003
 herself-0.003
Token small
Token ID1402
Feature activation+1.50e-01

Pos logit contributions
Mom+0.024
 half+0.024
 sticker+0.023
 icing+0.023
ushes+0.023
Neg logit contributions
 vill-0.023
 ot-0.022
 current-0.022
 challenged-0.022
vious-0.020
Token boy
Token ID2933
Feature activation-4.79e+00

Pos logit contributions
 half+0.005
Mom+0.005
 sticker+0.005
 cookie+0.005
 icing+0.005
Neg logit contributions
 vill-0.005
 challenged-0.005
 current-0.005
vious-0.005
 ot-0.005
Token with
Token ID351
Feature activation-2.11e-01

Pos logit contributions
 vill+0.174
 challenged+0.167
 current+0.165
 ot+0.164
vious+0.164
Neg logit contributions
Mom-0.155
 half-0.155
 sticker-0.149
 cookie-0.141
 icing-0.141
Token a
Token ID257
Feature activation+7.03e-01

Pos logit contributions
 vill+0.009
 challenged+0.009
 current+0.009
 ot+0.009
vious+0.009
Neg logit contributions
 half-0.005
Mom-0.005
 sticker-0.005
 cookie-0.005
 icing-0.005
Token mis
Token ID2984
Feature activation-5.44e+00

Pos logit contributions
Mom+0.023
 half+0.023
 sticker+0.021
 icing+0.021
ushes+0.021
Neg logit contributions
 vill-0.025
 challenged-0.024
 current-0.024
 ot-0.024
vious-0.023
Tokenchie
Token ID3043
Feature activation-1.22e+01

Pos logit contributions
 vill+0.112
 current+0.111
 challenged+0.111
 ot+0.108
 ships+0.100
Neg logit contributions
 half-0.258
Mom-0.256
 sticker-0.245
ushes-0.236
 ribbon-0.235
Tokenvous
Token ID31222
Feature activation-4.08e+00

Pos logit contributions
 current+0.306
 harbor+0.285
 ships+0.278
 ot+0.275
 padd+0.263
Neg logit contributions
 half-0.558
Mom-0.537
 sticker-0.519
 cookie-0.495
Anna-0.487
Token tw
Token ID665
Feature activation-8.28e-01

Pos logit contributions
 vill+0.160
 challenged+0.160
vious+0.158
roads+0.155
 current+0.152
Neg logit contributions
 half-0.118
 sticker-0.115
 cookie-0.111
Mom-0.106
 ribbon-0.105
Tokeninkle
Token ID19894
Feature activation+1.63e+00

Pos logit contributions
 vill+0.035
 challenged+0.034
 current+0.034
 ot+0.034
vious+0.033
Neg logit contributions
 half-0.022
Mom-0.021
 sticker-0.021
 ribbon-0.020
 wrist-0.019
Token in
Token ID287
Feature activation+2.13e-01

Pos logit contributions
 half+0.043
Mom+0.042
 sticker+0.040
 icing+0.038
 cookie+0.038
Neg logit contributions
 vill-0.070
 challenged-0.067
 current-0.067
vious-0.066
 ot-0.066
Token his
Token ID465
Feature activation+8.20e-01

Pos logit contributions
Mom+0.008
 half+0.008
 sticker+0.007
 cookie+0.007
 icing+0.007
Neg logit contributions
 vill-0.007
 challenged-0.007
 current-0.007
 ot-0.006
vious-0.006
Token went
Token ID1816
Feature activation-2.40e+00

Pos logit contributions
 vill+0.061
vious+0.059
 current+0.058
ules+0.057
 ot+0.056
Neg logit contributions
 half-0.059
Mom-0.058
 ribbon-0.056
 sticker-0.054
 tape-0.053
Token on
Token ID319
Feature activation+2.05e+00

Pos logit contributions
 vill+0.112
 current+0.108
vious+0.108
 ot+0.107
 challenged+0.106
Neg logit contributions
 half-0.054
Mom-0.053
 sticker-0.052
 cookie-0.048
 ribbon-0.047
Token with
Token ID351
Feature activation-3.37e-01

Pos logit contributions
 half+0.060
Mom+0.059
 sticker+0.057
 cookie+0.054
 ribbon+0.054
Neg logit contributions
 vill-0.081
vious-0.078
 challenged-0.078
 ot-0.078
 current-0.077
Token his
Token ID465
Feature activation+7.80e-01

Pos logit contributions
 vill+0.014
 challenged+0.013
vious+0.013
 current+0.013
 ot+0.013
Neg logit contributions
 half-0.010
Mom-0.009
 sticker-0.009
 cookie-0.008
 herself-0.008
Token mis
Token ID2984
Feature activation-5.29e+00

Pos logit contributions
Mom+0.023
 half+0.023
 sticker+0.022
 icing+0.021
ushes+0.021
Neg logit contributions
 vill-0.031
 current-0.029
 challenged-0.029
 ot-0.029
vious-0.028
Tokenchie
Token ID3043
Feature activation-1.22e+01

Pos logit contributions
 vill+0.133
 current+0.128
 ot+0.127
 challenged+0.126
vious+0.119
Neg logit contributions
 half-0.231
Mom-0.231
 sticker-0.217
ushes-0.211
 ribbon-0.210
Tokenvous
Token ID31222
Feature activation-4.03e+00

Pos logit contributions
 ot+0.312
 current+0.312
 harbor+0.298
 ships+0.289
 ranc+0.266
Neg logit contributions
 half-0.563
Mom-0.546
 sticker-0.503
Anna-0.499
 cookie-0.488
Token ways
Token ID2842
Feature activation-2.15e+00

Pos logit contributions
 vill+0.146
 challenged+0.144
vious+0.143
lves+0.142
roads+0.141
Neg logit contributions
 half-0.127
 cookie-0.119
 sticker-0.119
Mom-0.114
 ribbon-0.112
Token,
Token ID11
Feature activation-8.54e-01

Pos logit contributions
 vill+0.094
 current+0.091
 challenged+0.091
vious+0.090
 ot+0.090
Neg logit contributions
 half-0.054
Mom-0.051
 sticker-0.050
 cookie-0.046
 ribbon-0.045
Token causing
Token ID6666
Feature activation-5.18e+00

Pos logit contributions
 vill+0.030
vious+0.028
 ot+0.027
 challenged+0.027
 current+0.027
Neg logit contributions
 half-0.029
Mom-0.028
 sticker-0.028
 cookie-0.027
 tape-0.026
Token problems
Token ID2761
Feature activation-1.89e+00

Pos logit contributions
 vill+0.204
 challenged+0.198
vious+0.197
enced+0.196
 ot+0.195
Neg logit contributions
 half-0.154
Mom-0.137
 sticker-0.135
 herself-0.134
 cookie-0.127
Token old
Token ID1468
Feature activation-1.84e+00

Pos logit contributions
 vill+0.078
 challenged+0.075
 current+0.074
 ot+0.074
vious+0.074
Neg logit contributions
 half-0.065
Mom-0.065
 sticker-0.063
 cookie-0.060
 ribbon-0.059
Token lady
Token ID10846
Feature activation-1.68e+00

Pos logit contributions
 vill+0.072
 challenged+0.069
 current+0.069
 ot+0.068
vious+0.068
Neg logit contributions
Mom-0.055
 half-0.054
 sticker-0.051
 icing-0.050
ushes-0.048
Token with
Token ID351
Feature activation-2.35e-01

Pos logit contributions
 vill+0.065
 challenged+0.063
vious+0.062
 ot+0.062
 current+0.061
Neg logit contributions
Mom-0.051
 half-0.049
 sticker-0.047
 icing-0.045
 ribbon-0.045
Token a
Token ID257
Feature activation+7.56e-01

Pos logit contributions
 vill+0.010
 challenged+0.010
 current+0.010
 ot+0.010
vious+0.010
Neg logit contributions
Mom-0.006
 half-0.006
 sticker-0.006
 cookie-0.005
 icing-0.005
Token mis
Token ID2984
Feature activation-5.27e+00

Pos logit contributions
 half+0.022
Mom+0.022
 sticker+0.022
 cookie+0.021
 ribbon+0.020
Neg logit contributions
 vill-0.029
 challenged-0.028
 current-0.028
vious-0.028
 ot-0.028
Tokenchie
Token ID3043
Feature activation-1.21e+01

Pos logit contributions
 current+0.119
 ot+0.117
 challenged+0.116
 vill+0.113
 ships+0.110
Neg logit contributions
 half-0.239
Mom-0.236
 sticker-0.227
ushes-0.219
 wrist-0.218
Tokenvous
Token ID31222
Feature activation-3.98e+00

Pos logit contributions
 current+0.327
 harbor+0.315
 ot+0.312
 ships+0.293
 ranc+0.284
Neg logit contributions
 half-0.532
Mom-0.503
 sticker-0.496
Anna-0.469
 cookie-0.467
Token tw
Token ID665
Feature activation-7.66e-01

Pos logit contributions
 vill+0.151
 challenged+0.149
vious+0.147
lves+0.147
 ot+0.146
Neg logit contributions
 sticker-0.118
 half-0.117
 cookie-0.113
 ribbon-0.108
Mom-0.105
Tokeninkle
Token ID19894
Feature activation+1.69e+00

Pos logit contributions
 vill+0.032
 challenged+0.032
 ot+0.031
 current+0.031
vious+0.030
Neg logit contributions
 half-0.020
 sticker-0.019
Mom-0.019
 ribbon-0.019
 wrist-0.018
Token in
Token ID287
Feature activation+2.38e-01

Pos logit contributions
 half+0.042
Mom+0.041
 sticker+0.040
 icing+0.038
 cookie+0.038
Neg logit contributions
 vill-0.074
 challenged-0.071
 current-0.071
vious-0.070
 ot-0.069
Token her
Token ID607
Feature activation+2.47e+00

Pos logit contributions
 half+0.006
Mom+0.006
 sticker+0.006
 cookie+0.006
 icing+0.006
Neg logit contributions
 vill-0.010
 challenged-0.010
 current-0.010
vious-0.010
 ot-0.010
Token
Token ID198
Feature activation+5.66e-01

Pos logit contributions
 half+0.017
 sticker+0.017
 icing+0.016
Mom+0.016
 ribbon+0.016
Neg logit contributions
 vill-0.026
 challenged-0.025
 ot-0.024
 current-0.024
vious-0.024
TokenSuddenly
Token ID38582
Feature activation+9.72e-01

Pos logit contributions
 sticker+0.018
 icing+0.018
 half+0.017
 cookie+0.017
ushes+0.016
Neg logit contributions
 vill-0.021
 challenged-0.021
vious-0.020
 current-0.019
 ot-0.019
Token,
Token ID11
Feature activation-4.21e-01

Pos logit contributions
Mom+0.032
 half+0.032
 sticker+0.030
 icing+0.029
 cookie+0.029
Neg logit contributions
 vill-0.035
 challenged-0.033
 current-0.033
 ot-0.033
vious-0.033
Token a
Token ID257
Feature activation+1.00e+00

Pos logit contributions
 vill+0.018
 challenged+0.017
 ot+0.017
 current+0.017
vious+0.017
Neg logit contributions
Mom-0.011
 half-0.011
 sticker-0.010
 icing-0.010
ushes-0.010
Token mis
Token ID2984
Feature activation-5.21e+00

Pos logit contributions
Mom+0.033
 sticker+0.032
 half+0.032
 cookie+0.031
 ribbon+0.030
Neg logit contributions
vious-0.037
 challenged-0.036
 vill-0.035
 current-0.034
 ot-0.034
Tokenchie
Token ID3043
Feature activation-1.21e+01

Pos logit contributions
 current+0.111
 challenged+0.109
 vill+0.109
 ot+0.106
 ships+0.103
Neg logit contributions
Mom-0.243
 half-0.241
 sticker-0.228
 ribbon-0.223
 wrist-0.222
Tokenvous
Token ID31222
Feature activation-3.85e+00

Pos logit contributions
 current+0.325
 ranc+0.316
 ships+0.314
 ot+0.313
 harbor+0.311
Neg logit contributions
Mom-0.509
 half-0.499
Anna-0.464
 sticker-0.455
 card-0.438
Token bird
Token ID6512
Feature activation-3.30e+00

Pos logit contributions
 challenged+0.135
roads+0.135
vious+0.131
 ships+0.128
lves+0.125
Neg logit contributions
 sticker-0.127
 cookie-0.125
 half-0.121
 ribbon-0.117
Mom-0.116
Token flew
Token ID13112
Feature activation-2.78e+00

Pos logit contributions
 vill+0.121
 current+0.113
 fishermen+0.111
 traveller+0.108
 bust+0.107
Neg logit contributions
 half-0.107
Mom-0.106
 sticker-0.096
 ribbon-0.095
 brush-0.090
Token by
Token ID416
Feature activation-9.57e-01

Pos logit contributions
 vill+0.116
 current+0.110
 challenged+0.108
 ot+0.107
vious+0.105
Neg logit contributions
 half-0.078
Mom-0.078
 sticker-0.069
 ribbon-0.068
 herself-0.065
Token and
Token ID290
Feature activation+2.99e-01

Pos logit contributions
 vill+0.037
 challenged+0.036
 current+0.036
 ot+0.035
vious+0.035
Neg logit contributions
Mom-0.029
 half-0.028
 sticker-0.028
 icing-0.027
 cookie-0.026
Token modest
Token ID12949
Feature activation-3.01e-01

Pos logit contributions
vious+0.028
 vill+0.028
 challenged+0.028
 current+0.027
roads+0.026
Neg logit contributions
Mom-0.022
 half-0.021
 sticker-0.020
 cookie-0.020
 ribbon-0.019
Token barn
Token ID25203
Feature activation-1.73e+00

Pos logit contributions
 vill+0.010
 challenged+0.010
vious+0.010
 current+0.009
 ot+0.009
Neg logit contributions
Mom-0.011
 half-0.011
 sticker-0.010
 cookie-0.010
 ribbon-0.010
Token.
Token ID13
Feature activation-4.87e-01

Pos logit contributions
 vill+0.081
vious+0.081
 current+0.079
 challenged+0.079
 ot+0.076
Neg logit contributions
Mom-0.037
 half-0.037
 sticker-0.035
 cookie-0.033
 icing-0.031
Token Two
Token ID4930
Feature activation-2.36e+00

Pos logit contributions
 vill+0.016
 challenged+0.015
 current+0.015
 ot+0.014
vious+0.014
Neg logit contributions
Mom-0.018
 half-0.018
 sticker-0.017
 ribbon-0.016
 icing-0.016
Token mis
Token ID2984
Feature activation-5.32e+00

Pos logit contributions
 current+0.097
vious+0.094
 vill+0.092
 challenged+0.092
roads+0.092
Neg logit contributions
 half-0.065
Mom-0.065
 cookies-0.062
 cookie-0.059
 tape-0.056
Tokenchie
Token ID3043
Feature activation-1.21e+01

Pos logit contributions
 current+0.114
 vill+0.109
 challenged+0.109
 ot+0.105
vious+0.102
Neg logit contributions
 half-0.250
Mom-0.247
 sticker-0.232
ushes-0.227
 icing-0.225
Tokenvous
Token ID31222
Feature activation-4.07e+00

Pos logit contributions
 current+0.315
 harbor+0.270
 ot+0.265
 padd+0.265
 vill+0.263
Neg logit contributions
Mom-0.542
 half-0.526
 sticker-0.494
Anna-0.489
 cookie-0.471
Token kittens
Token ID45584
Feature activation-1.99e+00

Pos logit contributions
roads+0.146
ounded+0.137
vious+0.137
 challenged+0.134
 current+0.134
Neg logit contributions
 cookie-0.131
 cookies-0.130
 chocolate-0.125
 half-0.123
 sticker-0.122
Token lived
Token ID5615
Feature activation+5.29e-01

Pos logit contributions
 current+0.071
 vill+0.069
vious+0.067
 bust+0.064
roads+0.062
Neg logit contributions
 half-0.063
Mom-0.063
 cookie-0.058
 sticker-0.058
 herself-0.058
Token in
Token ID287
Feature activation+3.25e-01

Pos logit contributions
Mom+0.016
 half+0.016
 sticker+0.015
 icing+0.014
 ribbon+0.014
Neg logit contributions
 vill-0.021
 challenged-0.020
 ot-0.020
 current-0.019
vious-0.019
Token the
Token ID262
Feature activation-2.08e+00

Pos logit contributions
Mom+0.010
 half+0.010
 sticker+0.010
 icing+0.009
 wrist+0.009
Neg logit contributions
 vill-0.013
 ot-0.012
 challenged-0.012
 current-0.011
vious-0.011
Token at
Token ID379
Feature activation-4.15e-01

Pos logit contributions
 vill+0.128
 current+0.125
 challenged+0.120
 ot+0.117
 ranc+0.115
Neg logit contributions
 half-0.102
Mom-0.093
 sticker-0.091
 cookie-0.090
ushes-0.088
Token him
Token ID683
Feature activation+1.70e-01

Pos logit contributions
 vill+0.018
 challenged+0.017
 current+0.017
vious+0.017
 ot+0.017
Neg logit contributions
 half-0.011
Mom-0.011
 sticker-0.010
 ribbon-0.010
 icing-0.010
Token with
Token ID351
Feature activation-2.00e-01

Pos logit contributions
Mom+0.006
ushes+0.006
 sticker+0.005
 half+0.005
 icing+0.005
Neg logit contributions
 vill-0.006
 challenged-0.006
 ot-0.006
 current-0.005
 padd-0.005
Token a
Token ID257
Feature activation+7.03e-01

Pos logit contributions
 vill+0.008
 challenged+0.008
 current+0.008
 ot+0.008
vious+0.007
Neg logit contributions
 half-0.006
Mom-0.006
 sticker-0.006
 cookie-0.005
 icing-0.005
Token mis
Token ID2984
Feature activation-5.23e+00

Pos logit contributions
Mom+0.023
 half+0.022
 sticker+0.021
 icing+0.020
 cookie+0.020
Neg logit contributions
 vill-0.026
 challenged-0.025
 current-0.024
 ot-0.024
vious-0.024
Tokenchie
Token ID3043
Feature activation-1.20e+01

Pos logit contributions
 vill+0.101
 challenged+0.096
 current+0.095
 ot+0.093
vious+0.089
Neg logit contributions
 half-0.258
Mom-0.256
 sticker-0.248
 ribbon-0.239
 icing-0.239
Tokenvous
Token ID31222
Feature activation-3.97e+00

Pos logit contributions
 current+0.274
 ot+0.262
 harbor+0.256
 ships+0.256
 ranc+0.245
Neg logit contributions
 half-0.581
Mom-0.553
 sticker-0.533
 cookie-0.521
 slice-0.509
Token grin
Token ID16770
Feature activation+4.64e-02

Pos logit contributions
 vill+0.162
 challenged+0.159
vious+0.157
 ot+0.154
 current+0.153
Neg logit contributions
 half-0.111
 sticker-0.107
 cookie-0.103
Mom-0.102
 ribbon-0.100
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
Mom+0.001
 half+0.001
ushes+0.001
 sticker+0.001
 icing+0.001
Neg logit contributions
 vill-0.002
 challenged-0.002
 ot-0.002
 current-0.002
vious-0.002
Token She
Token ID1375
Feature activation-2.15e-01

Pos logit contributions
 vill+0.016
 current+0.016
 challenged+0.016
 ot+0.016
vious+0.016
Neg logit contributions
Mom-0.012
 half-0.012
 sticker-0.012
 cookie-0.011
 icing-0.011
Token said
Token ID531
Feature activation-1.54e+00

Pos logit contributions
 vill+0.006
 current+0.006
vious+0.006
 ot+0.006
 challenged+0.006
Neg logit contributions
Mom-0.008
 half-0.008
 sticker-0.008
 ribbon-0.008
 cookie-0.008
Token
Token ID198
Feature activation+6.77e-02

Pos logit contributions
 vill+0.044
 challenged+0.043
vious+0.041
 ot+0.040
ules+0.040
Neg logit contributions
 sticker-0.036
 half-0.036
 icing-0.035
 ribbon-0.035
 cookie-0.034
Token
Token ID198
Feature activation+4.00e-02

Pos logit contributions
 half+0.002
 sticker+0.002
 icing+0.002
 cookie+0.002
Mom+0.002
Neg logit contributions
 vill-0.003
 challenged-0.003
vious-0.003
 current-0.003
 ot-0.003
TokenWith
Token ID3152
Feature activation-4.30e-01

Pos logit contributions
 half+0.001
Mom+0.001
 sticker+0.001
 cookie+0.001
 icing+0.001
Neg logit contributions
 vill-0.002
 challenged-0.002
vious-0.002
 current-0.002
 ot-0.002
Token a
Token ID257
Feature activation+7.24e-01

Pos logit contributions
 vill+0.020
 challenged+0.019
 current+0.019
 ot+0.019
vious+0.019
Neg logit contributions
Mom-0.010
 half-0.010
 sticker-0.009
 cookie-0.009
 icing-0.008
Token mis
Token ID2984
Feature activation-5.29e+00

Pos logit contributions
Mom+0.024
 half+0.024
 sticker+0.023
 cookie+0.022
 ribbon+0.022
Neg logit contributions
 vill-0.026
vious-0.026
 challenged-0.025
 ot-0.025
 current-0.025
Tokenchie
Token ID3043
Feature activation-1.20e+01

Pos logit contributions
 current+0.119
 challenged+0.115
 ot+0.115
 vill+0.113
 ships+0.107
Neg logit contributions
 half-0.240
Mom-0.237
 sticker-0.228
ushes-0.222
 wrist-0.219
Tokenvous
Token ID31222
Feature activation-3.94e+00

Pos logit contributions
 current+0.313
 harbor+0.293
 ot+0.293
 ships+0.276
 ranc+0.272
Neg logit contributions
Mom-0.521
 half-0.517
 sticker-0.487
Anna-0.465
 card-0.455
Token gl
Token ID1278
Feature activation-4.41e+00

Pos logit contributions
 challenged+0.148
vious+0.147
 vill+0.146
roads+0.140
 ships+0.140
Neg logit contributions
 half-0.120
 sticker-0.119
 cookie-0.116
 ribbon-0.112
Mom-0.110
Tokenint
Token ID600
Feature activation-2.77e+00

Pos logit contributions
 vill+0.168
 current+0.166
 challenged+0.165
 ot+0.162
 ships+0.154
Neg logit contributions
 sticker-0.135
 half-0.132
ushes-0.128
Mom-0.124
 wrist-0.120
Token in
Token ID287
Feature activation+2.84e-01

Pos logit contributions
 challenged+0.106
 vill+0.105
 current+0.104
lves+0.103
 ot+0.102
Neg logit contributions
 half-0.085
 sticker-0.080
Mom-0.077
 ribbon-0.073
 icing-0.072
Token her
Token ID607
Feature activation+2.59e+00

Pos logit contributions
 sticker+0.007
Mom+0.007
 cookie+0.007
 half+0.007
 icing+0.007
Neg logit contributions
 vill-0.012
 challenged-0.011
 current-0.011
vious-0.011
 ot-0.011
Token
Token ID198
Feature activation+2.77e-02

Pos logit contributions
 half+0.001
 icing+0.001
 sticker+0.001
 ribbon+0.001
 wrist+0.001
Neg logit contributions
 vill-0.001
 challenged-0.001
 current-0.001
 ot-0.001
vious-0.001
TokenThe
Token ID464
Feature activation-4.11e-01

Pos logit contributions
 sticker+0.001
 half+0.001
 icing+0.001
 ribbon+0.001
 cookie+0.001
Neg logit contributions
 vill-0.001
 challenged-0.001
 current-0.001
vious-0.001
 ot-0.001
Token cat
Token ID3797
Feature activation-1.12e+00

Pos logit contributions
 vill+0.014
 current+0.013
 challenged+0.013
 ot+0.013
vious+0.012
Neg logit contributions
Mom-0.015
 half-0.015
 sticker-0.014
 icing-0.014
ushes-0.014
Token grinned
Token ID36268
Feature activation+1.52e+00

Pos logit contributions
 vill+0.042
 current+0.040
vious+0.040
 ot+0.040
 challenged+0.039
Neg logit contributions
 half-0.035
Mom-0.035
 sticker-0.032
 cookie-0.031
 ribbon-0.031
Token mis
Token ID2984
Feature activation-5.25e+00

Pos logit contributions
 half+0.041
Mom+0.041
 sticker+0.038
 cookie+0.036
 ribbon+0.036
Neg logit contributions
 vill-0.064
 challenged-0.062
 current-0.061
vious-0.061
 ot-0.061
Tokenchie
Token ID3043
Feature activation-1.20e+01

Pos logit contributions
 vill+0.119
 ships+0.118
 current+0.117
 harbor+0.117
 challenged+0.117
Neg logit contributions
 half-0.237
Mom-0.229
 sticker-0.215
ushes-0.213
 wrist-0.208
Tokenv
Token ID85
Feature activation-6.75e-01

Pos logit contributions
 harbor+0.335
 current+0.317
 ships+0.309
 ot+0.305
 ranc+0.298
Neg logit contributions
 half-0.521
Mom-0.499
 sticker-0.466
Anna-0.452
 cookie-0.450
Tokenously
Token ID3481
Feature activation-4.16e+00

Pos logit contributions
 vill+0.024
 challenged+0.023
 current+0.023
 ot+0.023
vious+0.022
Neg logit contributions
 half-0.023
Mom-0.023
 sticker-0.021
 cookie-0.021
 icing-0.020
Token.
Token ID13
Feature activation-5.30e-01

Pos logit contributions
 vill+0.178
vious+0.170
 challenged+0.169
 current+0.169
 ot+0.168
Neg logit contributions
 half-0.110
Mom-0.107
 sticker-0.102
 cookie-0.097
 ribbon-0.096
Token "
Token ID366
Feature activation-1.54e+00

Pos logit contributions
 vill+0.019
 challenged+0.018
 current+0.018
 ot+0.017
vious+0.017
Neg logit contributions
Mom-0.018
 half-0.018
 sticker-0.017
 icing-0.016
 cookie-0.016
TokenNever
Token ID12295
Feature activation-1.50e+00

Pos logit contributions
 vill+0.062
 challenged+0.060
vious+0.059
 ot+0.059
 current+0.059
Neg logit contributions
 half-0.043
 sticker-0.042
Mom-0.041
 cookie-0.040
 icing-0.040
TokenOne
Token ID3198
Feature activation+1.72e+00

Pos logit contributions
Mom+0.009
 half+0.008
 sticker+0.008
 cookie+0.008
 icing+0.008
Neg logit contributions
 vill-0.014
 challenged-0.014
 current-0.014
 ot-0.014
vious-0.014
Token day
Token ID1110
Feature activation-4.06e-01

Pos logit contributions
Mom+0.049
 half+0.047
 sticker+0.044
 cookie+0.043
Anna+0.040
Neg logit contributions
 challenged-0.071
 current-0.071
 vill-0.070
vious-0.070
 ot-0.067
Token,
Token ID11
Feature activation-5.30e-01

Pos logit contributions
 vill+0.015
 challenged+0.015
 current+0.015
vious+0.015
 ot+0.015
Neg logit contributions
Mom-0.013
 half-0.013
 sticker-0.012
 cookie-0.011
 icing-0.011
Token a
Token ID257
Feature activation+9.47e-01

Pos logit contributions
 vill+0.025
vious+0.024
 challenged+0.024
 current+0.024
 ot+0.024
Neg logit contributions
 half-0.012
Mom-0.012
 sticker-0.011
 cookie-0.010
 ribbon-0.010
Token mis
Token ID2984
Feature activation-5.16e+00

Pos logit contributions
Mom+0.034
 sticker+0.033
 cookie+0.033
 half+0.033
 ribbon+0.031
Neg logit contributions
vious-0.032
 challenged-0.030
 current-0.029
 vill-0.029
roads-0.029
Tokenchie
Token ID3043
Feature activation-1.20e+01

Pos logit contributions
 current+0.106
 challenged+0.106
 vill+0.105
 ot+0.100
vious+0.097
Neg logit contributions
Mom-0.244
 half-0.241
 sticker-0.229
 ribbon-0.223
 wrist-0.222
Tokenvous
Token ID31222
Feature activation-3.90e+00

Pos logit contributions
 current+0.310
 ot+0.274
 fishermen+0.274
 ships+0.270
 harbor+0.265
Neg logit contributions
Mom-0.533
 half-0.502
Anna-0.481
 sticker-0.476
 card-0.451
Token young
Token ID1862
Feature activation-2.82e+00

Pos logit contributions
roads+0.149
vious+0.147
 challenged+0.144
ounded+0.137
 current+0.135
Neg logit contributions
 cookie-0.118
 sticker-0.115
 half-0.109
Mom-0.108
 ribbon-0.107
Token boy
Token ID2933
Feature activation-4.73e+00

Pos logit contributions
vious+0.108
roads+0.100
rated+0.100
ounded+0.098
enced+0.097
Neg logit contributions
Mom-0.084
 half-0.084
 sticker-0.084
 cookie-0.083
 doll-0.081
Token decided
Token ID3066
Feature activation-1.09e+00

Pos logit contributions
 current+0.156
 vill+0.151
 bust+0.144
vious+0.142
 daunting+0.139
Neg logit contributions
 half-0.171
Mom-0.166
 sticker-0.156
 cookie-0.151
 tape-0.148
Token to
Token ID284
Feature activation-1.49e+00

Pos logit contributions
vious+0.059
 vill+0.059
 current+0.058
enced+0.058
 bust+0.057
Neg logit contributions
 half-0.015
 sticker-0.013
Mom-0.012
 herself-0.011
 cookie-0.010
Token's
Token ID338
Feature activation+2.15e+00

Pos logit contributions
Mom+0.026
 half+0.025
 cookie+0.022
 sticker+0.021
 ribbon+0.020
Neg logit contributions
 vill-0.047
 current-0.045
vious-0.044
 challenged-0.044
 ot-0.043
Token share
Token ID2648
Feature activation+6.48e+00

Pos logit contributions
Mom+0.069
 half+0.069
ushes+0.068
 sticker+0.067
 icing+0.066
Neg logit contributions
 ot-0.076
 challenged-0.075
 vill-0.074
 current-0.074
vious-0.070
Token our
Token ID674
Feature activation+3.12e+00

Pos logit contributions
ushes+0.228
 scalp+0.227
Mom+0.226
Elsa+0.218
 bookmark+0.210
Neg logit contributions
 ot-0.195
 ships-0.184
 challenged-0.176
 padd-0.170
 fishermen-0.170
Token bread
Token ID8509
Feature activation+2.69e+00

Pos logit contributions
Mom+0.106
Anna+0.101
ushes+0.101
 icing+0.100
 scalp+0.099
Neg logit contributions
 ot-0.105
 current-0.101
 vill-0.101
 challenged-0.096
 ships-0.096
Token and
Token ID290
Feature activation+6.99e-01

Pos logit contributions
Mom+0.079
Elsa+0.073
 icing+0.073
 bookmark+0.071
 sticker+0.071
Neg logit contributions
 ot-0.102
 fishermen-0.092
 ships-0.090
 challenged-0.088
 oct-0.086
Token cheese
Token ID9891
Feature activation+5.33e+00

Pos logit contributions
Mom+0.021
ushes+0.020
 icing+0.019
 sticker+0.019
Anna+0.019
Neg logit contributions
 ot-0.027
 current-0.027
 challenged-0.026
 vill-0.025
 padd-0.025
Token with
Token ID351
Feature activation+3.31e-01

Pos logit contributions
Mom+0.174
Elsa+0.149
 icing+0.147
 bookmark+0.146
 ribbon+0.145
Neg logit contributions
 ot-0.192
 fishermen-0.178
 challenged-0.174
 current-0.173
 vill-0.171
Token it
Token ID340
Feature activation+1.00e+00

Pos logit contributions
 wrist+0.010
ushes+0.010
 bookmark+0.010
 sticker+0.010
Mom+0.009
Neg logit contributions
 ot-0.012
 ships-0.011
 current-0.011
 fishermen-0.011
 vill-0.011
Token instead
Token ID2427
Feature activation+1.20e+00

Pos logit contributions
Mom+0.032
 sticker+0.028
 half+0.028
 wrist+0.028
 icing+0.028
Neg logit contributions
 challenged-0.035
 ot-0.035
vious-0.035
 vill-0.034
 current-0.033
Token."
Token ID526
Feature activation+1.76e+00

Pos logit contributions
Mom+0.034
 sticker+0.033
 ribbon+0.032
 wrist+0.032
 half+0.032
Neg logit contributions
 challenged-0.046
vious-0.045
 vill-0.045
 current-0.045
 ot-0.043
Token She
Token ID1375
Feature activation+5.63e-01

Pos logit contributions
 half+0.051
 sticker+0.050
Mom+0.049
 ribbon+0.047
 icing+0.046
Neg logit contributions
 vill-0.068
 challenged-0.067
 ot-0.066
vious-0.065
 current-0.065
Token and
Token ID290
Feature activation+9.23e-01

Pos logit contributions
 half+0.007
Mom+0.007
 sticker+0.007
 cookie+0.006
 icing+0.006
Neg logit contributions
 vill-0.012
 challenged-0.011
 current-0.011
vious-0.011
 ot-0.011
Token then
Token ID788
Feature activation+2.03e+00

Pos logit contributions
 half+0.030
Mom+0.030
 sticker+0.029
 cookie+0.027
 icing+0.027
Neg logit contributions
 vill-0.034
 challenged-0.032
 current-0.032
vious-0.032
 ot-0.032
Token came
Token ID1625
Feature activation-3.47e+00

Pos logit contributions
 half+0.068
Mom+0.066
 sticker+0.065
 cookie+0.061
 icing+0.061
Neg logit contributions
 vill-0.073
vious-0.069
 current-0.069
 challenged-0.068
 ot-0.068
Token back
Token ID736
Feature activation+1.41e+00

Pos logit contributions
 vill+0.119
 challenged+0.118
 ot+0.114
 current+0.114
 padd+0.112
Neg logit contributions
 sticker-0.111
 icing-0.111
Mom-0.111
 cookie-0.110
 half-0.110
Token to
Token ID284
Feature activation-1.18e+00

Pos logit contributions
Mom+0.040
 half+0.039
 sticker+0.038
 icing+0.037
 ribbon+0.036
Neg logit contributions
 vill-0.056
 challenged-0.055
 ot-0.054
 current-0.053
vious-0.052
Token play
Token ID711
Feature activation+3.40e+00

Pos logit contributions
 vill+0.045
 challenged+0.044
 ot+0.043
 current+0.043
vious+0.041
Neg logit contributions
Mom-0.036
 half-0.036
 sticker-0.034
ushes-0.033
 icing-0.033
Token.
Token ID13
Feature activation+3.62e-01

Pos logit contributions
Mom+0.086
 half+0.083
 sticker+0.079
 icing+0.076
ushes+0.076
Neg logit contributions
 vill-0.147
 challenged-0.142
 current-0.140
 ot-0.140
vious-0.139
Token
Token ID198
Feature activation+6.56e-01

Pos logit contributions
 half+0.011
Mom+0.011
 sticker+0.011
 icing+0.010
 ribbon+0.010
Neg logit contributions
 vill-0.013
 challenged-0.013
 current-0.013
 ot-0.013
vious-0.013
Token
Token ID198
Feature activation+7.13e-01

Pos logit contributions
 half+0.018
 sticker+0.018
 icing+0.018
 ribbon+0.018
 wrist+0.017
Neg logit contributions
 vill-0.026
 challenged-0.025
 ot-0.024
 current-0.024
vious-0.024
TokenBut
Token ID1537
Feature activation+6.81e-01

Pos logit contributions
 sticker+0.018
 icing+0.018
 half+0.018
 ribbon+0.017
 cookie+0.016
Neg logit contributions
 vill-0.031
 challenged-0.030
vious-0.029
 ot-0.028
 current-0.028
Token then
Token ID788
Feature activation+2.31e+00

Pos logit contributions
Mom+0.022
 sticker+0.022
ushes+0.022
 half+0.022
 icing+0.021
Neg logit contributions
 vill-0.023
 challenged-0.023
 ot-0.023
 current-0.023
 padd-0.021
Token every
Token ID790
Feature activation-9.37e-01

Pos logit contributions
 vill+0.055
 ot+0.054
 challenged+0.053
 current+0.052
vious+0.048
Neg logit contributions
Mom-0.060
 sticker-0.059
 half-0.058
ushes-0.057
 icing-0.057
Token day
Token ID1110
Feature activation-3.99e-01

Pos logit contributions
 vill+0.033
 challenged+0.031
 current+0.031
vious+0.031
 ot+0.031
Neg logit contributions
Mom-0.031
 half-0.031
 sticker-0.030
 icing-0.029
ushes-0.029
Token,
Token ID11
Feature activation-1.12e-01

Pos logit contributions
 vill+0.016
 challenged+0.015
 current+0.015
 ot+0.015
vious+0.015
Neg logit contributions
Mom-0.012
 half-0.012
 sticker-0.011
 icing-0.011
 cookie-0.010
Token Lily
Token ID20037
Feature activation+3.40e+00

Pos logit contributions
 vill+0.004
 ot+0.004
 challenged+0.004
 current+0.004
vious+0.004
Neg logit contributions
Mom-0.003
 half-0.003
 sticker-0.003
ushes-0.003
 icing-0.003
Token and
Token ID290
Feature activation+7.36e-01

Pos logit contributions
Mom+0.108
 half+0.108
 sticker+0.105
 cookie+0.099
 ribbon+0.099
Neg logit contributions
 vill-0.124
 current-0.122
 ot-0.117
vious-0.116
 challenged-0.113
Token her
Token ID607
Feature activation+3.20e+00

Pos logit contributions
Mom+0.014
ushes+0.014
 half+0.013
 sticker+0.013
 icing+0.013
Neg logit contributions
 vill-0.036
 challenged-0.035
 ot-0.035
 current-0.033
vious-0.033
Token mom
Token ID1995
Feature activation+2.19e+00

Pos logit contributions
ushes+0.081
Mom+0.081
 half+0.079
rap+0.078
Anna+0.077
Neg logit contributions
 ot-0.133
 vill-0.126
 current-0.121
 vehicle-0.120
 ships-0.120
Tokenmy
Token ID1820
Feature activation+3.31e+00

Pos logit contributions
 half+0.067
Mom+0.067
 sticker+0.065
 wrist+0.062
 cookie+0.062
Neg logit contributions
 challenged-0.079
 vill-0.078
 ot-0.076
vious-0.076
 bust-0.073
Token would
Token ID561
Feature activation+2.52e+00

Pos logit contributions
Mom+0.123
 half+0.123
 sticker+0.118
 cookie+0.113
 icing+0.113
Neg logit contributions
 vill-0.104
 challenged-0.100
 current-0.098
 ot-0.098
vious-0.097
Token step
Token ID2239
Feature activation-2.68e+00

Pos logit contributions
 half+0.080
Mom+0.080
 sticker+0.077
ushes+0.076
 cookie+0.074
Neg logit contributions
 vill-0.090
 challenged-0.089
 ot-0.088
 current-0.087
 padd-0.083
Token outside
Token ID2354
Feature activation+2.15e+00

Pos logit contributions
 vill+0.090
 ot+0.087
 challenged+0.086
vious+0.085
 padd+0.085
Neg logit contributions
 half-0.091
Mom-0.091
 sticker-0.087
 wrist-0.084
 icing-0.084
Token.
Token ID13
Feature activation-6.06e-01

Pos logit contributions
 half+0.002
Mom+0.002
 sticker+0.002
 cookie+0.002
 wrist+0.002
Neg logit contributions
 vill-0.005
 current-0.005
vious-0.005
 challenged-0.005
 ot-0.005
Token They
Token ID1119
Feature activation-1.85e+00

Pos logit contributions
 vill+0.025
vious+0.024
 current+0.024
 ot+0.023
 challenged+0.023
Neg logit contributions
Mom-0.017
 half-0.017
 sticker-0.016
 ribbon-0.015
 icing-0.015
Token felt
Token ID2936
Feature activation-4.29e+00

Pos logit contributions
 vill+0.070
vious+0.069
 current+0.069
roads+0.068
ican+0.067
Neg logit contributions
Mom-0.062
 half-0.056
 love-0.051
 icing-0.050
 ribbon-0.049
Token the
Token ID262
Feature activation-1.93e+00

Pos logit contributions
 vill+0.183
 challenged+0.179
 current+0.175
ican+0.172
itive+0.170
Neg logit contributions
 herself-0.103
 half-0.102
Mom-0.101
 sticker-0.101
 cookie-0.093
Token warm
Token ID5814
Feature activation+3.85e+00

Pos logit contributions
 vill+0.078
 challenged+0.075
vious+0.074
 current+0.074
 ot+0.073
Neg logit contributions
Mom-0.056
 half-0.055
 sticker-0.053
 ribbon-0.050
 icing-0.050
Token sand
Token ID6450
Feature activation+4.44e+00

Pos logit contributions
Mom+0.109
 half+0.108
 sticker+0.103
 icing+0.098
 cookie+0.098
Neg logit contributions
 vill-0.158
 challenged-0.152
vious-0.149
 current-0.148
 ot-0.146
Token under
Token ID739
Feature activation+1.58e+00

Pos logit contributions
Mom+0.139
 half+0.135
 sticker+0.128
ushes+0.122
 cookie+0.121
Neg logit contributions
 vill-0.165
 ot-0.161
 current-0.161
 challenged-0.158
 ships-0.154
Token their
Token ID511
Feature activation+2.17e+00

Pos logit contributions
 sticker+0.045
 half+0.045
Mom+0.045
ushes+0.044
 cookie+0.043
Neg logit contributions
 vill-0.061
 ot-0.060
 current-0.059
 challenged-0.058
 ships-0.057
Token feet
Token ID3625
Feature activation-5.32e-01

Pos logit contributions
 half+0.074
Mom+0.073
 sticker+0.072
 cookie+0.069
 icing+0.068
Neg logit contributions
 vill-0.075
 current-0.073
 ot-0.072
 ships-0.071
 challenged-0.068
Token.
Token ID13
Feature activation-5.01e-01

Pos logit contributions
 vill+0.023
 challenged+0.022
 current+0.022
vious+0.022
 ot+0.022
Neg logit contributions
 half-0.013
Mom-0.013
 sticker-0.013
 cookie-0.012
 icing-0.012
Token
Token ID198
Feature activation+2.23e-01

Pos logit contributions
 vill+0.021
 current+0.020
vious+0.020
 ot+0.020
 challenged+0.020
Neg logit contributions
Mom-0.013
 half-0.013
 sticker-0.013
 cookie-0.012
 icing-0.012
Token flour
Token ID10601
Feature activation+3.51e+00

Pos logit contributions
Mom+0.007
 wrist+0.007
 half+0.007
 sticker+0.006
Anna+0.006
Neg logit contributions
 ot-0.010
 vill-0.010
vious-0.009
 current-0.009
 ships-0.009
Token,
Token ID11
Feature activation-5.39e-01

Pos logit contributions
 wrist+0.113
Mom+0.112
 bookmark+0.110
Anna+0.109
 sticker+0.108
Neg logit contributions
 ot-0.121
 current-0.110
 vill-0.110
 ships-0.108
 padd-0.108
Token sugar
Token ID7543
Feature activation+4.64e+00

Pos logit contributions
 vill+0.025
 ot+0.024
 challenged+0.024
 current+0.024
vious+0.024
Neg logit contributions
Mom-0.011
 half-0.011
 sticker-0.011
 wrist-0.010
ushes-0.010
Token and
Token ID290
Feature activation+1.82e-01

Pos logit contributions
 wrist+0.156
Mom+0.152
 bookmark+0.152
 sticker+0.151
 Love+0.150
Neg logit contributions
 ot-0.151
 vill-0.140
 padd-0.137
 current-0.137
 challenged-0.136
Token eggs
Token ID9653
Feature activation+8.04e-01

Pos logit contributions
 wrist+0.004
 sticker+0.004
Mom+0.004
 half+0.004
ushes+0.004
Neg logit contributions
 vill-0.008
 ot-0.008
 challenged-0.008
 current-0.007
vious-0.007
Token inside
Token ID2641
Feature activation+3.46e+00

Pos logit contributions
Mom+0.025
 sticker+0.023
 half+0.023
 bookmark+0.023
 wrist+0.023
Neg logit contributions
 ot-0.030
 challenged-0.028
 vill-0.028
 current-0.028
 padd-0.027
Token it
Token ID340
Feature activation+5.50e-01

Pos logit contributions
 wrist+0.120
Elsa+0.119
Mom+0.118
 bookmark+0.117
 sticker+0.117
Neg logit contributions
 vill-0.099
vious-0.095
 challenged-0.093
 ot-0.093
 overwhelmed-0.089
Token.
Token ID13
Feature activation-2.99e-01

Pos logit contributions
Mom+0.017
 sticker+0.017
 half+0.016
 bookmark+0.016
 wrist+0.016
Neg logit contributions
 vill-0.019
 challenged-0.019
 ot-0.019
 current-0.018
vious-0.018
Token She
Token ID1375
Feature activation-3.43e-02

Pos logit contributions
 vill+0.009
 challenged+0.009
 Int+0.009
vious+0.009
 Curious+0.008
Neg logit contributions
 sticker-0.011
 ribbon-0.011
 half-0.010
 bookmark-0.010
Mom-0.010
Token began
Token ID2540
Feature activation+7.96e-01

Pos logit contributions
 vill+0.001
 challenged+0.001
 ot+0.001
 current+0.001
vious+0.001
Neg logit contributions
Mom-0.001
 half-0.001
 sticker-0.001
 cookie-0.001
 ribbon-0.001
Token to
Token ID284
Feature activation-1.42e+00

Pos logit contributions
Mom+0.026
 half+0.024
 sticker+0.024
 wrist+0.023
 ribbon+0.023
Neg logit contributions
 vill-0.029
 challenged-0.028
 ot-0.027
 padd-0.027
 current-0.027
Token was
Token ID373
Feature activation-1.42e+00

Pos logit contributions
Mom+0.086
 half+0.086
 sticker+0.083
 icing+0.080
 cookie+0.079
Neg logit contributions
 vill-0.082
 challenged-0.079
 current-0.077
 ot-0.076
vious-0.076
Token amazed
Token ID24562
Feature activation-4.26e+00

Pos logit contributions
 vill+0.043
 current+0.041
 challenged+0.040
 ot+0.040
vious+0.039
Neg logit contributions
 half-0.056
Mom-0.055
 sticker-0.053
 cookie-0.051
 icing-0.051
Token.
Token ID13
Feature activation-4.46e-01

Pos logit contributions
 vill+0.176
 current+0.169
 challenged+0.169
 ot+0.166
vious+0.166
Neg logit contributions
Mom-0.119
 half-0.119
 sticker-0.112
 icing-0.106
 cookie-0.105
Token
Token ID220
Feature activation-1.26e+00

Pos logit contributions
 vill+0.016
 challenged+0.015
 ot+0.014
vious+0.014
 Int+0.014
Neg logit contributions
 sticker-0.015
 half-0.015
 ribbon-0.014
 icing-0.014
Mom-0.014
Token
Token ID198
Feature activation-8.96e-02

Pos logit contributions
 vill+0.043
 challenged+0.042
vious+0.040
 ot+0.039
 Int+0.038
Neg logit contributions
 sticker-0.040
 ribbon-0.040
 half-0.040
 icing-0.039
Mom-0.038
Token
Token ID198
Feature activation-1.07e-01

Pos logit contributions
 vill+0.003
 challenged+0.003
 Int+0.003
ules+0.003
 Jon+0.003
Neg logit contributions
 sticker-0.003
 icing-0.003
 half-0.003
 ribbon-0.003
 cookie-0.003
TokenAfter
Token ID3260
Feature activation+5.52e+00

Pos logit contributions
 vill+0.004
 challenged+0.004
roads+0.004
vious+0.004
 bust+0.004
Neg logit contributions
 sticker-0.003
 half-0.003
 icing-0.003
 cookie-0.003
 card-0.003
Token a
Token ID257
Feature activation+7.43e-01

Pos logit contributions
Mom+0.185
 half+0.180
ushes+0.179
 sticker+0.175
 wrist+0.170
Neg logit contributions
 vill-0.198
 ot-0.185
 challenged-0.184
 current-0.180
 padd-0.176
Token while
Token ID981
Feature activation+1.32e+00

Pos logit contributions
 half+0.028
Mom+0.028
ushes+0.027
 icing+0.027
 sticker+0.026
Neg logit contributions
 vill-0.023
 challenged-0.022
 current-0.021
 ot-0.021
 bust-0.020
Token,
Token ID11
Feature activation-7.63e-01

Pos logit contributions
Mom+0.045
 half+0.045
 sticker+0.044
 wrist+0.042
ushes+0.042
Neg logit contributions
 vill-0.045
 current-0.043
 challenged-0.043
 ot-0.043
vious-0.042
Token Lucy
Token ID22162
Feature activation+2.48e+00

Pos logit contributions
 vill+0.028
 ot+0.027
 challenged+0.027
 current+0.026
vious+0.025
Neg logit contributions
Mom-0.024
 half-0.023
 sticker-0.023
ushes-0.022
 wrist-0.022
Token.
Token ID13
Feature activation-6.44e-01

Pos logit contributions
Mom+0.155
 half+0.150
 sticker+0.143
ushes+0.134
 icing+0.134
Neg logit contributions
 vill-0.228
 ot-0.219
 challenged-0.219
 current-0.217
vious-0.215
Token<|endoftext|>
Token ID50256
Feature activation-1.16e-01

Pos logit contributions
 vill+0.026
 challenged+0.025
 current+0.025
 ot+0.025
vious+0.025
Neg logit contributions
 half-0.018
Mom-0.018
 sticker-0.018
 ribbon-0.016
 icing-0.016
TokenOnce
Token ID7454
Feature activation+8.01e-01

Pos logit contributions
 vill+0.004
 challenged+0.003
 ot+0.003
 current+0.003
vious+0.003
Neg logit contributions
 half-0.004
Mom-0.004
 sticker-0.004
 icing-0.004
 ribbon-0.004
Token upon
Token ID2402
Feature activation+1.61e-01

Pos logit contributions
 half+0.029
Mom+0.028
 sticker+0.026
 cookie+0.026
ushes+0.026
Neg logit contributions
 vill-0.027
 current-0.026
 challenged-0.026
vious-0.026
 ot-0.026
Token a
Token ID257
Feature activation+5.27e-01

Pos logit contributions
Mom+0.005
 sticker+0.005
ushes+0.005
 half+0.005
 wrist+0.005
Neg logit contributions
 vill-0.006
 challenged-0.006
vious-0.005
 ot-0.005
 padd-0.005
Token time
Token ID640
Feature activation+5.59e-01

Pos logit contributions
 half+0.017
Mom+0.017
 sticker+0.016
 icing+0.015
 ribbon+0.015
Neg logit contributions
 vill-0.019
 challenged-0.018
 current-0.018
vious-0.018
 ot-0.018
Token,
Token ID11
Feature activation-7.48e-01

Pos logit contributions
 half+0.015
Mom+0.015
 sticker+0.013
 cookie+0.013
 icing+0.012
Neg logit contributions
 vill-0.024
 current-0.023
vious-0.023
 challenged-0.023
 ot-0.023
Token there
Token ID612
Feature activation-1.85e+00

Pos logit contributions
 vill+0.023
 challenged+0.022
 current+0.021
 ot+0.021
vious+0.021
Neg logit contributions
Mom-0.029
 half-0.029
 sticker-0.028
 cookie-0.027
 icing-0.027
Token was
Token ID373
Feature activation-1.51e+00

Pos logit contributions
 vill+0.066
 challenged+0.064
 ot+0.063
 current+0.062
vious+0.061
Neg logit contributions
Mom-0.060
 half-0.060
 sticker-0.059
 icing-0.056
 ribbon-0.056
Token a
Token ID257
Feature activation+5.70e-01

Pos logit contributions
 ot+0.053
 vill+0.052
vious+0.050
 challenged+0.050
 current+0.048
Neg logit contributions
 sticker-0.047
 wrist-0.047
ushes-0.046
Mom-0.045
 half-0.045
Token little
Token ID1310
Feature activation-2.93e+00

Pos logit contributions
Mom+0.023
 half+0.023
 sticker+0.022
 cookie+0.021
 icing+0.021
Neg logit contributions
 vill-0.016
 challenged-0.015
 current-0.015
 ot-0.015
vious-0.015
Token squirrel
Token ID33039
Feature activation-4.10e+00

Pos logit contributions
 vill+0.040
 current+0.038
 challenged+0.037
 ot+0.037
vious+0.036
Neg logit contributions
 half-0.048
Mom-0.048
 sticker-0.046
 icing-0.045
 cookie-0.044
Token said
Token ID531
Feature activation-1.09e+00

Pos logit contributions
 vill+0.143
 current+0.142
 hurricane+0.138
 harbor+0.137
 ot+0.136
Neg logit contributions
 half-0.143
Mom-0.136
 sticker-0.126
 cookie-0.123
 ribbon-0.118
Token.
Token ID13
Feature activation+1.20e+00

Pos logit contributions
 vill+0.051
 challenged+0.049
 current+0.049
 ot+0.049
vious+0.048
Neg logit contributions
Mom-0.024
 half-0.024
 sticker-0.023
 cookie-0.021
 icing-0.021
Token "
Token ID366
Feature activation-4.76e-01

Pos logit contributions
Mom+0.041
 half+0.041
 sticker+0.039
 icing+0.038
 cookie+0.037
Neg logit contributions
 vill-0.042
 challenged-0.040
 current-0.040
 ot-0.039
vious-0.039
TokenIt
Token ID1026
Feature activation+8.44e-01

Pos logit contributions
 vill+0.019
vious+0.017
 current+0.017
 challenged+0.017
 ot+0.017
Neg logit contributions
 icing-0.014
 ribbon-0.013
 half-0.013
 sticker-0.013
 bookmark-0.013
Token is
Token ID318
Feature activation+1.17e+00

Pos logit contributions
 half+0.018
Mom+0.017
 sticker+0.017
 cookie+0.016
 icing+0.015
Neg logit contributions
 vill-0.040
 current-0.039
 challenged-0.039
 ot-0.038
vious-0.038
Token my
Token ID616
Feature activation+3.62e+00

Pos logit contributions
Mom+0.038
 wrist+0.037
 sticker+0.036
 icing+0.035
 half+0.035
Neg logit contributions
 ot-0.041
 vill-0.040
 current-0.040
 challenged-0.039
 fishermen-0.038
Token home
Token ID1363
Feature activation+1.20e+00

Pos logit contributions
Mom+0.124
 half+0.113
 icing+0.110
 sticker+0.110
Anna+0.109
Neg logit contributions
 vill-0.129
 ot-0.127
 current-0.125
 challenged-0.119
vious-0.115
Token.
Token ID13
Feature activation+9.39e-01

Pos logit contributions
Mom+0.035
 ribbon+0.035
 icing+0.033
 half+0.033
 sticker+0.032
Neg logit contributions
 vill-0.044
vious-0.044
 ot-0.042
 current-0.042
 challenged-0.041
Token I
Token ID314
Feature activation+6.86e-01

Pos logit contributions
 half+0.030
 ribbon+0.030
 sticker+0.030
Mom+0.029
 icing+0.029
Neg logit contributions
 vill-0.033
 ot-0.032
vious-0.031
 current-0.031
 challenged-0.031
Token have
Token ID423
Feature activation+5.03e+00

Pos logit contributions
 half+0.020
Mom+0.020
 sticker+0.019
 cookie+0.018
 ribbon+0.018
Neg logit contributions
 vill-0.027
 current-0.026
 challenged-0.026
 ot-0.026
vious-0.026
Token world
Token ID995
Feature activation-4.78e+00

Pos logit contributions
Mom+0.079
 half+0.077
 sticker+0.074
 icing+0.072
ushes+0.072
Neg logit contributions
 vill-0.089
 ot-0.085
 current-0.084
 challenged-0.084
vious-0.080
Token,
Token ID11
Feature activation-6.48e-01

Pos logit contributions
 vill+0.195
 challenged+0.188
 current+0.187
 ot+0.185
vious+0.185
Neg logit contributions
 half-0.133
Mom-0.132
 sticker-0.126
 cookie-0.119
 icing-0.119
Token just
Token ID655
Feature activation-8.54e-01

Pos logit contributions
 vill+0.025
 challenged+0.024
 current+0.023
vious+0.023
 ot+0.023
Neg logit contributions
 half-0.020
Mom-0.020
 sticker-0.019
 icing-0.018
 cookie-0.018
Token waiting
Token ID4953
Feature activation-3.34e-01

Pos logit contributions
 vill+0.033
 challenged+0.031
 current+0.031
vious+0.031
 ot+0.030
Neg logit contributions
 half-0.027
Mom-0.025
 sticker-0.025
 icing-0.024
 ribbon-0.024
Token to
Token ID284
Feature activation-1.52e+00

Pos logit contributions
 vill+0.013
 challenged+0.012
 current+0.012
 ot+0.012
vious+0.012
Neg logit contributions
Mom-0.010
 half-0.010
 sticker-0.010
 cookie-0.009
 icing-0.009
Token be
Token ID307
Feature activation-8.74e-01

Pos logit contributions
 vill+0.060
 challenged+0.058
 current+0.058
 ot+0.057
vious+0.056
Neg logit contributions
Mom-0.045
 half-0.043
 sticker-0.042
 cookie-0.040
 icing-0.040
Token explored
Token ID18782
Feature activation-6.90e-01

Pos logit contributions
 vill+0.034
 current+0.032
 challenged+0.032
vious+0.032
 ot+0.032
Neg logit contributions
 half-0.027
Mom-0.026
 sticker-0.025
 icing-0.024
 cookie-0.024
Token.
Token ID13
Feature activation-5.50e-01

Pos logit contributions
 vill+0.028
 challenged+0.027
 current+0.027
 ot+0.027
vious+0.026
Neg logit contributions
Mom-0.019
 half-0.019
 sticker-0.018
 cookie-0.017
 icing-0.017
Token And
Token ID843
Feature activation-2.00e-01

Pos logit contributions
 vill+0.024
 challenged+0.023
 current+0.023
 ot+0.022
vious+0.022
Neg logit contributions
Mom-0.014
 half-0.014
 sticker-0.014
 icing-0.013
 cookie-0.013
Token so
Token ID523
Feature activation-3.37e+00

Pos logit contributions
 vill+0.008
vious+0.008
 current+0.008
 challenged+0.008
 ot+0.007
Neg logit contributions
 half-0.006
Mom-0.006
 sticker-0.005
 ribbon-0.005
 cookie-0.005
Token,
Token ID11
Feature activation-5.93e-01

Pos logit contributions
 vill+0.136
vious+0.134
 challenged+0.132
 current+0.131
 ot+0.131
Neg logit contributions
 half-0.096
Mom-0.094
 sticker-0.088
 cookie-0.084
 ribbon-0.082
Token and
Token ID290
Feature activation+1.17e+00

Pos logit contributions
 vill+0.254
 challenged+0.244
 current+0.243
 ot+0.239
vious+0.233
Neg logit contributions
Mom-0.157
 half-0.157
 sticker-0.143
 cookie-0.136
 icing-0.132
Token did
Token ID750
Feature activation+3.24e+00

Pos logit contributions
 half+0.043
Mom+0.042
 sticker+0.041
 herself+0.041
 cookie+0.040
Neg logit contributions
 vill-0.036
 ot-0.033
ules-0.032
 current-0.032
ican-0.032
Token not
Token ID407
Feature activation+7.45e-01

Pos logit contributions
Mom+0.084
 icing+0.078
 half+0.076
 sticker+0.072
 cookie+0.072
Neg logit contributions
 challenged-0.137
 vill-0.136
vious-0.132
 current-0.130
 padd-0.129
Token want
Token ID765
Feature activation+5.91e-01

Pos logit contributions
 half+0.027
 sticker+0.026
Mom+0.026
 cookie+0.025
 ribbon+0.024
Neg logit contributions
 vill-0.025
 current-0.024
 ot-0.023
 challenged-0.023
vious-0.023
Token to
Token ID284
Feature activation-7.80e-01

Pos logit contributions
Mom+0.020
 wrist+0.018
 half+0.018
 sticker+0.018
 icing+0.017
Neg logit contributions
 vill-0.022
 current-0.020
 challenged-0.020
vious-0.020
 ot-0.020
Token touch
Token ID3638
Feature activation+1.47e+00

Pos logit contributions
 vill+0.027
 challenged+0.026
 ot+0.026
 current+0.026
vious+0.025
Neg logit contributions
Mom-0.027
 half-0.026
 sticker-0.025
 icing-0.025
ushes-0.025
Token the
Token ID262
Feature activation-1.23e+00

Pos logit contributions
Mom+0.042
 sticker+0.039
 half+0.039
 icing+0.038
ushes+0.038
Neg logit contributions
 vill-0.058
 ot-0.056
 current-0.056
vious-0.055
 challenged-0.054
Token chest
Token ID7721
Feature activation+4.78e-01

Pos logit contributions
 current+0.039
 ot+0.038
 vill+0.037
 eagle+0.036
 wolf+0.035
Neg logit contributions
Mom-0.045
ushes-0.045
Her-0.041
 icing-0.041
 half-0.041
Token.
Token ID13
Feature activation+1.06e+00

Pos logit contributions
Mom+0.012
 half+0.011
 sticker+0.011
 icing+0.010
 cookie+0.010
Neg logit contributions
 vill-0.021
 current-0.020
 challenged-0.020
 ot-0.020
vious-0.020
Token
Token ID198
Feature activation+1.61e+00

Pos logit contributions
 half+0.028
Mom+0.027
 sticker+0.027
 icing+0.025
 ribbon+0.025
Neg logit contributions
 vill-0.045
 challenged-0.044
 current-0.043
 ot-0.043
vious-0.043
Token
Token ID198
Feature activation+1.60e+00

Pos logit contributions
 half+0.045
 sticker+0.044
 icing+0.044
 ribbon+0.043
 cookie+0.043
Neg logit contributions
 vill-0.064
 challenged-0.061
 current-0.060
 ot-0.060
vious-0.058
Token a
Token ID257
Feature activation+8.73e-01

Pos logit contributions
 vill+0.004
 challenged+0.004
vious+0.004
 ot+0.004
 current+0.004
Neg logit contributions
Mom-0.003
 half-0.003
 sticker-0.003
ushes-0.003
 icing-0.003
Token time
Token ID640
Feature activation+6.97e-01

Pos logit contributions
Mom+0.026
 half+0.026
 sticker+0.024
 cookie+0.023
 icing+0.023
Neg logit contributions
 vill-0.034
 challenged-0.033
 current-0.033
 ot-0.033
vious-0.033
Token there
Token ID612
Feature activation-1.80e+00

Pos logit contributions
 half+0.019
Mom+0.019
 sticker+0.017
 cookie+0.017
 icing+0.016
Neg logit contributions
 vill-0.029
 current-0.028
vious-0.028
 challenged-0.028
 ot-0.028
Token was
Token ID373
Feature activation-1.36e+00

Pos logit contributions
 vill+0.067
 challenged+0.064
 current+0.064
 ot+0.063
vious+0.063
Neg logit contributions
Mom-0.056
 half-0.056
 sticker-0.054
 icing-0.052
 cookie-0.051
Token a
Token ID257
Feature activation+8.93e-01

Pos logit contributions
 ot+0.052
 vill+0.051
 challenged+0.049
vious+0.049
 current+0.048
Neg logit contributions
 sticker-0.040
 half-0.039
 wrist-0.039
ushes-0.038
Mom-0.038
Token squirrel
Token ID33039
Feature activation-4.62e+00

Pos logit contributions
Mom+0.036
 half+0.036
 sticker+0.035
 cookie+0.033
 icing+0.033
Neg logit contributions
 vill-0.025
 challenged-0.024
 current-0.024
vious-0.024
 ot-0.023
Token.
Token ID13
Feature activation-4.93e-01

Pos logit contributions
 vill+0.170
 current+0.168
vious+0.162
 bust+0.161
 challenged+0.159
Neg logit contributions
Mom-0.150
 half-0.146
 sticker-0.140
 cookie-0.134
Anna-0.127
Token It
Token ID632
Feature activation+9.70e-01

Pos logit contributions
 vill+0.017
 challenged+0.016
 current+0.016
vious+0.016
 ot+0.016
Neg logit contributions
 half-0.017
Mom-0.017
 sticker-0.016
 cookie-0.016
 icing-0.016
Token was
Token ID373
Feature activation-1.22e+00

Pos logit contributions
Mom+0.028
 half+0.027
 sticker+0.026
 cookie+0.025
 ribbon+0.024
Neg logit contributions
 vill-0.039
 current-0.038
vious-0.037
 challenged-0.037
 fishermen-0.036
Token very
Token ID845
Feature activation-7.49e-01

Pos logit contributions
 vill+0.048
 challenged+0.047
 ot+0.046
 current+0.046
vious+0.046
Neg logit contributions
Mom-0.036
 half-0.035
 sticker-0.034
 icing-0.032
 ribbon-0.032
Token small
Token ID1402
Feature activation+2.80e-01

Pos logit contributions
 vill+0.026
 challenged+0.025
 current+0.025
 ot+0.025
vious+0.025
Neg logit contributions
Mom-0.025
 half-0.025
 sticker-0.024
 cookie-0.023
 icing-0.023
Token over
Token ID625
Feature activation+7.74e-01

Pos logit contributions
 vill+0.107
 challenged+0.103
vious+0.100
 ot+0.100
 current+0.099
Neg logit contributions
 half-0.112
 sticker-0.112
Mom-0.111
 icing-0.109
 wrist-0.107
Token to
Token ID284
Feature activation-1.46e+00

Pos logit contributions
Mom+0.026
 sticker+0.025
 half+0.024
ushes+0.024
 scalp+0.024
Neg logit contributions
 vill-0.027
 challenged-0.025
 ot-0.024
 padd-0.024
 current-0.024
Token take
Token ID1011
Feature activation-8.77e-01

Pos logit contributions
 vill+0.060
 challenged+0.058
 ot+0.057
 current+0.057
vious+0.056
Neg logit contributions
Mom-0.040
 half-0.039
 sticker-0.038
ushes-0.037
 cookie-0.037
Token a
Token ID257
Feature activation+7.63e-01

Pos logit contributions
 vill+0.030
 challenged+0.027
vious+0.027
 ot+0.027
 padd+0.026
Neg logit contributions
Mom-0.031
 wrist-0.029
ushes-0.028
Anna-0.027
 half-0.027
Token closer
Token ID5699
Feature activation+3.42e-01

Pos logit contributions
Mom+0.028
 half+0.027
 sticker+0.025
 icing+0.025
ushes+0.025
Neg logit contributions
 vill-0.025
 challenged-0.024
 ot-0.024
vious-0.023
 current-0.023
Token look
Token ID804
Feature activation-2.49e+00

Pos logit contributions
 half+0.010
 sticker+0.010
Mom+0.010
 ribbon+0.009
 cookie+0.009
Neg logit contributions
 vill-0.014
 challenged-0.013
 current-0.013
vious-0.013
 ot-0.013
Token.
Token ID13
Feature activation-3.17e-01

Pos logit contributions
 vill+0.118
 current+0.114
 challenged+0.114
 ot+0.112
vious+0.112
Neg logit contributions
 half-0.054
Mom-0.053
 sticker-0.050
 icing-0.046
 cookie-0.046
Token But
Token ID887
Feature activation-1.94e+00

Pos logit contributions
 vill+0.011
 challenged+0.011
 current+0.010
 ot+0.010
vious+0.010
Neg logit contributions
 half-0.011
 sticker-0.010
Mom-0.010
 icing-0.010
 ribbon-0.010
Token when
Token ID618
Feature activation-1.50e-01

Pos logit contributions
 vill+0.073
 challenged+0.071
 current+0.070
 ot+0.070
vious+0.068
Neg logit contributions
Mom-0.059
 half-0.058
 sticker-0.057
 icing-0.054
 cookie-0.054
Token Molly
Token ID30236
Feature activation+8.37e-01

Pos logit contributions
 vill+0.006
 current+0.006
 challenged+0.006
 ot+0.006
vious+0.005
Neg logit contributions
Mom-0.004
 half-0.004
 sticker-0.004
ushes-0.004
 icing-0.004
Token got
Token ID1392
Feature activation-8.04e-01

Pos logit contributions
 half+0.032
Mom+0.032
 sticker+0.030
 ribbon+0.030
 cookie+0.030
Neg logit contributions
 vill-0.025
 current-0.024
 ot-0.024
vious-0.024
 challenged-0.023
Token Bob
Token ID5811
Feature activation-4.51e-01

Pos logit contributions
 vill+0.010
 challenged+0.009
 current+0.009
 ot+0.009
vious+0.009
Neg logit contributions
 half-0.013
 sticker-0.013
Mom-0.013
 ribbon-0.012
 icing-0.012
Token was
Token ID373
Feature activation-1.30e+00

Pos logit contributions
 vill+0.014
 challenged+0.014
 ot+0.013
 current+0.013
vious+0.013
Neg logit contributions
Mom-0.016
 half-0.016
 sticker-0.016
 icing-0.015
ushes-0.015
Token so
Token ID523
Feature activation-3.26e+00

Pos logit contributions
 vill+0.036
 challenged+0.034
 current+0.034
vious+0.033
 ot+0.033
Neg logit contributions
Mom-0.053
 half-0.053
 sticker-0.052
 cookie-0.050
 ribbon-0.050
Token happy
Token ID3772
Feature activation+1.71e+00

Pos logit contributions
 vill+0.112
 challenged+0.107
 current+0.105
vious+0.105
 ot+0.105
Neg logit contributions
Mom-0.113
 half-0.112
 sticker-0.108
 ribbon-0.104
 icing-0.104
Token and
Token ID290
Feature activation+3.27e-01

Pos logit contributions
Mom+0.052
 half+0.052
 sticker+0.049
 cookie+0.047
 icing+0.047
Neg logit contributions
 vill-0.066
 challenged-0.063
 current-0.063
 ot-0.063
vious-0.062
Token he
Token ID339
Feature activation-2.54e+00

Pos logit contributions
Mom+0.013
 half+0.013
 sticker+0.012
 cookie+0.012
 icing+0.012
Neg logit contributions
 vill-0.010
 challenged-0.009
 current-0.009
vious-0.009
 ot-0.009
Token smiled
Token ID13541
Feature activation+1.31e+00

Pos logit contributions
 vill+0.079
 challenged+0.076
 current+0.075
 ot+0.074
vious+0.074
Neg logit contributions
Mom-0.096
 half-0.095
 sticker-0.092
 cookie-0.088
 icing-0.088
Token for
Token ID329
Feature activation+5.58e-01

Pos logit contributions
Mom+0.036
 half+0.036
 sticker+0.034
 icing+0.033
 cookie+0.033
Neg logit contributions
 vill-0.054
 challenged-0.052
 current-0.052
 ot-0.051
vious-0.051
Token the
Token ID262
Feature activation-2.01e+00

Pos logit contributions
Mom+0.021
ushes+0.020
 half+0.019
 sticker+0.019
 icing+0.019
Neg logit contributions
 vill-0.018
 challenged-0.017
 ot-0.017
 current-0.017
 padd-0.016
Token first
Token ID717
Feature activation-5.25e-01

Pos logit contributions
 vill+0.079
 ot+0.073
 current+0.072
vious+0.071
 challenged+0.071
Neg logit contributions
Mom-0.062
ushes-0.058
 half-0.057
 sticker-0.054
 wrist-0.054
Token time
Token ID640
Feature activation+6.01e-01

Pos logit contributions
 vill+0.020
 challenged+0.019
 current+0.019
vious+0.018
 ot+0.018
Neg logit contributions
Mom-0.016
ushes-0.015
 half-0.015
 sticker-0.014
 icing-0.014
Token
Token ID198
Feature activation-4.10e-01

Pos logit contributions
 vill+0.021
 challenged+0.020
 current+0.020
 ot+0.020
vious+0.020
Neg logit contributions
Mom-0.010
 half-0.010
 sticker-0.010
 cookie-0.009
 icing-0.009
TokenThe
Token ID464
Feature activation-7.32e-01

Pos logit contributions
 vill+0.019
 current+0.018
vious+0.018
 ot+0.018
 challenged+0.018
Neg logit contributions
Mom-0.010
 half-0.009
 sticker-0.008
 ribbon-0.008
 cookie-0.008
Token old
Token ID1468
Feature activation-2.00e+00

Pos logit contributions
vious+0.023
 challenged+0.023
 vill+0.022
ules+0.022
 bust+0.022
Neg logit contributions
 half-0.026
Mom-0.026
 sticker-0.025
 cookie-0.024
 ribbon-0.023
Token man
Token ID582
Feature activation-4.98e+00

Pos logit contributions
vious+0.075
 bust+0.069
rified+0.067
 challenged+0.066
lves+0.066
Neg logit contributions
Mom-0.062
 half-0.062
 sticker-0.061
 cookie-0.056
 card-0.056
Token was
Token ID373
Feature activation-1.61e+00

Pos logit contributions
 vill+0.183
 current+0.181
vious+0.178
 ot+0.175
 challenged+0.169
Neg logit contributions
 half-0.163
Mom-0.157
 sticker-0.145
 cookie-0.138
 ribbon-0.137
Token disappointed
Token ID11679
Feature activation-4.27e+00

Pos logit contributions
 vill+0.056
 current+0.054
 ot+0.054
vious+0.053
 challenged+0.052
Neg logit contributions
 half-0.056
Mom-0.055
 sticker-0.052
 cookie-0.049
 herself-0.048
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
 vill+0.183
vious+0.178
 challenged+0.177
 current+0.175
 ot+0.174
Neg logit contributions
 half-0.110
Mom-0.108
 sticker-0.101
 cookie-0.094
 herself-0.094
Token he
Token ID339
Feature activation-2.84e+00

Pos logit contributions
vious+0.036
 vill+0.035
 ot+0.033
enced+0.033
 current+0.033
Neg logit contributions
Mom-0.034
 half-0.034
 herself-0.031
 sticker-0.031
 ribbon-0.030
Token had
Token ID550
Feature activation+2.57e+00

Pos logit contributions
 vill+0.095
 current+0.092
vious+0.091
 ot+0.091
 ships+0.086
Neg logit contributions
Mom-0.099
 half-0.098
 sticker-0.093
 ribbon-0.090
 cookie-0.087
Token hoped
Token ID10719
Feature activation-4.41e+00

Pos logit contributions
 half+0.076
Mom+0.068
 sticker+0.065
 cookie+0.060
 icing+0.060
Neg logit contributions
 vill-0.106
 ot-0.104
 current-0.103
vious-0.101
 bust-0.098
Token to
Token ID284
Feature activation-1.69e+00

Pos logit contributions
 vill+0.174
vious+0.172
 challenged+0.171
 current+0.169
 ot+0.168
Neg logit contributions
 half-0.127
Mom-0.122
 sticker-0.122
 cookie-0.112
 ribbon-0.109
Token and
Token ID290
Feature activation-4.72e-02

Pos logit contributions
Mom+0.005
 half+0.005
 sticker+0.005
Anna+0.005
ushes+0.005
Neg logit contributions
 vill-0.005
 ot-0.005
 current-0.005
 challenged-0.005
 padd-0.005
Token walked
Token ID6807
Feature activation-5.45e+00

Pos logit contributions
 vill+0.002
 challenged+0.001
 current+0.001
 ot+0.001
vious+0.001
Neg logit contributions
Mom-0.002
 half-0.002
 sticker-0.002
 icing-0.002
 cookie-0.002
Token back
Token ID736
Feature activation+1.82e+00

Pos logit contributions
 vill+0.196
 challenged+0.190
 current+0.187
 ot+0.185
vious+0.182
Neg logit contributions
 half-0.177
Mom-0.175
 sticker-0.174
 cookie-0.169
 icing-0.168
Token home
Token ID1363
Feature activation+5.34e-01

Pos logit contributions
Mom+0.055
 half+0.053
 sticker+0.051
 icing+0.050
 cookie+0.049
Neg logit contributions
 vill-0.071
 challenged-0.069
 current-0.067
 ot-0.067
vious-0.066
Token to
Token ID284
Feature activation-1.58e+00

Pos logit contributions
Mom+0.013
 half+0.012
 sticker+0.012
 icing+0.011
 ribbon+0.011
Neg logit contributions
 vill-0.024
 challenged-0.023
 current-0.023
 ot-0.023
vious-0.022
Token show
Token ID905
Feature activation-2.91e+00

Pos logit contributions
 vill+0.057
 challenged+0.055
 ot+0.054
 current+0.054
vious+0.052
Neg logit contributions
Mom-0.053
 half-0.051
 sticker-0.049
ushes-0.048
 icing-0.048
Token it
Token ID340
Feature activation+4.13e-01

Pos logit contributions
 vill+0.100
 challenged+0.096
 ot+0.094
 current+0.093
vious+0.092
Neg logit contributions
Mom-0.101
 half-0.097
 sticker-0.094
 icing-0.092
 cookie-0.091
Token to
Token ID284
Feature activation-1.54e+00

Pos logit contributions
Mom+0.012
 half+0.012
 sticker+0.011
 icing+0.011
 cookie+0.011
Neg logit contributions
 vill-0.016
 challenged-0.016
 current-0.016
 ot-0.016
vious-0.016
Token his
Token ID465
Feature activation+8.94e-01

Pos logit contributions
 vill+0.052
 challenged+0.049
 ot+0.049
 current+0.049
vious+0.047
Neg logit contributions
Mom-0.055
 half-0.054
 sticker-0.052
 icing-0.050
 cookie-0.050
Token mom
Token ID1995
Feature activation+2.10e+00

Pos logit contributions
Mom+0.025
 half+0.024
 icing+0.023
 sticker+0.023
ushes+0.023
Neg logit contributions
 vill-0.036
 ot-0.036
 current-0.034
 challenged-0.033
 padd-0.033
Tokenmy
Token ID1820
Feature activation+2.85e+00

Pos logit contributions
Mom+0.052
 half+0.051
 sticker+0.049
 ribbon+0.046
 icing+0.046
Neg logit contributions
 vill-0.092
 challenged-0.089
 ot-0.088
vious-0.088
 current-0.087
Token he
Token ID339
Feature activation-2.87e+00

Pos logit contributions
Mom+0.134
 half+0.133
 sticker+0.128
 cookie+0.124
 ribbon+0.122
Neg logit contributions
 vill-0.103
vious-0.097
 challenged-0.097
 ot-0.096
 current-0.096
Token got
Token ID1392
Feature activation-7.68e-01

Pos logit contributions
itive+0.105
 current+0.100
 ships+0.098
vious+0.097
 ot+0.097
Neg logit contributions
 half-0.099
Mom-0.094
 sticker-0.085
Anna-0.081
 cookie-0.080
Token to
Token ID284
Feature activation-1.67e+00

Pos logit contributions
 vill+0.033
 ot+0.031
vious+0.031
 current+0.031
 challenged+0.031
Neg logit contributions
Mom-0.021
 half-0.021
 sticker-0.019
 cookie-0.017
ushes-0.017
Token the
Token ID262
Feature activation-2.27e+00

Pos logit contributions
vious+0.082
 vill+0.079
 challenged+0.077
ules+0.076
enced+0.076
Neg logit contributions
 half-0.038
 sticker-0.034
Mom-0.033
 herself-0.031
 ribbon-0.030
Token river
Token ID7850
Feature activation-3.93e+00

Pos logit contributions
ules+0.082
itive+0.080
vious+0.077
oke+0.075
 challenged+0.074
Neg logit contributions
Mom-0.079
 half-0.076
 sticker-0.068
 tape-0.062
 ourselves-0.062
Tokenbank
Token ID17796
Feature activation-9.80e+00

Pos logit contributions
vious+0.212
itive+0.204
 vill+0.200
lves+0.198
 ranc+0.195
Neg logit contributions
 half-0.065
 sticker-0.043
 herself-0.043
Mom-0.040
 with-0.039
Token he
Token ID339
Feature activation-2.91e+00

Pos logit contributions
vious+0.526
 vill+0.523
 ranc+0.507
 bust+0.504
ican+0.502
Neg logit contributions
 half-0.137
 herself-0.123
Mom-0.096
 with-0.082
 ourselves-0.081
Token was
Token ID373
Feature activation-1.51e+00

Pos logit contributions
itive+0.107
 vill+0.100
vious+0.099
 current+0.096
 obstacle+0.095
Neg logit contributions
 half-0.095
Mom-0.088
 sticker-0.085
 tape-0.079
 ribbon-0.077
Token very
Token ID845
Feature activation-9.66e-01

Pos logit contributions
 vill+0.056
vious+0.051
 ot+0.051
 current+0.051
 challenged+0.048
Neg logit contributions
 half-0.053
Mom-0.051
 sticker-0.049
 cookie-0.046
 icing-0.046
Token amazed
Token ID24562
Feature activation-4.26e+00

Pos logit contributions
 vill+0.038
vious+0.037
ican+0.036
rified+0.034
 challenged+0.034
Neg logit contributions
Mom-0.031
 half-0.029
ushes-0.027
 sticker-0.026
 herself-0.023
Token.
Token ID13
Feature activation-6.71e-01

Pos logit contributions
 vill+0.213
 current+0.209
 bust+0.205
 ranc+0.204
 challenged+0.201
Neg logit contributions
 half-0.079
Mom-0.073
 sticker-0.062
 herself-0.061
 ribbon-0.061
Token.
Token ID13
Feature activation-3.15e-01

Pos logit contributions
 vill+0.121
 challenged+0.116
 ot+0.114
 current+0.112
vious+0.112
Neg logit contributions
Mom-0.085
 half-0.079
 sticker-0.076
 icing-0.073
ushes-0.071
Token They
Token ID1119
Feature activation-1.16e+00

Pos logit contributions
 vill+0.012
 challenged+0.012
 current+0.011
 bust+0.011
 ot+0.011
Neg logit contributions
 half-0.009
 sticker-0.009
Mom-0.009
 icing-0.009
 ribbon-0.009
Token were
Token ID547
Feature activation+2.01e-01

Pos logit contributions
 vill+0.038
 challenged+0.037
 current+0.036
 ot+0.036
vious+0.036
Neg logit contributions
Mom-0.041
 half-0.041
 sticker-0.040
 cookie-0.038
 icing-0.038
Token no
Token ID645
Feature activation-1.11e-01

Pos logit contributions
Mom+0.007
 half+0.007
 sticker+0.007
 ribbon+0.006
 cookie+0.006
Neg logit contributions
 vill-0.007
 challenged-0.007
 ot-0.007
vious-0.007
 current-0.007
Token longer
Token ID2392
Feature activation+2.71e-01

Pos logit contributions
 vill+0.004
 challenged+0.004
 current+0.004
 ot+0.004
vious+0.004
Neg logit contributions
 half-0.003
Mom-0.003
 sticker-0.003
 icing-0.003
 cookie-0.003
Token en
Token ID551
Feature activation-8.20e+00

Pos logit contributions
 half+0.011
 sticker+0.011
 icing+0.010
 cookie+0.010
Mom+0.010
Neg logit contributions
 vill-0.007
ican-0.007
 current-0.007
cient-0.007
roads-0.007
Tokenvious
Token ID1442
Feature activation-3.28e+00

Pos logit contributions
 current+0.123
 ranc+0.113
 ships+0.102
 ot+0.102
 padd+0.101
Neg logit contributions
 half-0.452
Mom-0.419
 sticker-0.415
 cookie-0.409
ushes-0.409
Token of
Token ID286
Feature activation+1.64e+00

Pos logit contributions
 vill+0.143
 current+0.137
 challenged+0.137
 bust+0.133
vious+0.132
Neg logit contributions
 half-0.084
Mom-0.078
 sticker-0.076
 cookie-0.073
 icing-0.072
Token each
Token ID1123
Feature activation-3.35e+00

Pos logit contributions
Mom+0.052
 half+0.049
 sticker+0.048
 cookie+0.045
 icing+0.045
Neg logit contributions
 vill-0.063
 ot-0.059
 challenged-0.059
 current-0.058
 ships-0.057
Token other
Token ID584
Feature activation+2.00e+00

Pos logit contributions
 vill+0.139
 challenged+0.134
 current+0.133
 ot+0.132
vious+0.132
Neg logit contributions
Mom-0.092
 half-0.092
 sticker-0.087
 cookie-0.082
 icing-0.082
Token,
Token ID11
Feature activation-6.19e-01

Pos logit contributions
Mom+0.056
 half+0.054
 sticker+0.052
 icing+0.049
 cookie+0.048
Neg logit contributions
 vill-0.083
 challenged-0.080
 ot-0.079
 current-0.079
vious-0.078
Token
Token ID198
Feature activation+5.58e-02

Pos logit contributions
 half+0.002
Mom+0.002
 sticker+0.002
 icing+0.002
 ribbon+0.002
Neg logit contributions
 vill-0.004
 challenged-0.003
 current-0.003
 ot-0.003
vious-0.003
TokenStanding
Token ID44196
Feature activation-1.75e+00

Pos logit contributions
Mom+0.001
 half+0.001
 sticker+0.001
 cookie+0.001
 ribbon+0.001
Neg logit contributions
 vill-0.003
 current-0.002
 ot-0.002
 challenged-0.002
vious-0.002
Token on
Token ID319
Feature activation+2.06e+00

Pos logit contributions
 vill+0.074
 challenged+0.071
 current+0.070
vious+0.070
 ot+0.070
Neg logit contributions
Mom-0.049
 half-0.047
 sticker-0.045
 icing-0.042
 ribbon-0.042
Token the
Token ID262
Feature activation-2.12e+00

Pos logit contributions
 half+0.053
Mom+0.051
 sticker+0.048
 cookie+0.045
 ribbon+0.045
Neg logit contributions
vious-0.090
 vill-0.090
 challenged-0.089
 ot-0.087
 current-0.087
Token river
Token ID7850
Feature activation-3.85e+00

Pos logit contributions
vious+0.069
ules+0.067
 vill+0.066
 challenged+0.065
itive+0.063
Neg logit contributions
 half-0.075
Mom-0.071
 sticker-0.071
 cookie-0.067
 card-0.067
Tokenbank
Token ID17796
Feature activation-9.78e+00

Pos logit contributions
vious+0.160
 vill+0.153
lves+0.150
 ranc+0.149
itive+0.148
Neg logit contributions
 half-0.108
Mom-0.093
 sticker-0.089
 cookie-0.082
 card-0.082
Token was
Token ID373
Feature activation-1.40e+00

Pos logit contributions
 vill+0.439
 ranc+0.430
vious+0.428
 current+0.422
lves+0.418
Neg logit contributions
 half-0.228
Mom-0.190
 herself-0.184
 sticker-0.173
 icing-0.156
Token a
Token ID257
Feature activation+6.12e-01

Pos logit contributions
 vill+0.054
 challenged+0.052
 current+0.051
 ot+0.051
vious+0.051
Neg logit contributions
 half-0.043
Mom-0.043
 sticker-0.041
 cookie-0.039
 icing-0.039
Token duck
Token ID22045
Feature activation-4.04e+00

Pos logit contributions
Mom+0.022
 half+0.022
 sticker+0.022
 cookie+0.021
 ribbon+0.021
Neg logit contributions
 vill-0.020
 challenged-0.019
vious-0.019
 current-0.018
 ot-0.018
Token.
Token ID13
Feature activation-6.00e-01

Pos logit contributions
 vill+0.169
vious+0.163
 current+0.161
 challenged+0.160
 bust+0.156
Neg logit contributions
 half-0.110
Mom-0.107
 sticker-0.102
 cookie-0.098
 ribbon-0.095
Token The
Token ID383
Feature activation-1.31e+00

Pos logit contributions
 vill+0.025
vious+0.024
itive+0.024
 challenged+0.024
roads+0.023
Neg logit contributions
 half-0.015
Mom-0.015
 cookie-0.014
 sticker-0.014
 icing-0.014
Token,
Token ID11
Feature activation-2.86e-01

Pos logit contributions
 vill+0.095
 challenged+0.095
 ot+0.092
vious+0.091
 current+0.090
Neg logit contributions
Mom-0.067
 half-0.067
 sticker-0.065
 icing-0.063
 ribbon-0.061
Token but
Token ID475
Feature activation-3.11e+00

Pos logit contributions
 vill+0.011
 current+0.011
vious+0.011
 challenged+0.010
 bust+0.010
Neg logit contributions
 half-0.009
Mom-0.008
 sticker-0.008
 cookie-0.008
 ribbon-0.008
Token the
Token ID262
Feature activation-1.69e+00

Pos logit contributions
 vill+0.127
vious+0.124
 current+0.120
 challenged+0.120
 ot+0.116
Neg logit contributions
 half-0.089
Mom-0.089
 sticker-0.082
 cookie-0.079
 ribbon-0.076
Token turtle
Token ID28699
Feature activation-5.92e+00

Pos logit contributions
vious+0.048
 vill+0.048
 challenged+0.047
 current+0.046
 bust+0.045
Neg logit contributions
Mom-0.066
 half-0.065
 sticker-0.062
 cookie-0.061
 ribbon-0.060
Token was
Token ID373
Feature activation-9.75e-01

Pos logit contributions
 vill+0.217
 current+0.217
vious+0.202
 bust+0.199
 ot+0.196
Neg logit contributions
 half-0.184
Mom-0.180
 sticker-0.176
 cookie-0.170
 ribbon-0.163
Token en
Token ID551
Feature activation-8.09e+00

Pos logit contributions
 vill+0.043
 current+0.041
vious+0.041
 ot+0.040
 challenged+0.039
Neg logit contributions
 half-0.026
 sticker-0.024
Mom-0.024
 cookie-0.023
Anna-0.020
Tokenvious
Token ID1442
Feature activation-3.20e+00

Pos logit contributions
 current+0.107
 vill+0.093
 ot+0.087
 padd+0.085
 ships+0.084
Neg logit contributions
 half-0.456
Mom-0.444
 sticker-0.434
Anna-0.425
ushes-0.425
Token of
Token ID286
Feature activation+2.01e+00

Pos logit contributions
 vill+0.165
 current+0.161
 bust+0.159
 challenged+0.158
 ot+0.154
Neg logit contributions
 half-0.058
Mom-0.054
 sticker-0.051
 cookie-0.048
 ribbon-0.042
Token the
Token ID262
Feature activation-1.75e+00

Pos logit contributions
Mom+0.059
 half+0.058
 sticker+0.056
 icing+0.053
 cookie+0.053
Neg logit contributions
 vill-0.080
 challenged-0.077
 current-0.076
 ot-0.076
vious-0.075
Token rabbit
Token ID22746
Feature activation-4.22e+00

Pos logit contributions
 vill+0.055
 challenged+0.052
vious+0.052
 current+0.052
 bust+0.051
Neg logit contributions
 half-0.064
Mom-0.063
 sticker-0.061
 cookie-0.060
 ribbon-0.059
Token's
Token ID338
Feature activation+1.90e+00

Pos logit contributions
 vill+0.187
 challenged+0.181
 ot+0.180
 current+0.179
vious+0.178
Neg logit contributions
Mom-0.105
 half-0.101
 sticker-0.096
 icing-0.091
 ribbon-0.089
Token pond
Token ID16723
Feature activation-1.92e+00

Pos logit contributions
 vill+0.064
 challenged+0.062
vious+0.060
 current+0.059
 ot+0.058
Neg logit contributions
 half-0.083
Mom-0.082
 sticker-0.078
 cookie-0.077
 ribbon-0.075
Token.
Token ID13
Feature activation-2.80e-01

Pos logit contributions
 vill+0.091
 challenged+0.088
 current+0.087
 ot+0.087
vious+0.087
Neg logit contributions
 half-0.041
Mom-0.041
 sticker-0.039
 cookie-0.036
 icing-0.036
Token It
Token ID632
Feature activation+6.95e-01

Pos logit contributions
vious+0.011
itive+0.011
 vill+0.011
 challenged+0.011
roads+0.011
Neg logit contributions
 half-0.007
 cookie-0.007
Mom-0.007
 sticker-0.007
 icing-0.006
Token was
Token ID373
Feature activation-1.25e+00

Pos logit contributions
 half+0.016
Mom+0.016
 ribbon+0.013
 sticker+0.012
 cookie+0.012
Neg logit contributions
vious-0.033
 vill-0.033
ules-0.031
 fishermen-0.031
 current-0.031
Token a
Token ID257
Feature activation+7.78e-01

Pos logit contributions
 vill+0.051
 current+0.050
 ot+0.050
 challenged+0.049
vious+0.048
Neg logit contributions
Mom-0.034
 half-0.033
 sticker-0.032
 wrist-0.031
 icing-0.031
Token tort
Token ID7619
Feature activation-8.35e+00

Pos logit contributions
Mom+0.028
 half+0.027
ushes+0.026
 icing+0.026
 sticker+0.026
Neg logit contributions
 vill-0.026
 ot-0.025
 current-0.025
 challenged-0.024
 padd-0.022
Tokenoise
Token ID25678
Feature activation-5.00e+00

Pos logit contributions
 vill+0.173
 current+0.173
 ot+0.159
 challenged+0.157
vious+0.150
Neg logit contributions
 half-0.403
Mom-0.402
 sticker-0.371
 wrist-0.366
 ribbon-0.360
Token!
Token ID0
Feature activation-1.59e+00

Pos logit contributions
 vill+0.203
 challenged+0.195
 current+0.194
vious+0.193
 ot+0.193
Neg logit contributions
 half-0.140
Mom-0.140
 sticker-0.133
 cookie-0.126
 icing-0.125
Token The
Token ID383
Feature activation-1.20e+00

Pos logit contributions
itive+0.068
rated+0.068
vious+0.066
 vill+0.065
 current+0.065
Neg logit contributions
 half-0.038
Mom-0.036
 cookie-0.036
 sticker-0.033
 tape-0.032
Token all
Token ID477
Feature activation-4.39e+00

Pos logit contributions
ules+0.038
enced+0.038
vious+0.037
 vill+0.036
 challenged+0.036
Neg logit contributions
 half-0.043
Mom-0.042
 cookie-0.041
 ribbon-0.037
 cookies-0.037
Tokenigator
Token ID23823
Feature activation-3.51e+00

Pos logit contributions
 ranc+0.120
 Pole+0.120
 harbor+0.116
 fishermen+0.116
 current+0.114
Neg logit contributions
 half-0.171
 her-0.153
Mom-0.151
 cookie-0.147
 herself-0.147