TOP ACTIVATIONS
MAX = 11.439

little girl named Lucy found a big box in her room
a girl named Sue found a broken scarf . She wanted
little boy named Tim found a big , heavy rock in
a boy named Tim found a toy motorcycle . It was
little girl named Lucy found a big book called a dictionary
a boy named Tim found a toy . The toy was
a boy named Tim found a cr ay on box .
little rabbit named Tim found a shiny trophy in the forest
a girl named Lily found a box of shiny jewelry .
little boy named Tim found a magic f auc et in
a boy named Tim found a heavy box . He wanted
an attractive crib in a nursery . Everyday a little girl
little girl named Lucy found a big scale in her house
a boy named Tim found a big hammer in his toy
, a little girl found a special sp ade . It
little girl named Lucy found a colorful bird c age in
a girl named Lily found a warm muff in on the
small boy named Tim found a penny . This penny was
a boy named Tim found a microphone in his toy box
little girl named Amy found a big box . Inside the

MIN ACTIVATIONS
MIN = -17.050

and laughed and ate ch ocol ates . They had a
bled up all the ch ocol ates , and she was
't have all these ch ocol ates ! Now , go
he ate all the ch ocol ates and sweets . Then
giving him too many ch ocol ates ." The king learned
as he opened the ch ocol ates and started eating them
not eat too many ch ocol ates and his friend learned
we can get more ch ocol ates later . For now
L ily , these ch ocol ates are bitter ," he
was filled with delicious ch ocol ates . He was happy
saw all the tasty ch ocol ates inside . She couldn
box and share the ch ocol ates . They are happy
and they shared the ch ocol ates with everyone in the
reward . It was ch ocol ates and sweets !
temper and often threw temper tant rums . One day ,
she paid for the ch ocol ates and the two of
son is eating our ch ocol ates !"
started eating the delicious ch ocol ates . She was so
ates . Lily loved ch ocol ates . She thanked Ben
and started eating the ch ocol ates . The shop keeper

INTERVAL 4.317 - 11.439
CONTAINS 6.206%

wear her new jacket to school . It was pink and
. <|endoftext|> One day , a sm elly cat named Tom
. He was a very charming triangle , and he loved
the key and it made a ' click ' sound .
playing , he saw a silly crab near the sand .

INTERVAL -2.805 - 4.317
CONTAINS 77.527%

either . Lily decided to touch it to see what it
. <|endoftext|> Once upon a time there was a hungry girl
them . It was so happy that it started to sing
Yes , please . Milk makes cereal y ummy ," Lily
it pop in the big pot . They also like to

INTERVAL -9.928 - -2.805
CONTAINS 16.226%

herself . She was excited to show the stranger what she
L ily feels better . She says , "
. They took the equipment to a nearby fountain
They will listen to each other . They will be safe
, but be careful and don 't get too close to

INTERVAL -17.050 - -9.928
CONTAINS 0.041%

perfect . Pe ggy was so very happy
Go away !" L ily and Max felt sad
. She says , " S ara and Tom , what
. Now !" L ily and Ben are ashamed
whim pered . L ily 's mom and dad
Token little
Token ID1310
Feature activation+8.08e+00

Pos logit contributions
 barrel+0.087
 Bun+0.081
 hut+0.074
 shield+0.073
 he+0.071
Neg logit contributions
ases-0.338
olds-0.319
cks-0.317
els-0.314
oke-0.307
Token girl
Token ID2576
Feature activation+4.00e+00

Pos logit contributions
 Bun+0.068
 he+0.065
 barrel+0.065
 accidentally+0.063
 shield+0.061
Neg logit contributions
ases-0.280
els-0.263
olds-0.256
ips-0.251
cks-0.244
Token named
Token ID3706
Feature activation+2.33e+00

Pos logit contributions
 barrel+0.029
 dark+0.028
 puppy+0.028
 bunny+0.028
 Bun+0.027
Neg logit contributions
ases-0.152
olds-0.145
els-0.143
cks-0.140
ips-0.138
Token Lucy
Token ID22162
Feature activation-3.09e-01

Pos logit contributions
 barrel+0.037
 shield+0.036
 puppy+0.036
 he+0.035
 cabin+0.035
Neg logit contributions
ases-0.068
olds-0.064
els-0.063
cks-0.061
ips-0.059
Token found
Token ID1043
Feature activation+3.67e+00

Pos logit contributions
ases+0.012
olds+0.011
els+0.011
cks+0.011
ips+0.011
Neg logit contributions
 barrel-0.002
 Bun-0.002
 bunny-0.002
 puppy-0.002
 hut-0.002
Token a
Token ID257
Feature activation+1.14e+01

Pos logit contributions
 barrel+0.025
 hut+0.023
 bicycle+0.022
 cabin+0.022
 puppy+0.022
Neg logit contributions
ases-0.140
els-0.132
olds-0.132
cks-0.128
ips-0.126
Token big
Token ID1263
Feature activation+6.97e+00

Pos logit contributions
 Bun+0.148
 decided+0.145
 While+0.144
 he+0.138
 Lots+0.129
Neg logit contributions
els-0.251
olds-0.246
ric-0.238
its-0.237
ocol-0.231
Token box
Token ID3091
Feature activation+6.18e+00

Pos logit contributions
 Bun+0.091
 he+0.083
Under+0.079
 decided+0.077
 Curious+0.074
Neg logit contributions
els-0.200
ases-0.195
olds-0.182
ocol-0.179
cks-0.175
Token in
Token ID287
Feature activation+3.26e+00

Pos logit contributions
 Bun+0.096
 barrel+0.093
 wolf+0.092
 puppy+0.092
 hunter+0.090
Neg logit contributions
ases-0.177
els-0.170
olds-0.167
cks-0.164
ips-0.159
Token her
Token ID607
Feature activation+4.52e+00

Pos logit contributions
 dark+0.051
 he+0.049
 there+0.049
 hut+0.049
 puppy+0.049
Neg logit contributions
ases-0.101
olds-0.093
els-0.091
ips-0.090
cks-0.088
Token room
Token ID2119
Feature activation+8.49e+00

Pos logit contributions
 Bun+0.047
 barrel+0.047
 he+0.046
 bunny+0.045
 wolf+0.044
Neg logit contributions
ases-0.148
els-0.141
olds-0.141
cks-0.136
ips-0.134
Token a
Token ID257
Feature activation+1.01e+01

Pos logit contributions
 superhero+0.044
 shield+0.044
 cabin+0.043
 vest+0.042
 wolf+0.042
Neg logit contributions
ases-0.122
cks-0.114
olds-0.111
els-0.109
its-0.105
Token girl
Token ID2576
Feature activation+4.76e+00

Pos logit contributions
 Bun+0.101
 barrel+0.099
 hut+0.092
 cabin+0.090
 shield+0.087
Neg logit contributions
ases-0.284
olds-0.272
oke-0.270
ila-0.252
els-0.252
Token named
Token ID3706
Feature activation+3.43e+00

Pos logit contributions
 barrel+0.047
 Bun+0.044
 hut+0.044
 bunny+0.044
 puppy+0.044
Neg logit contributions
ases-0.169
olds-0.159
els-0.158
cks-0.153
ips-0.150
Token Sue
Token ID26089
Feature activation+4.53e-01

Pos logit contributions
 barrel+0.056
 shield+0.054
 cabin+0.054
 hut+0.054
 puppy+0.053
Neg logit contributions
ases-0.099
olds-0.094
els-0.090
cks-0.088
ips-0.085
Token found
Token ID1043
Feature activation+3.56e+00

Pos logit contributions
 barrel+0.004
 Bun+0.004
 puppy+0.004
 bunny+0.004
 hut+0.004
Neg logit contributions
ases-0.017
olds-0.016
els-0.016
cks-0.015
ips-0.015
Token a
Token ID257
Feature activation+1.13e+01

Pos logit contributions
 barrel+0.025
 cabin+0.023
 hut+0.023
 bicycle+0.022
 Bun+0.021
Neg logit contributions
ases-0.137
olds-0.130
els-0.128
cks-0.125
ips-0.123
Token broken
Token ID5445
Feature activation+7.44e+00

Pos logit contributions
 Bun+0.155
 decided+0.146
 he+0.143
 While+0.143
 He+0.132
Neg logit contributions
olds-0.241
els-0.235
its-0.231
ases-0.224
 mistake-0.223
Token scarf
Token ID36953
Feature activation+5.39e+00

Pos logit contributions
 Curious+0.095
Under+0.095
 he+0.091
 While+0.090
 Bun+0.090
Neg logit contributions
els-0.193
ases-0.182
olds-0.171
ings-0.169
its-0.166
Token.
Token ID13
Feature activation+4.75e+00

Pos logit contributions
 barrel+0.088
 cabin+0.086
 hut+0.084
 cozy+0.083
 hunter+0.083
Neg logit contributions
ases-0.141
els-0.132
cks-0.129
olds-0.128
ips-0.128
Token She
Token ID1375
Feature activation+4.90e+00

Pos logit contributions
 barrel+0.057
 dark+0.056
 hut+0.055
 bunny+0.055
 he+0.054
Neg logit contributions
ases-0.158
els-0.149
olds-0.148
cks-0.145
irs-0.143
Token wanted
Token ID2227
Feature activation+4.85e+00

Pos logit contributions
 barrel+0.061
 hut+0.059
 cabin+0.056
 puppy+0.054
 wolf+0.053
Neg logit contributions
ases-0.156
els-0.156
olds-0.152
cks-0.146
its-0.145
Token little
Token ID1310
Feature activation+8.20e+00

Pos logit contributions
 barrel+0.100
 Bun+0.095
 hut+0.090
 cabin+0.087
 decided+0.085
Neg logit contributions
ases-0.285
oke-0.279
olds-0.275
els-0.261
avi-0.259
Token boy
Token ID2933
Feature activation+2.89e+00

Pos logit contributions
 Bun+0.070
 accidentally+0.070
 barrel+0.069
 deserted+0.069
 shield+0.068
Neg logit contributions
ases-0.264
els-0.241
olds-0.240
ips-0.235
oke-0.228
Token named
Token ID3706
Feature activation+2.64e+00

Pos logit contributions
 barrel+0.030
 hut+0.029
 Bun+0.029
 bunny+0.028
 dark+0.028
Neg logit contributions
ases-0.101
olds-0.094
els-0.094
cks-0.090
ips-0.088
Token Tim
Token ID5045
Feature activation-1.93e+00

Pos logit contributions
 hut+0.037
 shield+0.037
 puppy+0.037
 bunny+0.037
 cabin+0.037
Neg logit contributions
ases-0.080
olds-0.074
cks-0.071
els-0.069
irs-0.067
Token found
Token ID1043
Feature activation+3.51e+00

Pos logit contributions
ases+0.070
els+0.065
olds+0.064
cks+0.063
its+0.060
Neg logit contributions
 barrel-0.018
 bunny-0.017
 puppy-0.017
 Bun-0.017
 hut-0.016
Token a
Token ID257
Feature activation+1.12e+01

Pos logit contributions
 barrel+0.030
 hut+0.030
 cabin+0.030
 bicycle+0.030
 puppy+0.027
Neg logit contributions
ases-0.126
olds-0.119
els-0.117
cks-0.115
ips-0.111
Token big
Token ID1263
Feature activation+6.97e+00

Pos logit contributions
 decided+0.150
 Bun+0.150
 While+0.140
 he+0.132
 Curious+0.129
Neg logit contributions
olds-0.235
els-0.235
ric-0.225
its-0.221
ases-0.221
Token,
Token ID11
Feature activation+6.04e+00

Pos logit contributions
 Bun+0.091
 he+0.081
 decided+0.078
Under+0.077
 wanted+0.074
Neg logit contributions
els-0.198
ases-0.197
olds-0.183
ocol-0.177
cks-0.174
Token heavy
Token ID4334
Feature activation+7.18e+00

Pos logit contributions
 Bun+0.077
 barrel+0.076
 While+0.075
 cabin+0.074
 hut+0.073
Neg logit contributions
els-0.141
ases-0.135
olds-0.135
ocol-0.133
cks-0.131
Token rock
Token ID3881
Feature activation+5.42e+00

Pos logit contributions
 Bun+0.094
 decided+0.090
 Curious+0.085
 he+0.085
There+0.083
Neg logit contributions
els-0.193
ases-0.188
ocol-0.174
olds-0.171
ips-0.163
Token in
Token ID287
Feature activation+1.85e+00

Pos logit contributions
 Bun+0.080
 superhero+0.077
 cozy+0.076
 puppy+0.074
 bunny+0.073
Neg logit contributions
ases-0.163
els-0.157
cks-0.153
olds-0.152
ips-0.142
Token a
Token ID257
Feature activation+1.01e+01

Pos logit contributions
 superhero+0.042
 shield+0.040
 cabin+0.039
 barrel+0.039
 wolf+0.039
Neg logit contributions
ases-0.108
cks-0.102
olds-0.100
els-0.096
its-0.094
Token boy
Token ID2933
Feature activation+3.09e+00

Pos logit contributions
 Bun+0.101
 barrel+0.097
 hut+0.092
 cabin+0.090
 shield+0.087
Neg logit contributions
ases-0.274
oke-0.268
olds-0.265
ila-0.248
its-0.247
Token named
Token ID3706
Feature activation+3.11e+00

Pos logit contributions
 barrel+0.032
 Bun+0.031
 hut+0.031
 puppy+0.030
 bunny+0.030
Neg logit contributions
ases-0.109
olds-0.101
els-0.101
cks-0.098
ips-0.095
Token Tim
Token ID5045
Feature activation-1.09e+00

Pos logit contributions
 hut+0.045
 cabin+0.045
 puppy+0.045
 bunny+0.044
 shield+0.044
Neg logit contributions
ases-0.094
olds-0.088
cks-0.083
els-0.081
icks-0.078
Token found
Token ID1043
Feature activation+3.47e+00

Pos logit contributions
ases+0.039
els+0.035
olds+0.035
cks+0.035
its+0.033
Neg logit contributions
 barrel-0.011
 Bun-0.010
 bunny-0.010
 puppy-0.010
 hut-0.010
Token a
Token ID257
Feature activation+1.12e+01

Pos logit contributions
 hut+0.030
 barrel+0.030
 cabin+0.030
 bicycle+0.029
 puppy+0.028
Neg logit contributions
ases-0.126
olds-0.118
els-0.115
cks-0.114
ips-0.111
Token toy
Token ID13373
Feature activation+8.18e+00

Pos logit contributions
 Bun+0.156
 decided+0.151
 While+0.138
 he+0.131
 Curious+0.129
Neg logit contributions
olds-0.232
els-0.227
its-0.223
ases-0.221
ric-0.219
Token motorcycle
Token ID18757
Feature activation+7.02e+00

Pos logit contributions
 cozy+0.121
 ju+0.110
 Bun+0.110
 cos+0.108
 peaceful+0.105
Neg logit contributions
ases-0.240
els-0.235
olds-0.215
cks-0.206
ips-0.200
Token.
Token ID13
Feature activation+4.77e+00

Pos logit contributions
 cozy+0.118
 hut+0.116
 cabin+0.113
 Bun+0.112
 shield+0.110
Neg logit contributions
ases-0.190
els-0.181
olds-0.174
cks-0.173
ips-0.161
Token It
Token ID632
Feature activation+5.08e+00

Pos logit contributions
 puppy+0.058
 bunny+0.058
 hut+0.057
 barrel+0.057
 Bun+0.057
Neg logit contributions
ases-0.156
olds-0.146
els-0.144
cks-0.140
ips-0.137
Token was
Token ID373
Feature activation+3.17e+00

Pos logit contributions
 hut+0.078
 barrel+0.069
 thief+0.069
 puppy+0.068
 cabin+0.067
Neg logit contributions
ases-0.142
els-0.140
cks-0.138
olds-0.133
its-0.128
Token little
Token ID1310
Feature activation+8.12e+00

Pos logit contributions
 barrel+0.097
 Bun+0.097
 hut+0.091
 decided+0.089
 cabin+0.087
Neg logit contributions
ases-0.274
oke-0.264
olds-0.263
avi-0.247
els-0.246
Token girl
Token ID2576
Feature activation+4.44e+00

Pos logit contributions
 accidentally+0.072
 deserted+0.070
 Bun+0.070
 he+0.068
 barrel+0.067
Neg logit contributions
ases-0.258
els-0.233
olds-0.231
ips-0.226
ocol-0.221
Token named
Token ID3706
Feature activation+2.36e+00

Pos logit contributions
 barrel+0.047
 Bun+0.044
 hut+0.043
 bunny+0.043
 dark+0.043
Neg logit contributions
ases-0.154
olds-0.145
els-0.145
cks-0.139
ips-0.135
Token Lucy
Token ID22162
Feature activation-1.30e-02

Pos logit contributions
 barrel+0.035
 shield+0.034
 cabin+0.033
 hunter+0.033
 hut+0.033
Neg logit contributions
ases-0.072
olds-0.068
els-0.066
cks-0.064
irs-0.063
Token found
Token ID1043
Feature activation+3.40e+00

Pos logit contributions
ases+0.000
els+0.000
olds+0.000
cks+0.000
its+0.000
Neg logit contributions
 barrel-0.000
 shield-0.000
 Bun-0.000
 bicycle-0.000
 hut-0.000
Token a
Token ID257
Feature activation+1.12e+01

Pos logit contributions
 barrel+0.030
 bicycle+0.028
 cabin+0.028
 hut+0.027
 hunter+0.025
Neg logit contributions
ases-0.122
olds-0.116
els-0.115
cks-0.112
ips-0.110
Token big
Token ID1263
Feature activation+6.98e+00

Pos logit contributions
 decided+0.143
 Bun+0.139
 he+0.136
 While+0.135
 Curious+0.126
Neg logit contributions
olds-0.230
els-0.226
 mistake-0.222
its-0.221
ric-0.220
Token book
Token ID1492
Feature activation+7.07e+00

Pos logit contributions
 Bun+0.090
 he+0.083
Under+0.079
 decided+0.079
 Curious+0.076
Neg logit contributions
els-0.195
ases-0.194
olds-0.180
ocol-0.176
ips-0.171
Token called
Token ID1444
Feature activation+3.26e+00

Pos logit contributions
 wolf+0.119
 bunny+0.119
 Bun+0.118
 puppy+0.117
 barrel+0.116
Neg logit contributions
ases-0.187
olds-0.182
els-0.175
cks-0.173
ips-0.171
Token a
Token ID257
Feature activation+1.02e+01

Pos logit contributions
 barrel+0.043
 hut+0.041
 dark+0.041
 bunny+0.041
 Bun+0.040
Neg logit contributions
ases-0.104
olds-0.098
els-0.097
cks-0.094
ips-0.092
Token dictionary
Token ID22155
Feature activation+8.34e+00

Pos logit contributions
 Bun+0.159
 decided+0.148
 Benny+0.145
 Bug+0.140
 there+0.138
Neg logit contributions
olds-0.222
oke-0.208
ases-0.195
els-0.195
its-0.194
Token a
Token ID257
Feature activation+9.90e+00

Pos logit contributions
 shield+0.036
 barrel+0.036
 superhero+0.035
 vest+0.035
 puppy+0.035
Neg logit contributions
ases-0.115
cks-0.109
els-0.105
olds-0.105
its-0.100
Token boy
Token ID2933
Feature activation+3.17e+00

Pos logit contributions
 Bun+0.098
 barrel+0.092
 hut+0.085
 cabin+0.083
 shield+0.083
Neg logit contributions
ases-0.288
oke-0.273
olds-0.273
els-0.260
its-0.258
Token named
Token ID3706
Feature activation+2.81e+00

Pos logit contributions
 barrel+0.031
 Bun+0.030
 puppy+0.030
 hut+0.030
 bunny+0.030
Neg logit contributions
ases-0.112
olds-0.105
els-0.105
cks-0.102
ips-0.099
Token Tim
Token ID5045
Feature activation-1.68e+00

Pos logit contributions
 puppy+0.041
 bunny+0.039
 hut+0.039
 cabin+0.039
 shield+0.038
Neg logit contributions
ases-0.087
olds-0.080
cks-0.077
els-0.076
irs-0.071
Token found
Token ID1043
Feature activation+3.53e+00

Pos logit contributions
ases+0.062
els+0.058
olds+0.057
cks+0.057
ips+0.054
Neg logit contributions
 barrel-0.014
 puppy-0.014
 Bun-0.014
 bunny-0.014
 hut-0.013
Token a
Token ID257
Feature activation+1.12e+01

Pos logit contributions
 barrel+0.028
 hut+0.028
 cabin+0.027
 puppy+0.027
 Bun+0.027
Neg logit contributions
ases-0.131
olds-0.123
els-0.121
cks-0.120
ips-0.116
Token toy
Token ID13373
Feature activation+8.24e+00

Pos logit contributions
 Bun+0.160
 decided+0.153
 While+0.142
 he+0.137
 Benny+0.133
Neg logit contributions
els-0.233
olds-0.232
ases-0.225
its-0.223
ric-0.218
Token.
Token ID13
Feature activation+5.32e+00

Pos logit contributions
 cozy+0.118
 Bun+0.110
 ju+0.105
 cos+0.103
 peaceful+0.103
Neg logit contributions
ases-0.249
els-0.240
olds-0.224
cks-0.214
ips-0.207
Token The
Token ID383
Feature activation+3.00e+00

Pos logit contributions
 barrel+0.063
 puppy+0.062
 bunny+0.062
 Bun+0.062
 hut+0.061
Neg logit contributions
ases-0.177
olds-0.166
els-0.164
cks-0.159
ips-0.156
Token toy
Token ID13373
Feature activation+5.41e+00

Pos logit contributions
 Bun+0.027
 hut+0.025
 accidentally+0.024
 barrel+0.024
 cabin+0.023
Neg logit contributions
ases-0.102
els-0.098
olds-0.096
cks-0.092
its-0.092
Token was
Token ID373
Feature activation+3.37e+00

Pos logit contributions
 hut+0.068
 cozy+0.066
 dark+0.065
 Bun+0.063
 wolf+0.063
Neg logit contributions
els-0.163
ases-0.163
olds-0.153
cks-0.145
ips-0.142
Token a
Token ID257
Feature activation+9.92e+00

Pos logit contributions
 shield+0.040
 cabin+0.040
 vest+0.039
 superhero+0.038
 bicycle+0.038
Neg logit contributions
ases-0.116
cks-0.107
olds-0.104
els-0.103
ips-0.101
Token boy
Token ID2933
Feature activation+3.21e+00

Pos logit contributions
 Bun+0.093
 barrel+0.091
 hut+0.087
 cabin+0.085
 shield+0.081
Neg logit contributions
ases-0.286
oke-0.276
olds-0.275
ila-0.256
els-0.256
Token named
Token ID3706
Feature activation+2.94e+00

Pos logit contributions
 barrel+0.034
 Bun+0.033
 hut+0.033
 puppy+0.032
 bunny+0.032
Neg logit contributions
ases-0.112
olds-0.104
els-0.104
cks-0.100
ips-0.097
Token Tim
Token ID5045
Feature activation-1.13e+00

Pos logit contributions
 bunny+0.041
 puppy+0.041
 hut+0.041
 cabin+0.041
 shield+0.040
Neg logit contributions
ases-0.091
olds-0.084
cks-0.081
els-0.080
irs-0.076
Token found
Token ID1043
Feature activation+3.57e+00

Pos logit contributions
ases+0.040
els+0.037
olds+0.036
cks+0.036
its+0.035
Neg logit contributions
 barrel-0.011
 Bun-0.010
 bunny-0.010
 puppy-0.010
 hut-0.010
Token a
Token ID257
Feature activation+1.11e+01

Pos logit contributions
 hut+0.031
 cabin+0.031
 barrel+0.031
 bicycle+0.029
 puppy+0.028
Neg logit contributions
ases-0.129
olds-0.122
els-0.119
cks-0.118
ips-0.114
Token cr
Token ID1067
Feature activation+1.74e+00

Pos logit contributions
 Bun+0.150
 decided+0.147
 While+0.135
 he+0.130
 Curious+0.125
Neg logit contributions
olds-0.233
els-0.225
its-0.220
ric-0.219
 mistake-0.219
Tokenay
Token ID323
Feature activation+1.49e+00

Pos logit contributions
 barrel+0.043
 puppy+0.042
 bunny+0.042
 dark+0.042
 Bun+0.042
Neg logit contributions
ases-0.036
olds-0.033
els-0.032
cks-0.031
ips-0.030
Tokenon
Token ID261
Feature activation+5.21e+00

Pos logit contributions
 barrel+0.034
 hut+0.034
 cabin+0.033
 dark+0.033
 Bun+0.033
Neg logit contributions
ases-0.033
els-0.031
olds-0.030
cks-0.028
ips-0.027
Token box
Token ID3091
Feature activation+5.93e+00

Pos logit contributions
 Bun+0.087
 cozy+0.081
 cabin+0.080
 wolf+0.079
 hunter+0.078
Neg logit contributions
ases-0.148
els-0.139
olds-0.134
cks-0.130
ips-0.129
Token.
Token ID13
Feature activation+4.68e+00

Pos logit contributions
 Bun+0.092
 wolf+0.089
 puppy+0.089
 bunny+0.087
 hunter+0.087
Neg logit contributions
ases-0.172
els-0.165
olds-0.160
cks-0.160
ips-0.154
Token little
Token ID1310
Feature activation+8.32e+00

Pos logit contributions
 barrel+0.099
 Bun+0.095
 hut+0.090
 cabin+0.087
 shield+0.085
Neg logit contributions
ases-0.285
olds-0.274
oke-0.273
cks-0.256
its-0.255
Token rabbit
Token ID22746
Feature activation+5.42e+00

Pos logit contributions
 accidentally+0.071
 Bun+0.069
 barrel+0.067
 deserted+0.067
 he+0.067
Neg logit contributions
ases-0.271
els-0.246
olds-0.246
ips-0.240
ocol-0.231
Token named
Token ID3706
Feature activation+3.27e+00

Pos logit contributions
 barrel+0.074
 dark+0.073
 cabin+0.072
 bicycle+0.072
 puppy+0.072
Neg logit contributions
ases-0.164
olds-0.150
els-0.149
cks-0.146
its-0.134
Token Tim
Token ID5045
Feature activation-1.24e+00

Pos logit contributions
 cabin+0.043
 hut+0.042
 bicycle+0.041
 superhero+0.041
 barrel+0.041
Neg logit contributions
ases-0.099
cks-0.091
olds-0.089
els-0.089
irs-0.088
Token found
Token ID1043
Feature activation+3.36e+00

Pos logit contributions
ases+0.044
els+0.041
cks+0.041
olds+0.041
its+0.039
Neg logit contributions
 barrel-0.011
 puppy-0.011
 bunny-0.011
 hut-0.010
 Bun-0.010
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 bicycle+0.026
 barrel+0.026
 cabin+0.026
 hut+0.025
 puppy+0.024
Neg logit contributions
ases-0.124
olds-0.116
els-0.115
cks-0.114
ips-0.109
Token shiny
Token ID22441
Feature activation+6.89e+00

Pos logit contributions
 decided+0.143
chair+0.141
 Lots+0.137
 While+0.133
 he+0.133
Neg logit contributions
ric-0.209
 mistake-0.204
its-0.200
upid-0.194
ings-0.192
Token trophy
Token ID16383
Feature activation+7.14e+00

Pos logit contributions
 Bun+0.090
 Curious+0.088
Under+0.087
There+0.087
 late+0.086
Neg logit contributions
els-0.186
ases-0.174
ocol-0.165
ir-0.159
its-0.157
Token in
Token ID287
Feature activation+2.28e+00

Pos logit contributions
 Bun+0.124
 cozy+0.119
 dark+0.113
 While+0.112
 cabin+0.112
Neg logit contributions
ases-0.191
els-0.180
cks-0.171
olds-0.167
ips-0.164
Token the
Token ID262
Feature activation+3.62e+00

Pos logit contributions
 barrel+0.029
 puppy+0.028
 bunny+0.028
 hut+0.028
 Bun+0.028
Neg logit contributions
ases-0.074
olds-0.070
els-0.070
cks-0.068
ips-0.066
Token forest
Token ID8222
Feature activation+7.20e+00

Pos logit contributions
 while+0.047
 he+0.046
 Bun+0.045
 there+0.042
 superhero+0.042
Neg logit contributions
ases-0.101
els-0.093
olds-0.093
cks-0.091
ips-0.088
Token a
Token ID257
Feature activation+9.36e+00

Pos logit contributions
 puppy+0.032
 barrel+0.031
 shield+0.030
 vest+0.030
 superhero+0.030
Neg logit contributions
ases-0.114
cks-0.109
els-0.108
olds-0.103
ips-0.102
Token girl
Token ID2576
Feature activation+4.00e+00

Pos logit contributions
 Bun+0.070
 barrel+0.069
 hut+0.062
 he+0.062
 shield+0.061
Neg logit contributions
ases-0.315
olds-0.298
els-0.293
oke-0.291
cks-0.289
Token named
Token ID3706
Feature activation+2.46e+00

Pos logit contributions
 barrel+0.030
 dark+0.029
 puppy+0.029
 bunny+0.029
 Bun+0.028
Neg logit contributions
ases-0.151
olds-0.143
els-0.142
cks-0.139
ips-0.137
Token Lily
Token ID20037
Feature activation-5.29e-01

Pos logit contributions
 barrel+0.035
 puppy+0.033
 hut+0.033
 bunny+0.033
 Bun+0.033
Neg logit contributions
ases-0.077
olds-0.073
els-0.072
cks-0.070
ips-0.068
Token found
Token ID1043
Feature activation+3.21e+00

Pos logit contributions
ases+0.020
olds+0.019
els+0.019
cks+0.019
ips+0.018
Neg logit contributions
 barrel-0.004
 bunny-0.003
 Bun-0.003
 puppy-0.003
 hut-0.003
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 barrel+0.022
 hut+0.020
 puppy+0.019
 cabin+0.019
 Bun+0.019
Neg logit contributions
ases-0.123
olds-0.117
els-0.117
cks-0.113
ips-0.111
Token box
Token ID3091
Feature activation+5.73e+00

Pos logit contributions
 Bun+0.141
 he+0.133
 decided+0.131
 While+0.131
 Benny+0.119
Neg logit contributions
els-0.251
olds-0.251
its-0.240
ases-0.236
ric-0.230
Token of
Token ID286
Feature activation+1.44e+00

Pos logit contributions
 Bun+0.096
 barrel+0.094
 wolf+0.093
 puppy+0.092
 bunny+0.091
Neg logit contributions
ases-0.158
els-0.149
olds-0.148
cks-0.144
ips-0.140
Token shiny
Token ID22441
Feature activation+4.99e+00

Pos logit contributions
 Bun+0.021
storm+0.020
 barrel+0.020
 he+0.020
 accidentally+0.020
Neg logit contributions
ases-0.041
els-0.040
olds-0.039
irs-0.036
cks-0.035
Token jewelry
Token ID22634
Feature activation+6.53e+00

Pos logit contributions
 Bun+0.091
storm+0.083
 restless+0.082
 Benny+0.082
 accidentally+0.082
Neg logit contributions
els-0.140
ases-0.126
olds-0.116
ocol-0.111
its-0.109
Token.
Token ID13
Feature activation+4.52e+00

Pos logit contributions
 Bun+0.113
 Benny+0.108
 While+0.107
 accidentally+0.106
 dark+0.106
Neg logit contributions
els-0.171
ases-0.156
ips-0.148
olds-0.148
cks-0.143
Token little
Token ID1310
Feature activation+7.93e+00

Pos logit contributions
 barrel+0.092
 Bun+0.091
 hut+0.086
 cabin+0.083
 shield+0.081
Neg logit contributions
ases-0.295
olds-0.284
oke-0.279
els-0.267
cks-0.265
Token boy
Token ID2933
Feature activation+2.76e+00

Pos logit contributions
 Bun+0.067
 accidentally+0.066
 deserted+0.065
 barrel+0.063
 cozy+0.062
Neg logit contributions
ases-0.259
els-0.236
olds-0.236
ips-0.227
ocol-0.223
Token named
Token ID3706
Feature activation+2.95e+00

Pos logit contributions
 barrel+0.029
 hut+0.028
 Bun+0.027
 bunny+0.027
 puppy+0.027
Neg logit contributions
ases-0.096
olds-0.090
els-0.090
cks-0.087
ips-0.084
Token Tim
Token ID5045
Feature activation-1.09e+00

Pos logit contributions
 bunny+0.043
 puppy+0.043
 hut+0.042
 cabin+0.042
 wolf+0.042
Neg logit contributions
ases-0.088
olds-0.082
cks-0.079
els-0.076
irs-0.073
Token found
Token ID1043
Feature activation+3.42e+00

Pos logit contributions
ases+0.038
els+0.035
olds+0.035
cks+0.034
its+0.033
Neg logit contributions
 barrel-0.011
 bunny-0.011
 Bun-0.011
 puppy-0.011
 hut-0.010
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 barrel+0.028
 hut+0.028
 cabin+0.028
 bicycle+0.027
 bunny+0.026
Neg logit contributions
ases-0.125
olds-0.117
els-0.115
cks-0.114
ips-0.110
Token magic
Token ID5536
Feature activation+7.59e+00

Pos logit contributions
 decided+0.143
 Bun+0.142
 While+0.130
 he+0.123
 Curious+0.120
Neg logit contributions
olds-0.234
ric-0.229
els-0.227
its-0.224
 mistake-0.219
Token f
Token ID277
Feature activation+1.61e+00

Pos logit contributions
 While+0.129
 Bun+0.129
 restless+0.121
 Curious+0.120
 Betsy+0.119
Neg logit contributions
els-0.174
ases-0.171
olds-0.158
its-0.157
ocol-0.153
Tokenauc
Token ID14272
Feature activation-1.70e+00

Pos logit contributions
 barrel+0.043
 puppy+0.043
 Bun+0.043
 bunny+0.043
 hut+0.042
Neg logit contributions
ases-0.031
olds-0.028
els-0.027
ips-0.025
cks-0.025
Tokenet
Token ID316
Feature activation+2.07e+00

Pos logit contributions
ases+0.029
olds+0.026
els+0.026
cks+0.024
ips+0.023
Neg logit contributions
 barrel-0.048
 bunny-0.047
 hut-0.047
 puppy-0.047
 Bun-0.047
Token in
Token ID287
Feature activation+1.87e+00

Pos logit contributions
 cozy+0.032
 hut+0.031
 Bun+0.031
 barrel+0.029
 cabin+0.029
Neg logit contributions
els-0.063
ases-0.062
olds-0.056
cks-0.055
ips-0.055
Token a
Token ID257
Feature activation+9.76e+00

Pos logit contributions
 shield+0.041
 superhero+0.041
 vest+0.041
 cabin+0.040
 bicycle+0.039
Neg logit contributions
ases-0.112
cks-0.107
olds-0.102
els-0.101
its-0.098
Token boy
Token ID2933
Feature activation+2.75e+00

Pos logit contributions
 barrel+0.094
 hut+0.087
 Bun+0.085
 cabin+0.085
 shield+0.082
Neg logit contributions
ases-0.263
oke-0.261
olds-0.255
avi-0.243
ila-0.239
Token named
Token ID3706
Feature activation+2.49e+00

Pos logit contributions
 barrel+0.030
 hut+0.028
 Bun+0.028
 bunny+0.028
 dark+0.028
Neg logit contributions
ases-0.095
olds-0.089
els-0.088
cks-0.085
ips-0.082
Token Tim
Token ID5045
Feature activation-2.04e+00

Pos logit contributions
 hut+0.036
 bunny+0.036
 cabin+0.035
 puppy+0.034
 wolf+0.034
Neg logit contributions
ases-0.075
olds-0.070
cks-0.067
els-0.066
irs-0.064
Token found
Token ID1043
Feature activation+3.23e+00

Pos logit contributions
ases+0.071
els+0.065
olds+0.064
cks+0.063
its+0.061
Neg logit contributions
 barrel-0.021
 bunny-0.021
 hut-0.020
 Bun-0.020
 puppy-0.020
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 cabin+0.030
 hut+0.030
 barrel+0.029
 bicycle+0.028
 bunny+0.027
Neg logit contributions
ases-0.114
olds-0.107
els-0.105
cks-0.104
ips-0.100
Token heavy
Token ID4334
Feature activation+7.52e+00

Pos logit contributions
 Bun+0.139
 decided+0.139
 While+0.129
 he+0.123
 there+0.120
Neg logit contributions
olds-0.229
ric-0.221
 mistake-0.220
els-0.218
its-0.212
Token box
Token ID3091
Feature activation+5.75e+00

Pos logit contributions
 Bun+0.097
 decided+0.094
There+0.090
 Curious+0.089
 he+0.088
Neg logit contributions
els-0.194
ases-0.191
ocol-0.178
olds-0.176
its-0.167
Token.
Token ID13
Feature activation+4.75e+00

Pos logit contributions
 Bun+0.089
 wolf+0.088
 bunny+0.087
 barrel+0.086
 puppy+0.086
Neg logit contributions
ases-0.160
els-0.153
olds-0.149
cks-0.147
ips-0.143
Token He
Token ID679
Feature activation+4.73e+00

Pos logit contributions
 bunny+0.047
 puppy+0.047
 Bun+0.047
 barrel+0.046
 hut+0.045
Neg logit contributions
ases-0.166
olds-0.157
els-0.154
cks-0.150
ips-0.148
Token wanted
Token ID2227
Feature activation+5.04e+00

Pos logit contributions
 barrel+0.059
 hut+0.058
 wolf+0.057
 cabin+0.056
 puppy+0.055
Neg logit contributions
ases-0.141
els-0.140
olds-0.137
cks-0.131
its-0.128
Token an
Token ID281
Feature activation+5.21e+00

Pos logit contributions
 bicycle+0.064
 barrel+0.064
 thief+0.062
 hunter+0.061
 cabin+0.061
Neg logit contributions
ases-0.168
els-0.151
cks-0.151
ips-0.149
irs-0.148
Token attractive
Token ID10966
Feature activation+7.42e+00

Pos logit contributions
 Bun+0.068
 he+0.066
 barrel+0.065
 hut+0.063
 bunny+0.062
Neg logit contributions
ases-0.165
els-0.159
olds-0.152
cks-0.148
its-0.140
Token crib
Token ID48083
Feature activation+6.86e+00

Pos logit contributions
 he+0.098
 Bun+0.096
There+0.095
 decided+0.091
 deserted+0.091
Neg logit contributions
els-0.185
ases-0.182
ums-0.170
olds-0.169
ocol-0.167
Token in
Token ID287
Feature activation+2.88e+00

Pos logit contributions
 Bun+0.131
 cozy+0.127
 dark+0.123
 ju+0.122
 shield+0.121
Neg logit contributions
ases-0.160
olds-0.142
els-0.141
ips-0.130
cks-0.130
Token a
Token ID257
Feature activation+9.38e+00

Pos logit contributions
 barrel+0.029
 puppy+0.028
 Bun+0.028
 bunny+0.028
 hut+0.027
Neg logit contributions
ases-0.102
els-0.096
olds-0.095
cks-0.094
ips-0.091
Token nursery
Token ID41326
Feature activation+1.10e+01

Pos logit contributions
 Bun+0.132
 he+0.128
 Benny+0.116
 barrel+0.114
 miner+0.112
Neg logit contributions
ases-0.234
cks-0.222
els-0.222
olds-0.218
ips-0.208
Token.
Token ID13
Feature activation+5.82e+00

Pos logit contributions
 Bun+0.193
 barrel+0.185
 Benny+0.182
 wolf+0.179
 shield+0.177
Neg logit contributions
ases-0.286
olds-0.274
els-0.264
ips-0.254
ums-0.242
Token Everyday
Token ID48154
Feature activation+4.77e+00

Pos logit contributions
 barrel+0.097
 hut+0.096
 shield+0.095
 puppy+0.093
 bunny+0.093
Neg logit contributions
ases-0.161
olds-0.150
els-0.144
ips-0.140
cks-0.139
Token a
Token ID257
Feature activation+7.85e+00

Pos logit contributions
 Bun+0.088
 deserted+0.085
 barrel+0.082
 hut+0.082
 puppy+0.080
Neg logit contributions
ases-0.110
els-0.100
olds-0.097
ips-0.097
rs-0.086
Token little
Token ID1310
Feature activation+5.93e+00

Pos logit contributions
 buried+0.092
 barrel+0.089
 Bun+0.085
 hut+0.084
 abandoned+0.078
Neg logit contributions
oke-0.178
olds-0.177
 humor-0.172
 apology-0.169
ases-0.164
Token girl
Token ID2576
Feature activation+3.71e+00

Pos logit contributions
 deserted+0.083
 barrel+0.074
 hut+0.072
 accidentally+0.071
 Bun+0.070
Neg logit contributions
ases-0.142
olds-0.132
oke-0.131
 humor-0.122
 supervision-0.121
Token little
Token ID1310
Feature activation+7.99e+00

Pos logit contributions
 Bun+0.087
 barrel+0.086
 hut+0.082
 cabin+0.078
 shield+0.075
Neg logit contributions
ases-0.293
olds-0.282
oke-0.280
els-0.267
cks-0.263
Token girl
Token ID2576
Feature activation+4.17e+00

Pos logit contributions
 Bun+0.066
 accidentally+0.065
 barrel+0.062
 shield+0.060
 deserted+0.059
Neg logit contributions
ases-0.267
els-0.244
olds-0.243
ips-0.238
ocol-0.229
Token named
Token ID3706
Feature activation+2.78e+00

Pos logit contributions
 barrel+0.041
 Bun+0.038
 hut+0.038
 puppy+0.038
 bunny+0.038
Neg logit contributions
ases-0.148
olds-0.139
els-0.139
cks-0.134
ips-0.131
Token Lucy
Token ID22162
Feature activation-2.19e-01

Pos logit contributions
 barrel+0.039
 shield+0.038
 hut+0.037
 cabin+0.037
 puppy+0.037
Neg logit contributions
ases-0.087
olds-0.082
els-0.079
cks-0.077
ips-0.076
Token found
Token ID1043
Feature activation+3.32e+00

Pos logit contributions
ases+0.008
els+0.008
olds+0.008
cks+0.007
ips+0.007
Neg logit contributions
 barrel-0.002
 Bun-0.002
 shield-0.002
 hut-0.002
 bunny-0.002
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 barrel+0.025
 bicycle+0.023
 hut+0.023
 cabin+0.023
 puppy+0.021
Neg logit contributions
ases-0.124
olds-0.118
els-0.117
cks-0.114
ips-0.112
Token big
Token ID1263
Feature activation+6.81e+00

Pos logit contributions
 Bun+0.140
 decided+0.140
 he+0.134
 While+0.132
 He+0.122
Neg logit contributions
olds-0.235
els-0.233
ric-0.225
its-0.219
 mistake-0.218
Token scale
Token ID5046
Feature activation+6.10e+00

Pos logit contributions
 Bun+0.088
 he+0.081
Under+0.076
 decided+0.076
 Curious+0.073
Neg logit contributions
els-0.193
ases-0.191
olds-0.178
ocol-0.173
cks-0.168
Token in
Token ID287
Feature activation+1.99e+00

Pos logit contributions
 Bun+0.097
 superhero+0.089
 Benny+0.086
 bunny+0.085
 wolf+0.084
Neg logit contributions
ases-0.182
els-0.179
olds-0.176
cks-0.170
ips-0.161
Token her
Token ID607
Feature activation+3.75e+00

Pos logit contributions
 dark+0.030
 there+0.030
 he+0.029
 puppy+0.029
 hut+0.029
Neg logit contributions
ases-0.063
olds-0.058
els-0.057
ips-0.055
cks-0.055
Token house
Token ID2156
Feature activation+6.55e+00

Pos logit contributions
 Bun+0.041
 bunny+0.038
 puppy+0.037
 dark+0.036
 barrel+0.036
Neg logit contributions
ases-0.124
olds-0.119
els-0.119
cks-0.115
ips-0.112
Token a
Token ID257
Feature activation+9.93e+00

Pos logit contributions
 shield+0.043
 superhero+0.043
 barrel+0.042
 cabin+0.041
 hunter+0.040
Neg logit contributions
ases-0.111
olds-0.104
cks-0.103
els-0.101
ips-0.098
Token boy
Token ID2933
Feature activation+2.96e+00

Pos logit contributions
 barrel+0.095
 Bun+0.095
 hut+0.088
 cabin+0.087
 decided+0.084
Neg logit contributions
ases-0.275
oke-0.271
olds-0.268
ila-0.248
its-0.246
Token named
Token ID3706
Feature activation+3.07e+00

Pos logit contributions
 barrel+0.029
 Bun+0.028
 hut+0.028
 puppy+0.028
 bunny+0.028
Neg logit contributions
ases-0.105
olds-0.099
els-0.098
cks-0.095
ips-0.093
Token Tim
Token ID5045
Feature activation-1.19e+00

Pos logit contributions
 hut+0.042
 bunny+0.041
 puppy+0.041
 cabin+0.041
 shield+0.041
Neg logit contributions
ases-0.096
olds-0.090
cks-0.086
els-0.085
irs-0.081
Token found
Token ID1043
Feature activation+3.36e+00

Pos logit contributions
ases+0.041
els+0.038
olds+0.038
cks+0.037
its+0.035
Neg logit contributions
 barrel-0.012
 bunny-0.012
 Bun-0.012
 puppy-0.012
 hut-0.011
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 hut+0.028
 barrel+0.028
 cabin+0.028
 bicycle+0.027
 puppy+0.026
Neg logit contributions
ases-0.123
olds-0.116
els-0.113
cks-0.112
ips-0.109
Token big
Token ID1263
Feature activation+6.82e+00

Pos logit contributions
 Bun+0.148
 decided+0.146
 While+0.133
 he+0.127
 Curious+0.125
Neg logit contributions
olds-0.230
els-0.219
its-0.216
 mistake-0.214
ric-0.214
Token hammer
Token ID15554
Feature activation+4.86e+00

Pos logit contributions
 Bun+0.090
 decided+0.079
 he+0.079
Under+0.079
 Curious+0.076
Neg logit contributions
els-0.189
ases-0.189
olds-0.174
ocol-0.170
ips-0.166
Token in
Token ID287
Feature activation+2.40e+00

Pos logit contributions
 cozy+0.068
 hut+0.068
 Bun+0.068
 cabin+0.066
 barrel+0.066
Neg logit contributions
ases-0.148
els-0.145
olds-0.136
cks-0.135
ips-0.132
Token his
Token ID465
Feature activation+3.95e+00

Pos logit contributions
 barrel+0.029
 dark+0.029
 puppy+0.028
 bunny+0.028
 Bun+0.028
Neg logit contributions
ases-0.080
olds-0.076
els-0.075
cks-0.073
ips-0.072
Token toy
Token ID13373
Feature activation+8.00e+00

Pos logit contributions
 Bun+0.044
 bunny+0.042
 he+0.040
 barrel+0.040
 while+0.039
Neg logit contributions
ases-0.127
olds-0.121
els-0.120
cks-0.117
ips-0.114
Token,
Token ID11
Feature activation+3.89e+00

Pos logit contributions
 barrel+0.051
 Bun+0.050
 dark+0.050
 he+0.050
 bunny+0.049
Neg logit contributions
ases-0.178
olds-0.168
els-0.167
cks-0.163
ips-0.159
Token a
Token ID257
Feature activation+9.97e+00

Pos logit contributions
 barrel+0.039
 shield+0.038
 superhero+0.038
 hunter+0.038
 puppy+0.038
Neg logit contributions
ases-0.125
cks-0.122
els-0.120
ips-0.113
olds-0.112
Token little
Token ID1310
Feature activation+8.04e+00

Pos logit contributions
 barrel+0.082
 Bun+0.074
 hut+0.071
 he+0.071
 shield+0.071
Neg logit contributions
ases-0.318
olds-0.301
oke-0.299
els-0.298
cks-0.297
Token girl
Token ID2576
Feature activation+3.83e+00

Pos logit contributions
 barrel+0.067
 he+0.067
 Bun+0.066
 accidentally+0.065
 shield+0.063
Neg logit contributions
ases-0.267
els-0.250
olds-0.241
ips-0.238
ocol-0.234
Token found
Token ID1043
Feature activation+3.32e+00

Pos logit contributions
 barrel+0.033
 bunny+0.032
 puppy+0.032
 Bun+0.031
 dark+0.031
Neg logit contributions
ases-0.140
olds-0.133
els-0.132
cks-0.129
ips-0.126
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 barrel+0.022
 hut+0.020
 puppy+0.019
 Bun+0.019
 dark+0.019
Neg logit contributions
ases-0.128
olds-0.122
els-0.121
cks-0.118
ips-0.116
Token special
Token ID2041
Feature activation+7.47e+00

Pos logit contributions
 Bun+0.133
 While+0.128
 he+0.128
 decided+0.126
 He+0.115
Neg logit contributions
olds-0.248
els-0.240
its-0.234
ocol-0.229
ric-0.229
Token sp
Token ID599
Feature activation+4.63e+00

Pos logit contributions
 Bun+0.110
 he+0.103
There+0.103
 While+0.102
Under+0.098
Neg logit contributions
els-0.175
olds-0.172
ases-0.171
ocol-0.162
its-0.155
Tokenade
Token ID671
Feature activation+5.23e+00

Pos logit contributions
 Bun+0.113
 puppy+0.110
 bunny+0.107
 hunter+0.104
 Benny+0.102
Neg logit contributions
ases-0.097
els-0.094
olds-0.092
its-0.090
ips-0.082
Token.
Token ID13
Feature activation+5.00e+00

Pos logit contributions
 Bun+0.079
 dark+0.078
 cozy+0.077
 puppy+0.073
 bicycle+0.073
Neg logit contributions
ases-0.152
els-0.145
olds-0.138
ips-0.135
cks-0.132
Token It
Token ID632
Feature activation+4.49e+00

Pos logit contributions
 barrel+0.066
 puppy+0.063
 Bun+0.063
 hut+0.062
 dark+0.062
Neg logit contributions
ases-0.160
olds-0.151
els-0.149
cks-0.143
ips-0.142
Token little
Token ID1310
Feature activation+7.96e+00

Pos logit contributions
 barrel+0.096
 Bun+0.089
 hut+0.085
 shield+0.083
 cabin+0.081
Neg logit contributions
ases-0.274
olds-0.269
oke-0.267
avi-0.251
els-0.248
Token girl
Token ID2576
Feature activation+4.15e+00

Pos logit contributions
 Bun+0.065
 barrel+0.065
 accidentally+0.064
 shield+0.062
 he+0.062
Neg logit contributions
ases-0.260
els-0.239
olds-0.238
ips-0.230
ocol-0.226
Token named
Token ID3706
Feature activation+2.31e+00

Pos logit contributions
 barrel+0.041
 Bun+0.039
 bunny+0.038
 hut+0.038
 puppy+0.038
Neg logit contributions
ases-0.146
olds-0.138
els-0.138
cks-0.133
ips-0.129
Token Lucy
Token ID22162
Feature activation-1.50e-01

Pos logit contributions
 barrel+0.032
 shield+0.030
 cabin+0.030
 hut+0.030
 puppy+0.030
Neg logit contributions
ases-0.073
olds-0.069
els-0.067
cks-0.065
irs-0.064
Token found
Token ID1043
Feature activation+3.28e+00

Pos logit contributions
ases+0.005
els+0.005
olds+0.005
cks+0.005
its+0.005
Neg logit contributions
 barrel-0.001
 shield-0.001
 Bun-0.001
 bicycle-0.001
 cabin-0.001
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 barrel+0.026
 cabin+0.024
 hut+0.023
 bicycle+0.023
 puppy+0.021
Neg logit contributions
ases-0.122
olds-0.115
els-0.115
cks-0.111
ips-0.109
Token colorful
Token ID20239
Feature activation+8.12e+00

Pos logit contributions
 decided+0.136
 Bun+0.134
 he+0.132
 While+0.130
 Curious+0.120
Neg logit contributions
olds-0.232
els-0.222
its-0.222
 mistake-0.222
ric-0.220
Token bird
Token ID6512
Feature activation+2.94e+00

Pos logit contributions
 Bun+0.111
 he+0.107
 Curious+0.106
 late+0.105
 could+0.104
Neg logit contributions
els-0.213
ases-0.199
ocol-0.195
olds-0.187
ir-0.180
Tokenc
Token ID66
Feature activation+2.45e+00

Pos logit contributions
 barrel+0.040
 cabin+0.037
 superhero+0.037
 Bun+0.036
 wolf+0.035
Neg logit contributions
els-0.089
ases-0.089
cks-0.087
olds-0.081
ips-0.079
Tokenage
Token ID496
Feature activation+4.43e+00

Pos logit contributions
 barrel+0.038
 puppy+0.037
 dark+0.037
 bunny+0.037
 Bun+0.037
Neg logit contributions
ases-0.073
olds-0.068
els-0.067
cks-0.065
ips-0.064
Token in
Token ID287
Feature activation+1.97e+00

Pos logit contributions
 barrel+0.066
 hut+0.063
 cabin+0.063
 superhero+0.062
 vest+0.061
Neg logit contributions
ases-0.128
els-0.124
cks-0.121
ips-0.118
olds-0.116
Token a
Token ID257
Feature activation+9.84e+00

Pos logit contributions
 shield+0.051
 vest+0.050
 superhero+0.048
 cabin+0.048
 barrel+0.047
Neg logit contributions
ases-0.095
cks-0.089
olds-0.085
els-0.083
its-0.082
Token girl
Token ID2576
Feature activation+4.36e+00

Pos logit contributions
 Bun+0.090
 barrel+0.090
 hut+0.085
 cabin+0.081
 decided+0.078
Neg logit contributions
ases-0.274
oke-0.273
olds-0.268
avi-0.249
els-0.248
Token named
Token ID3706
Feature activation+2.39e+00

Pos logit contributions
 barrel+0.047
 Bun+0.044
 hut+0.043
 dark+0.043
 puppy+0.043
Neg logit contributions
ases-0.150
olds-0.142
els-0.141
cks-0.135
ips-0.132
Token Lily
Token ID20037
Feature activation-2.48e-01

Pos logit contributions
 barrel+0.032
 shield+0.030
 cabin+0.030
 hut+0.030
 bunny+0.029
Neg logit contributions
ases-0.076
olds-0.073
els-0.070
cks-0.068
ips-0.067
Token found
Token ID1043
Feature activation+3.14e+00

Pos logit contributions
ases+0.009
els+0.008
olds+0.008
cks+0.008
ips+0.008
Neg logit contributions
 barrel-0.002
 Bun-0.002
 shield-0.002
 bunny-0.002
 cabin-0.002
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 barrel+0.027
 cabin+0.025
 bicycle+0.024
 hut+0.024
 shield+0.022
Neg logit contributions
ases-0.116
olds-0.111
els-0.109
cks-0.105
ips-0.104
Token warm
Token ID5814
Feature activation+6.21e+00

Pos logit contributions
 Bun+0.143
 decided+0.140
 he+0.135
 While+0.134
 He+0.126
Neg logit contributions
olds-0.233
els-0.228
its-0.219
ric-0.219
 mistake-0.217
Token muff
Token ID27563
Feature activation-4.58e-01

Pos logit contributions
 he+0.083
 accidentally+0.083
Under+0.082
 decided+0.082
 could+0.078
Neg logit contributions
els-0.143
ases-0.139
ir-0.134
olds-0.134
rs-0.133
Tokenin
Token ID259
Feature activation+2.83e+00

Pos logit contributions
ases+0.011
els+0.010
olds+0.010
cks+0.010
ips+0.010
Neg logit contributions
 Bun-0.010
 barrel-0.010
 puppy-0.010
 bunny-0.010
 dark-0.010
Token on
Token ID319
Feature activation+2.01e+00

Pos logit contributions
 Bun+0.048
 cozy+0.044
 superhero+0.044
 Benny+0.044
 shield+0.043
Neg logit contributions
ases-0.082
els-0.077
olds-0.074
cks-0.071
ips-0.069
Token the
Token ID262
Feature activation+3.05e+00

Pos logit contributions
 barrel+0.031
 hut+0.029
 puppy+0.029
 Bun+0.029
 bunny+0.028
Neg logit contributions
ases-0.059
els-0.056
olds-0.055
cks-0.054
irs-0.052
Token small
Token ID1402
Feature activation+6.74e+00

Pos logit contributions
 Bun+0.087
 barrel+0.083
 hut+0.080
 cabin+0.075
 he+0.073
Neg logit contributions
ases-0.297
olds-0.284
oke-0.282
els-0.271
cks-0.264
Token boy
Token ID2933
Feature activation+2.93e+00

Pos logit contributions
 Bun+0.079
 deserted+0.075
 accidentally+0.072
 decided+0.072
 he+0.070
Neg logit contributions
ases-0.201
els-0.186
olds-0.184
oke-0.176
ips-0.171
Token named
Token ID3706
Feature activation+3.01e+00

Pos logit contributions
 barrel+0.031
 hut+0.029
 Bun+0.029
 puppy+0.029
 dark+0.029
Neg logit contributions
ases-0.103
olds-0.096
els-0.096
cks-0.092
ips-0.090
Token Tim
Token ID5045
Feature activation-2.49e+00

Pos logit contributions
 puppy+0.045
 shield+0.045
 bunny+0.045
 superhero+0.044
 hut+0.044
Neg logit contributions
ases-0.087
olds-0.081
cks-0.078
els-0.075
irs-0.073
Token found
Token ID1043
Feature activation+3.34e+00

Pos logit contributions
ases+0.084
els+0.078
olds+0.076
cks+0.075
its+0.072
Neg logit contributions
 barrel-0.029
 bunny-0.029
 puppy-0.029
 Bun-0.028
 hut-0.028
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 hut+0.029
 barrel+0.028
 cabin+0.028
 bicycle+0.028
 puppy+0.026
Neg logit contributions
ases-0.121
olds-0.114
els-0.112
cks-0.110
ips-0.107
Token penny
Token ID26369
Feature activation+4.67e+00

Pos logit contributions
 decided+0.147
 Bun+0.145
 While+0.133
 he+0.129
 wanted+0.126
Neg logit contributions
els-0.230
olds-0.229
ric-0.220
its-0.218
 mistake-0.215
Token.
Token ID13
Feature activation+4.74e+00

Pos logit contributions
 Bun+0.073
 superhero+0.071
 cozy+0.070
 cabin+0.069
 hut+0.069
Neg logit contributions
els-0.131
ases-0.125
cks-0.119
ips-0.116
olds-0.115
Token This
Token ID770
Feature activation+4.74e+00

Pos logit contributions
 bunny+0.052
 puppy+0.052
 hut+0.051
 Bun+0.051
 barrel+0.051
Neg logit contributions
ases-0.160
olds-0.151
els-0.149
cks-0.144
ips-0.141
Token penny
Token ID26369
Feature activation+2.49e+00

Pos logit contributions
 Bun+0.054
 barrel+0.054
 hut+0.053
 dark+0.051
 cabin+0.050
Neg logit contributions
ases-0.156
els-0.149
olds-0.146
cks-0.142
ips-0.140
Token was
Token ID373
Feature activation+1.93e+00

Pos logit contributions
 hut+0.033
 cabin+0.031
 wolf+0.030
 puppy+0.030
 barrel+0.030
Neg logit contributions
els-0.078
ases-0.075
olds-0.073
cks-0.071
ips-0.069
Token a
Token ID257
Feature activation+9.84e+00

Pos logit contributions
 shield+0.039
 superhero+0.038
 vest+0.037
 barrel+0.037
 cabin+0.036
Neg logit contributions
ases-0.121
cks-0.112
olds-0.111
els-0.108
ips-0.105
Token boy
Token ID2933
Feature activation+3.19e+00

Pos logit contributions
 barrel+0.093
 Bun+0.092
 hut+0.084
 decided+0.082
 cabin+0.081
Neg logit contributions
ases-0.281
olds-0.273
oke-0.269
els-0.253
its-0.248
Token named
Token ID3706
Feature activation+3.13e+00

Pos logit contributions
 barrel+0.032
 Bun+0.030
 hut+0.030
 puppy+0.030
 bunny+0.030
Neg logit contributions
ases-0.113
olds-0.106
els-0.106
cks-0.102
ips-0.100
Token Tim
Token ID5045
Feature activation-1.07e+00

Pos logit contributions
 bunny+0.040
 hut+0.039
 cabin+0.039
 puppy+0.039
 shield+0.038
Neg logit contributions
ases-0.101
olds-0.095
cks-0.091
els-0.090
irs-0.086
Token found
Token ID1043
Feature activation+3.38e+00

Pos logit contributions
ases+0.037
els+0.034
olds+0.034
cks+0.034
its+0.032
Neg logit contributions
 barrel-0.011
 bunny-0.011
 Bun-0.011
 puppy-0.010
 hut-0.010
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 barrel+0.027
 hut+0.027
 cabin+0.027
 bicycle+0.026
 bunny+0.025
Neg logit contributions
ases-0.124
olds-0.117
els-0.115
cks-0.113
ips-0.110
Token microphone
Token ID21822
Feature activation+6.16e+00

Pos logit contributions
 Bun+0.146
 decided+0.144
 While+0.133
 Curious+0.127
 he+0.125
Neg logit contributions
olds-0.237
els-0.225
ases-0.223
its-0.222
ric-0.221
Token in
Token ID287
Feature activation+2.18e+00

Pos logit contributions
 Bun+0.109
 cabin+0.103
 cozy+0.103
 hunter+0.102
 superhero+0.101
Neg logit contributions
ases-0.156
els-0.148
olds-0.139
cks-0.138
ips-0.136
Token his
Token ID465
Feature activation+3.70e+00

Pos logit contributions
 barrel+0.026
 dark+0.026
 puppy+0.025
 bunny+0.025
 Bun+0.025
Neg logit contributions
ases-0.073
olds-0.069
els-0.068
cks-0.066
ips-0.065
Token toy
Token ID13373
Feature activation+7.83e+00

Pos logit contributions
 barrel+0.037
 Bun+0.037
 he+0.036
 bunny+0.035
 wolf+0.034
Neg logit contributions
ases-0.124
olds-0.117
els-0.116
cks-0.114
ips-0.112
Token box
Token ID3091
Feature activation+5.44e+00

Pos logit contributions
 Bun+0.084
 restless+0.082
 dark+0.082
 cozy+0.080
 thief+0.079
Neg logit contributions
ases-0.250
els-0.241
olds-0.234
ips-0.230
cks-0.221
Token little
Token ID1310
Feature activation+7.85e+00

Pos logit contributions
 barrel+0.094
 Bun+0.091
 hut+0.089
 shield+0.084
 decided+0.083
Neg logit contributions
ases-0.267
oke-0.263
olds-0.260
avi-0.247
ila-0.243
Token girl
Token ID2576
Feature activation+4.26e+00

Pos logit contributions
 accidentally+0.068
 deserted+0.067
 barrel+0.065
 shield+0.065
 Bun+0.065
Neg logit contributions
ases-0.248
els-0.226
olds-0.224
ips-0.218
ocol-0.215
Token named
Token ID3706
Feature activation+2.37e+00

Pos logit contributions
 barrel+0.044
 Bun+0.042
 hut+0.041
 bunny+0.041
 dark+0.041
Neg logit contributions
ases-0.149
olds-0.140
els-0.139
cks-0.134
ips-0.130
Token Amy
Token ID14235
Feature activation+1.00e+00

Pos logit contributions
 barrel+0.033
 shield+0.032
 cabin+0.031
 hunter+0.031
 hut+0.031
Neg logit contributions
ases-0.074
olds-0.071
els-0.068
cks-0.066
irs-0.065
Token found
Token ID1043
Feature activation+3.16e+00

Pos logit contributions
 barrel+0.010
 Bun+0.009
 shield+0.009
 bunny+0.009
 bicycle+0.009
Neg logit contributions
ases-0.035
els-0.033
olds-0.033
cks-0.032
its-0.031
Token a
Token ID257
Feature activation+1.10e+01

Pos logit contributions
 barrel+0.026
 hut+0.024
 cabin+0.023
 bicycle+0.023
 puppy+0.021
Neg logit contributions
ases-0.116
olds-0.110
els-0.109
cks-0.106
ips-0.104
Token big
Token ID1263
Feature activation+6.82e+00

Pos logit contributions
 decided+0.137
 While+0.132
 he+0.132
 Bun+0.132
 Curious+0.123
Neg logit contributions
olds-0.227
els-0.224
 mistake-0.220
ric-0.219
its-0.218
Token box
Token ID3091
Feature activation+6.14e+00

Pos logit contributions
 Bun+0.089
 he+0.082
Under+0.080
 decided+0.078
 Curious+0.076
Neg logit contributions
els-0.191
ases-0.187
olds-0.174
ocol-0.172
ips-0.165
Token.
Token ID13
Feature activation+4.59e+00

Pos logit contributions
 Bun+0.092
 barrel+0.089
 wolf+0.088
 puppy+0.088
 hunter+0.087
Neg logit contributions
ases-0.178
els-0.172
olds-0.167
cks-0.166
ips-0.161
Token Inside
Token ID14384
Feature activation+5.41e+00

Pos logit contributions
 barrel+0.060
 Bun+0.058
 puppy+0.058
 bunny+0.057
 dark+0.057
Neg logit contributions
ases-0.147
olds-0.139
els-0.136
cks-0.132
ips-0.130
Token the
Token ID262
Feature activation+5.08e+00

Pos logit contributions
 he+0.060
 barrel+0.060
 dark+0.059
 bunny+0.057
 hut+0.057
Neg logit contributions
ases-0.189
olds-0.178
els-0.174
cks-0.172
ips-0.166
Token and
Token ID290
Feature activation+1.15e+00

Pos logit contributions
ases+0.028
olds+0.026
els+0.026
cks+0.025
ips+0.025
Neg logit contributions
 bunny-0.013
 Bun-0.013
 puppy-0.013
 barrel-0.013
 dark-0.013
Token laughed
Token ID13818
Feature activation-1.69e+00

Pos logit contributions
 barrel+0.018
 puppy+0.018
 Bun+0.017
 hut+0.017
 bunny+0.017
Neg logit contributions
ases-0.034
olds-0.032
els-0.031
cks-0.031
ips-0.030
Token and
Token ID290
Feature activation+2.20e-01

Pos logit contributions
ases+0.045
els+0.041
olds+0.041
rs+0.040
cks+0.039
Neg logit contributions
 barrel-0.031
 thief-0.028
 bicycle-0.027
 stole-0.026
 abandoned-0.026
Token ate
Token ID15063
Feature activation-1.05e+00

Pos logit contributions
 barrel+0.004
 hut+0.004
 Bun+0.004
 puppy+0.004
 cabin+0.004
Neg logit contributions
ases-0.006
olds-0.006
els-0.006
cks-0.005
ips-0.005
Token ch
Token ID442
Feature activation-6.42e+00

Pos logit contributions
ases+0.033
olds+0.031
els+0.031
cks+0.030
ips+0.029
Neg logit contributions
 barrel-0.014
 puppy-0.014
 Bun-0.014
 bunny-0.013
 hut-0.013
Tokenocol
Token ID4668
Feature activation-1.70e+01

Pos logit contributions
 supervision+0.083
olds+0.072
ric+0.062
reating+0.061
 angles+0.059
Neg logit contributions
 little-0.170
 bunny-0.169
 dark-0.168
 restless-0.167
 hungry-0.165
Tokenates
Token ID689
Feature activation-2.78e+00

Pos logit contributions
olds+0.345
 supervision+0.318
ases+0.312
its+0.304
 humor+0.303
Neg logit contributions
 barrel-0.342
 hut-0.331
 there-0.331
 Bun-0.330
 outside-0.329
Token.
Token ID13
Feature activation+2.02e+00

Pos logit contributions
ases+0.101
olds+0.096
els+0.094
cks+0.092
ips+0.091
Neg logit contributions
 barrel-0.025
 bunny-0.025
 dark-0.024
 he-0.024
 puppy-0.024
Token They
Token ID1119
Feature activation+1.43e+00

Pos logit contributions
 barrel+0.029
 puppy+0.028
 bunny+0.028
 Bun+0.027
 hut+0.027
Neg logit contributions
ases-0.063
olds-0.059
els-0.059
cks-0.057
ips-0.056
Token had
Token ID550
Feature activation+5.53e-01

Pos logit contributions
 barrel+0.020
 hut+0.019
 Bun+0.019
 puppy+0.018
 cabin+0.018
Neg logit contributions
ases-0.045
els-0.042
olds-0.041
cks-0.040
ips-0.038
Token a
Token ID257
Feature activation+4.47e+00

Pos logit contributions
 barrel+0.005
 hut+0.004
 bicycle+0.004
 Bun+0.004
 bunny+0.004
Neg logit contributions
ases-0.020
olds-0.019
cks-0.019
els-0.019
ips-0.018
Tokenbled
Token ID9342
Feature activation-4.41e+00

Pos logit contributions
ases+0.129
olds+0.120
els+0.117
cks+0.116
irs+0.111
Neg logit contributions
 bunny-0.113
 he-0.112
 barrel-0.111
 Bun-0.110
 hut-0.110
Token up
Token ID510
Feature activation-3.15e+00

Pos logit contributions
ases+0.154
olds+0.148
cks+0.140
els+0.138
irs+0.137
Neg logit contributions
 bunny-0.051
 he-0.050
 there-0.049
 dark-0.049
 puppy-0.047
Token all
Token ID477
Feature activation-3.98e+00

Pos logit contributions
ases+0.099
olds+0.094
els+0.093
cks+0.090
ips+0.088
Neg logit contributions
 barrel-0.043
 puppy-0.041
 Bun-0.041
 hut-0.041
 bunny-0.041
Token the
Token ID262
Feature activation-3.82e+00

Pos logit contributions
ases+0.134
olds+0.126
cks+0.124
els+0.124
irs+0.119
Neg logit contributions
 dark-0.048
 he-0.048
 barrel-0.047
 bunny-0.047
 there-0.047
Token ch
Token ID442
Feature activation-5.34e+00

Pos logit contributions
ases+0.128
olds+0.119
els+0.117
cks+0.114
ips+0.113
Neg logit contributions
 barrel-0.049
 dark-0.049
 bunny-0.048
 puppy-0.048
 hut-0.047
Tokenocol
Token ID4668
Feature activation-1.70e+01

Pos logit contributions
ases+0.056
cks+0.055
olds+0.055
ric+0.054
 supervision+0.054
Neg logit contributions
 hut-0.145
 seed-0.145
 little-0.142
 barrel-0.140
 shield-0.140
Tokenates
Token ID689
Feature activation-2.63e+00

Pos logit contributions
olds+0.355
ases+0.327
 supervision+0.321
its+0.312
 humor+0.312
Neg logit contributions
 barrel-0.329
 seed-0.321
 hut-0.319
 there-0.312
 in-0.306
Token,
Token ID11
Feature activation+3.21e-01

Pos logit contributions
ases+0.087
olds+0.082
els+0.082
cks+0.080
ips+0.078
Neg logit contributions
 barrel-0.031
 puppy-0.030
 Bun-0.030
 dark-0.030
 bunny-0.030
Token and
Token ID290
Feature activation+1.86e+00

Pos logit contributions
 barrel+0.004
 Bun+0.004
 puppy+0.004
 hut+0.004
 bunny+0.004
Neg logit contributions
ases-0.010
olds-0.010
els-0.010
cks-0.009
ips-0.009
Token she
Token ID673
Feature activation+1.19e+00

Pos logit contributions
 barrel+0.024
 hut+0.023
 puppy+0.022
 dark+0.022
 Bun+0.022
Neg logit contributions
ases-0.059
olds-0.056
els-0.056
cks-0.054
ips-0.053
Token was
Token ID373
Feature activation-3.30e-01

Pos logit contributions
 barrel+0.013
 puppy+0.013
 dark+0.013
 hut+0.012
 Bun+0.012
Neg logit contributions
ases-0.040
olds-0.038
els-0.038
cks-0.037
ips-0.036
Token't
Token ID470
Feature activation-3.21e+00

Pos logit contributions
ases+0.064
els+0.060
cks+0.059
olds+0.059
ips+0.057
Neg logit contributions
 puppy-0.029
 Bun-0.029
 bunny-0.029
 he-0.029
 dark-0.028
Token have
Token ID423
Feature activation-8.53e-01

Pos logit contributions
ases+0.089
olds+0.083
els+0.082
cks+0.080
ips+0.077
Neg logit contributions
 barrel-0.056
 dark-0.054
 Bun-0.054
 bunny-0.054
 hut-0.054
Token all
Token ID477
Feature activation-2.84e+00

Pos logit contributions
ases+0.027
olds+0.025
els+0.025
cks+0.024
ips+0.024
Neg logit contributions
 barrel-0.012
 hut-0.011
 bunny-0.011
 Bun-0.011
 puppy-0.011
Token these
Token ID777
Feature activation-2.47e+00

Pos logit contributions
ases+0.089
els+0.084
cks+0.081
olds+0.081
ips+0.080
Neg logit contributions
 he-0.040
 dark-0.039
 there-0.039
 puppy-0.038
 barrel-0.038
Token ch
Token ID442
Feature activation-5.42e+00

Pos logit contributions
ases+0.081
olds+0.075
els+0.075
cks+0.074
ips+0.072
Neg logit contributions
 barrel-0.031
 dark-0.031
 puppy-0.030
 bunny-0.030
 he-0.030
Tokenocol
Token ID4668
Feature activation-1.70e+01

Pos logit contributions
cks+0.058
ases+0.054
irs+0.053
olds+0.050
 angles+0.048
Neg logit contributions
 little-0.140
 restless-0.132
 barrel-0.132
 hungry-0.131
 long-0.131
Tokenates
Token ID689
Feature activation-1.93e+00

Pos logit contributions
olds+0.355
 horror+0.350
ases+0.330
its+0.329
oke+0.314
Neg logit contributions
 there-0.290
 in-0.287
 outside-0.284
 barrel-0.283
 seed-0.278
Token!
Token ID0
Feature activation+1.66e+00

Pos logit contributions
ases+0.064
olds+0.060
els+0.060
cks+0.058
ips+0.057
Neg logit contributions
 barrel-0.024
 Bun-0.023
 puppy-0.023
 hut-0.023
 bunny-0.023
Token Now
Token ID2735
Feature activation+3.91e-01

Pos logit contributions
 Bun+0.024
 puppy+0.024
 bunny+0.024
 he+0.023
 barrel+0.023
Neg logit contributions
ases-0.051
els-0.048
cks-0.047
olds-0.046
ips-0.045
Token,
Token ID11
Feature activation-9.36e-01

Pos logit contributions
 barrel+0.005
 dark+0.005
 bunny+0.005
 puppy+0.005
 Bun+0.005
Neg logit contributions
ases-0.012
olds-0.012
els-0.011
cks-0.011
ips-0.011
Token go
Token ID467
Feature activation-2.86e+00

Pos logit contributions
ases+0.027
olds+0.026
els+0.025
cks+0.024
ips+0.024
Neg logit contributions
 barrel-0.015
 hut-0.014
 dark-0.014
 Bun-0.014
 puppy-0.014
Token he
Token ID339
Feature activation+1.78e+00

Pos logit contributions
 barrel+0.013
 hut+0.012
 Bun+0.012
 puppy+0.011
 bunny+0.011
Neg logit contributions
olds-0.065
ases-0.065
els-0.062
cks-0.060
 supervision-0.060
Token ate
Token ID15063
Feature activation+1.83e-01

Pos logit contributions
 hut+0.030
 barrel+0.028
 cabin+0.028
 dark+0.026
 wolf+0.025
Neg logit contributions
ases-0.046
olds-0.044
els-0.043
cks-0.042
its-0.041
Token all
Token ID477
Feature activation-3.32e+00

Pos logit contributions
 barrel+0.002
 dark+0.002
 bunny+0.002
 puppy+0.002
 Bun+0.002
Neg logit contributions
ases-0.006
olds-0.006
els-0.006
cks-0.006
ips-0.006
Token the
Token ID262
Feature activation-2.53e+00

Pos logit contributions
ases+0.107
els+0.100
olds+0.100
cks+0.098
ips+0.095
Neg logit contributions
 he-0.044
 barrel-0.044
 dark-0.043
 bunny-0.042
 Bun-0.042
Token ch
Token ID442
Feature activation-4.84e+00

Pos logit contributions
ases+0.082
els+0.079
olds+0.079
cks+0.076
its+0.074
Neg logit contributions
 barrel-0.029
 hut-0.029
 Bun-0.028
 puppy-0.028
 dark-0.027
Tokenocol
Token ID4668
Feature activation-1.62e+01

Pos logit contributions
ases+0.050
olds+0.050
cks+0.047
 supervision+0.047
irs+0.044
Neg logit contributions
 bunny-0.141
 he-0.140
 little-0.139
 shield-0.135
 seed-0.135
Tokenates
Token ID689
Feature activation-1.50e+00

Pos logit contributions
olds+0.331
ases+0.314
its+0.292
 supervision+0.282
 humor+0.278
Neg logit contributions
 barrel-0.318
 there-0.311
 outside-0.310
 hut-0.308
 in-0.307
Token and
Token ID290
Feature activation+1.84e+00

Pos logit contributions
ases+0.049
els+0.047
olds+0.047
cks+0.045
ips+0.044
Neg logit contributions
 barrel-0.018
 Bun-0.018
 puppy-0.017
 dark-0.017
 hut-0.017
Token sweets
Token ID42402
Feature activation+3.41e-01

Pos logit contributions
 barrel+0.025
 hut+0.025
 cabin+0.024
 dark+0.023
 puppy+0.023
Neg logit contributions
ases-0.056
olds-0.054
els-0.053
cks-0.052
ips-0.049
Token.
Token ID13
Feature activation+2.15e+00

Pos logit contributions
 barrel+0.005
 Bun+0.004
 dark+0.004
 puppy+0.004
 hut+0.004
Neg logit contributions
ases-0.010
els-0.010
olds-0.010
cks-0.009
ips-0.009
Token Then
Token ID3244
Feature activation+1.57e+00

Pos logit contributions
 hut+0.025
 dark+0.025
 barrel+0.025
 bunny+0.024
 shield+0.024
Neg logit contributions
ases-0.070
olds-0.069
els-0.064
ips-0.063
irs-0.061
Token giving
Token ID3501
Feature activation-3.59e+00

Pos logit contributions
ases+0.148
olds+0.141
els+0.136
ips+0.135
irs+0.132
Neg logit contributions
 little-0.083
 bunny-0.081
 there-0.080
 puppy-0.079
 Bun-0.079
Token him
Token ID683
Feature activation-3.43e+00

Pos logit contributions
ases+0.109
olds+0.102
els+0.101
cks+0.099
ips+0.097
Neg logit contributions
 barrel-0.053
 puppy-0.053
 bunny-0.053
 Bun-0.053
 dark-0.053
Token too
Token ID1165
Feature activation-1.91e+00

Pos logit contributions
ases+0.116
olds+0.110
els+0.108
cks+0.105
ips+0.102
Neg logit contributions
 barrel-0.038
 Bun-0.037
 hut-0.036
 puppy-0.036
 bunny-0.036
Token many
Token ID867
Feature activation-2.67e+00

Pos logit contributions
ases+0.064
olds+0.062
els+0.060
cks+0.059
its+0.057
Neg logit contributions
 barrel-0.022
 puppy-0.021
 bunny-0.021
 Bun-0.021
 hut-0.021
Token ch
Token ID442
Feature activation-5.04e+00

Pos logit contributions
ases+0.085
olds+0.081
els+0.080
cks+0.077
ips+0.075
Neg logit contributions
 barrel-0.035
 Bun-0.034
 hut-0.034
 puppy-0.034
 bunny-0.034
Tokenocol
Token ID4668
Feature activation-1.62e+01

Pos logit contributions
olds+0.066
ases+0.065
cks+0.063
irs+0.062
els+0.059
Neg logit contributions
 dark-0.134
 there-0.134
 hut-0.132
 barrel-0.132
 little-0.132
Tokenates
Token ID689
Feature activation-1.55e+00

Pos logit contributions
olds+0.312
ases+0.286
its+0.284
irs+0.279
oke+0.261
Neg logit contributions
 there-0.337
 barrel-0.334
 hut-0.327
 in-0.323
 seed-0.323
Token."
Token ID526
Feature activation-1.13e+00

Pos logit contributions
ases+0.050
olds+0.047
els+0.047
cks+0.045
ips+0.044
Neg logit contributions
 barrel-0.020
 Bun-0.020
 puppy-0.019
 hut-0.019
 dark-0.019
Token The
Token ID383
Feature activation-2.37e+00

Pos logit contributions
ases+0.035
olds+0.033
els+0.033
cks+0.032
ips+0.031
Neg logit contributions
 barrel-0.016
 dark-0.016
 hut-0.016
 bunny-0.015
 puppy-0.015
Token king
Token ID5822
Feature activation-2.76e+00

Pos logit contributions
ases+0.078
olds+0.075
els+0.073
cks+0.070
its+0.068
Neg logit contributions
 Bun-0.027
 barrel-0.027
 dark-0.026
 hut-0.026
 puppy-0.025
Token learned
Token ID4499
Feature activation-1.08e+00

Pos logit contributions
ases+0.088
olds+0.083
els+0.082
cks+0.080
ips+0.078
Neg logit contributions
 barrel-0.037
 dark-0.036
 puppy-0.035
 Bun-0.035
 hut-0.035
Token as
Token ID355
Feature activation-8.73e-01

Pos logit contributions
 barrel+0.014
 Bun+0.014
 dark+0.014
 hut+0.014
 bunny+0.013
Neg logit contributions
ases-0.040
olds-0.038
els-0.038
cks-0.037
ips-0.036
Token he
Token ID339
Feature activation+2.66e-01

Pos logit contributions
ases+0.030
olds+0.029
els+0.028
cks+0.027
irs+0.027
Neg logit contributions
 barrel-0.009
 hut-0.008
 puppy-0.008
 bunny-0.008
 cabin-0.008
Token opened
Token ID4721
Feature activation+2.14e-01

Pos logit contributions
 barrel+0.003
 hut+0.003
 dark+0.003
 Bun+0.003
 puppy+0.003
Neg logit contributions
ases-0.009
olds-0.009
els-0.009
cks-0.008
ips-0.008
Token the
Token ID262
Feature activation+1.76e-01

Pos logit contributions
 barrel+0.003
 puppy+0.003
 bunny+0.003
 dark+0.003
 Bun+0.003
Neg logit contributions
ases-0.006
olds-0.006
els-0.006
cks-0.006
ips-0.006
Token ch
Token ID442
Feature activation-3.24e+00

Pos logit contributions
 Bun+0.003
 he+0.002
 accidentally+0.002
 Benny+0.002
 bunny+0.002
Neg logit contributions
ases-0.005
olds-0.005
els-0.005
cks-0.004
its-0.004
Tokenocol
Token ID4668
Feature activation-1.61e+01

Pos logit contributions
ases+0.040
olds+0.039
cks+0.036
els+0.035
irs+0.034
Neg logit contributions
 barrel-0.097
 shield-0.097
 bunny-0.096
 little-0.096
 dark-0.096
Tokenates
Token ID689
Feature activation-4.24e-01

Pos logit contributions
olds+0.331
ases+0.300
its+0.290
oke+0.276
irs+0.276
Neg logit contributions
 barrel-0.324
 hut-0.309
 there-0.307
 shield-0.304
 in-0.303
Token and
Token ID290
Feature activation+2.54e+00

Pos logit contributions
ases+0.014
els+0.013
olds+0.013
cks+0.013
ips+0.012
Neg logit contributions
 barrel-0.005
 Bun-0.005
 puppy-0.005
 dark-0.005
 bunny-0.005
Token started
Token ID2067
Feature activation+3.02e+00

Pos logit contributions
 barrel+0.035
 Bun+0.034
 hut+0.034
 dark+0.034
 puppy+0.034
Neg logit contributions
ases-0.078
olds-0.074
els-0.073
cks-0.071
ips-0.068
Token eating
Token ID6600
Feature activation+4.09e-01

Pos logit contributions
 barrel+0.034
 he+0.034
 dark+0.034
 bunny+0.034
 puppy+0.034
Neg logit contributions
ases-0.102
olds-0.095
els-0.095
cks-0.092
ips-0.090
Token them
Token ID606
Feature activation-1.01e+00

Pos logit contributions
 barrel+0.006
 dark+0.006
 bunny+0.006
 puppy+0.006
 hut+0.006
Neg logit contributions
ases-0.013
olds-0.012
els-0.012
cks-0.012
ips-0.011
Token not
Token ID407
Feature activation-2.53e+00

Pos logit contributions
ases+0.052
els+0.049
olds+0.049
cks+0.048
ips+0.047
Neg logit contributions
 he-0.021
 barrel-0.020
 bunny-0.020
 Bun-0.020
 puppy-0.020
Token eat
Token ID4483
Feature activation-2.03e+00

Pos logit contributions
ases+0.072
olds+0.067
els+0.067
cks+0.065
ips+0.063
Neg logit contributions
 barrel-0.042
 puppy-0.041
 bunny-0.041
 dark-0.041
 Bun-0.041
Token too
Token ID1165
Feature activation-1.53e+00

Pos logit contributions
ases+0.066
olds+0.062
els+0.060
cks+0.059
ips+0.059
Neg logit contributions
 dark-0.027
 he-0.027
 barrel-0.027
 bunny-0.027
 puppy-0.026
Token many
Token ID867
Feature activation-2.16e+00

Pos logit contributions
ases+0.053
olds+0.050
els+0.049
cks+0.048
ips+0.047
Neg logit contributions
 barrel-0.017
 puppy-0.016
 Bun-0.016
 bunny-0.016
 hut-0.016
Token ch
Token ID442
Feature activation-4.87e+00

Pos logit contributions
ases+0.073
olds+0.068
ips+0.067
cks+0.066
els+0.066
Neg logit contributions
 he-0.027
 dark-0.026
 bunny-0.025
 barrel-0.025
 puppy-0.025
Tokenocol
Token ID4668
Feature activation-1.61e+01

Pos logit contributions
olds+0.047
ases+0.046
 supervision+0.045
irs+0.044
cks+0.043
Neg logit contributions
 there-0.141
 little-0.140
 seed-0.140
 he-0.140
 dark-0.139
Tokenates
Token ID689
Feature activation-1.71e+00

Pos logit contributions
olds+0.318
its+0.291
ases+0.288
irs+0.283
oke+0.270
Neg logit contributions
 barrel-0.328
 there-0.324
 hut-0.317
 in-0.315
 seed-0.314
Token and
Token ID290
Feature activation+1.87e+00

Pos logit contributions
ases+0.059
olds+0.056
els+0.055
cks+0.054
ips+0.053
Neg logit contributions
 barrel-0.018
 bunny-0.018
 puppy-0.018
 dark-0.018
 Bun-0.018
Token his
Token ID465
Feature activation-7.65e-01

Pos logit contributions
 barrel+0.023
 Bun+0.022
 hut+0.022
 puppy+0.022
 bunny+0.022
Neg logit contributions
ases-0.061
olds-0.058
els-0.057
cks-0.055
ips-0.053
Token friend
Token ID1545
Feature activation-8.33e-01

Pos logit contributions
ases+0.023
olds+0.022
els+0.022
cks+0.021
ips+0.021
Neg logit contributions
 barrel-0.011
 Bun-0.011
 puppy-0.011
 dark-0.011
 bunny-0.011
Token learned
Token ID4499
Feature activation-1.29e+00

Pos logit contributions
ases+0.030
olds+0.028
els+0.028
cks+0.027
ips+0.026
Neg logit contributions
 barrel-0.008
 hut-0.007
 dark-0.007
 Bun-0.007
 puppy-0.007
Token we
Token ID356
Feature activation-1.46e+00

Pos logit contributions
ases+0.105
olds+0.099
els+0.098
cks+0.095
ips+0.093
Neg logit contributions
 barrel-0.047
 puppy-0.046
 bunny-0.046
 dark-0.045
 Bun-0.045
Token can
Token ID460
Feature activation-6.98e-01

Pos logit contributions
ases+0.043
olds+0.040
els+0.040
irs+0.038
its+0.038
Neg logit contributions
 barrel-0.022
 Bun-0.022
 dark-0.022
 puppy-0.021
 hut-0.021
Token get
Token ID651
Feature activation-2.74e+00

Pos logit contributions
ases+0.019
olds+0.018
els+0.018
cks+0.017
ips+0.016
Neg logit contributions
 barrel-0.013
 dark-0.012
 puppy-0.012
 Bun-0.012
 hut-0.012
Token more
Token ID517
Feature activation-4.54e-01

Pos logit contributions
ases+0.089
olds+0.084
els+0.083
cks+0.081
ips+0.079
Neg logit contributions
 barrel-0.035
 hut-0.034
 Bun-0.033
 puppy-0.033
 bunny-0.032
Token ch
Token ID442
Feature activation-5.30e+00

Pos logit contributions
ases+0.015
olds+0.014
els+0.014
cks+0.014
ips+0.013
Neg logit contributions
 barrel-0.006
 dark-0.005
 bunny-0.005
 puppy-0.005
 Bun-0.005
Tokenocol
Token ID4668
Feature activation-1.60e+01

Pos logit contributions
olds+0.057
ases+0.056
irs+0.052
cks+0.049
 supervision+0.048
Neg logit contributions
 strong-0.148
 little-0.148
 bunny-0.146
 dark-0.145
 seed-0.145
Tokenates
Token ID689
Feature activation-1.76e+00

Pos logit contributions
olds+0.311
its+0.295
ases+0.288
irs+0.276
 humor+0.275
Neg logit contributions
 barrel-0.328
 outside-0.322
 there-0.322
 hut-0.316
 in-0.315
Token later
Token ID1568
Feature activation+1.27e+00

Pos logit contributions
ases+0.057
olds+0.054
els+0.054
cks+0.052
ips+0.051
Neg logit contributions
 barrel-0.022
 Bun-0.022
 puppy-0.021
 dark-0.021
 hut-0.021
Token.
Token ID13
Feature activation+2.92e+00

Pos logit contributions
 barrel+0.019
 bunny+0.018
 hut+0.018
 Bun+0.018
 shield+0.017
Neg logit contributions
ases-0.038
olds-0.036
els-0.035
ips-0.034
cks-0.034
Token For
Token ID1114
Feature activation-3.17e+00

Pos logit contributions
 barrel+0.039
 Bun+0.039
 puppy+0.039
 bunny+0.038
 dark+0.038
Neg logit contributions
ases-0.093
els-0.087
olds-0.087
cks-0.085
ips-0.082
Token now
Token ID783
Feature activation-2.17e-01

Pos logit contributions
ases+0.109
olds+0.105
els+0.104
cks+0.100
its+0.099
Neg logit contributions
 Bun-0.034
 dark-0.034
 there-0.033
 bunny-0.032
 puppy-0.032
TokenL
Token ID43
Feature activation-1.01e+01

Pos logit contributions
ases+0.083
olds+0.079
els+0.078
cks+0.077
irs+0.074
Neg logit contributions
 bunny-0.040
 puppy-0.039
 dark-0.039
 he-0.038
 barrel-0.037
Tokenily
Token ID813
Feature activation-3.61e+00

Pos logit contributions
ases+0.262
els+0.254
cks+0.251
olds+0.247
irs+0.233
Neg logit contributions
 he-0.175
 barrel-0.171
 there-0.168
 bunny-0.168
 Bun-0.167
Token,
Token ID11
Feature activation-2.39e+00

Pos logit contributions
ases+0.117
olds+0.110
els+0.109
cks+0.106
ips+0.104
Neg logit contributions
 barrel-0.046
 hut-0.044
 dark-0.044
 Bun-0.044
 puppy-0.043
Token these
Token ID777
Feature activation-1.88e+00

Pos logit contributions
ases+0.068
olds+0.064
els+0.063
cks+0.061
ips+0.060
Neg logit contributions
 barrel-0.041
 bunny-0.040
 puppy-0.040
 he-0.040
 dark-0.040
Token ch
Token ID442
Feature activation-5.40e+00

Pos logit contributions
ases+0.042
olds+0.038
els+0.038
cks+0.036
ips+0.035
Neg logit contributions
 barrel-0.044
 Bun-0.043
 dark-0.043
 hut-0.043
 puppy-0.043
Tokenocol
Token ID4668
Feature activation-1.59e+01

Pos logit contributions
olds+0.079
 supervision+0.078
cks+0.071
irs+0.070
ases+0.069
Neg logit contributions
 bunny-0.138
 wolf-0.129
 bear-0.128
 little-0.127
 hunter-0.126
Tokenates
Token ID689
Feature activation-1.94e+00

Pos logit contributions
olds+0.336
 supervision+0.304
irs+0.297
ases+0.295
 apology+0.289
Neg logit contributions
 barrel-0.289
 there-0.284
 bunny-0.281
 carrot-0.280
 in-0.280
Token are
Token ID389
Feature activation-2.80e+00

Pos logit contributions
ases+0.057
olds+0.054
els+0.053
cks+0.052
ips+0.050
Neg logit contributions
 barrel-0.030
 bunny-0.030
 dark-0.030
 puppy-0.030
 Bun-0.029
Token bitter
Token ID12922
Feature activation-1.51e+00

Pos logit contributions
ases+0.100
olds+0.095
els+0.094
cks+0.091
ips+0.090
Neg logit contributions
 barrel-0.027
 dark-0.027
 bunny-0.026
 puppy-0.026
 Bun-0.026
Token,"
Token ID553
Feature activation-4.09e+00

Pos logit contributions
ases+0.047
olds+0.044
els+0.044
cks+0.041
its+0.041
Neg logit contributions
 barrel-0.021
 Bun-0.021
 hut-0.020
 puppy-0.020
 cabin-0.019
Token he
Token ID339
Feature activation-2.27e+00

Pos logit contributions
ases+0.140
olds+0.135
els+0.131
cks+0.128
ips+0.124
Neg logit contributions
 barrel-0.045
 hut-0.043
 Bun-0.043
 puppy-0.042
 bunny-0.041
Token was
Token ID373
Feature activation-1.30e+00

Pos logit contributions
 barrel+0.001
 puppy+0.001
 hut+0.001
 bunny+0.001
 dark+0.001
Neg logit contributions
ases-0.002
olds-0.002
els-0.002
cks-0.002
ips-0.002
Token filled
Token ID5901
Feature activation-6.96e-01

Pos logit contributions
ases+0.042
els+0.040
olds+0.040
cks+0.039
irs+0.037
Neg logit contributions
 barrel-0.016
 bunny-0.015
 puppy-0.015
 Bun-0.015
 hut-0.015
Token with
Token ID351
Feature activation-2.35e+00

Pos logit contributions
ases+0.022
els+0.021
olds+0.021
cks+0.021
ips+0.020
Neg logit contributions
 barrel-0.009
 bunny-0.008
 puppy-0.008
 hut-0.008
 dark-0.008
Token delicious
Token ID12625
Feature activation-7.49e-01

Pos logit contributions
ases+0.071
olds+0.067
els+0.066
cks+0.064
ips+0.062
Neg logit contributions
 barrel-0.035
 Bun-0.033
 bunny-0.033
 puppy-0.033
 hut-0.033
Token ch
Token ID442
Feature activation-4.41e+00

Pos logit contributions
ases+0.022
els+0.022
olds+0.021
cks+0.020
irs+0.020
Neg logit contributions
 Bun-0.011
 barrel-0.010
 he-0.010
 dark-0.010
 hut-0.010
Tokenocol
Token ID4668
Feature activation-1.57e+01

Pos logit contributions
olds+0.049
ases+0.049
cks+0.043
 supervision+0.041
els+0.038
Neg logit contributions
 little-0.135
 bunny-0.135
 hut-0.134
 dark-0.134
 barrel-0.133
Tokenates
Token ID689
Feature activation-1.73e+00

Pos logit contributions
olds+0.305
ases+0.289
its+0.267
oke+0.250
 supervision+0.249
Neg logit contributions
 barrel-0.350
 hut-0.342
 there-0.340
 seed-0.335
 outside-0.334
Token.
Token ID13
Feature activation+2.03e+00

Pos logit contributions
ases+0.056
olds+0.053
els+0.053
cks+0.052
ips+0.050
Neg logit contributions
 barrel-0.021
 Bun-0.021
 dark-0.020
 hut-0.020
 puppy-0.020
Token He
Token ID679
Feature activation+2.18e+00

Pos logit contributions
 barrel+0.026
 dark+0.026
 hut+0.026
 puppy+0.025
 bunny+0.025
Neg logit contributions
ases-0.065
olds-0.062
els-0.060
cks-0.059
ips-0.058
Token was
Token ID373
Feature activation+1.98e-01

Pos logit contributions
 barrel+0.027
 dark+0.026
 hut+0.026
 puppy+0.025
 Bun+0.025
Neg logit contributions
ases-0.071
olds-0.067
els-0.066
cks-0.064
ips-0.062
Token happy
Token ID3772
Feature activation+1.12e+00

Pos logit contributions
 barrel+0.001
 dark+0.001
 puppy+0.001
 bunny+0.001
 Bun+0.001
Neg logit contributions
ases-0.008
olds-0.007
els-0.007
cks-0.007
ips-0.007
Token saw
Token ID2497
Feature activation-6.14e-01

Pos logit contributions
 puppy+0.015
 barrel+0.015
 Bun+0.014
 hut+0.014
 bunny+0.014
Neg logit contributions
ases-0.052
els-0.050
olds-0.049
cks-0.048
ips-0.047
Token all
Token ID477
Feature activation-1.53e+00

Pos logit contributions
ases+0.021
olds+0.020
els+0.019
cks+0.019
ips+0.019
Neg logit contributions
 dark-0.007
 barrel-0.007
 bunny-0.007
 hut-0.007
 he-0.007
Token the
Token ID262
Feature activation-2.18e+00

Pos logit contributions
ases+0.048
olds+0.045
els+0.044
cks+0.043
ips+0.042
Neg logit contributions
 dark-0.022
 barrel-0.022
 he-0.022
 hut-0.021
 bunny-0.021
Token tasty
Token ID25103
Feature activation-5.80e-01

Pos logit contributions
ases+0.069
olds+0.066
els+0.065
cks+0.063
ips+0.061
Neg logit contributions
 barrel-0.029
 Bun-0.028
 bunny-0.028
 puppy-0.028
 hut-0.028
Token ch
Token ID442
Feature activation-4.03e+00

Pos logit contributions
ases+0.018
olds+0.017
els+0.017
cks+0.017
ips+0.016
Neg logit contributions
 barrel-0.008
 puppy-0.008
 bunny-0.008
 dark-0.008
 hut-0.008
Tokenocol
Token ID4668
Feature activation-1.57e+01

Pos logit contributions
ases+0.036
olds+0.035
cks+0.030
irs+0.026
rs+0.025
Neg logit contributions
 hut-0.134
 barrel-0.131
 there-0.129
 shield-0.129
 thief-0.129
Tokenates
Token ID689
Feature activation-9.47e-01

Pos logit contributions
olds+0.327
ases+0.300
its+0.280
 humor+0.279
 supervision+0.278
Neg logit contributions
 barrel-0.326
 hut-0.317
 seed-0.312
 there-0.312
 outside-0.304
Token inside
Token ID2641
Feature activation+1.68e+00

Pos logit contributions
ases+0.031
els+0.030
olds+0.029
cks+0.029
ips+0.028
Neg logit contributions
 Bun-0.011
 barrel-0.011
 puppy-0.011
 bunny-0.010
 dark-0.010
Token.
Token ID13
Feature activation+1.94e+00

Pos logit contributions
 barrel+0.016
 dark+0.016
 bunny+0.015
 hut+0.015
 he+0.015
Neg logit contributions
ases-0.060
olds-0.057
els-0.056
cks-0.055
ips-0.054
Token She
Token ID1375
Feature activation+2.67e+00

Pos logit contributions
 barrel+0.027
 dark+0.026
 puppy+0.026
 bunny+0.026
 hut+0.026
Neg logit contributions
ases-0.060
olds-0.058
els-0.056
cks-0.054
ips-0.054
Token couldn
Token ID3521
Feature activation+6.51e-01

Pos logit contributions
 barrel+0.033
 hut+0.032
 dark+0.032
 puppy+0.032
 Bun+0.031
Neg logit contributions
ases-0.085
els-0.081
olds-0.081
cks-0.078
its-0.075
Token box
Token ID3091
Feature activation+1.07e+00

Pos logit contributions
ases+0.027
els+0.025
olds+0.025
cks+0.024
ips+0.024
Neg logit contributions
 Bun-0.006
 barrel-0.006
 puppy-0.006
 bunny-0.006
 dark-0.006
Token and
Token ID290
Feature activation+1.90e+00

Pos logit contributions
 barrel+0.011
 dark+0.011
 hut+0.011
 he+0.011
 bunny+0.010
Neg logit contributions
ases-0.037
olds-0.035
els-0.035
cks-0.034
irs-0.034
Token share
Token ID2648
Feature activation-2.03e+00

Pos logit contributions
 barrel+0.029
 dark+0.028
 bunny+0.028
 puppy+0.028
 hut+0.028
Neg logit contributions
ases-0.057
olds-0.053
els-0.053
cks-0.051
ips-0.050
Token the
Token ID262
Feature activation-3.48e+00

Pos logit contributions
ases+0.072
olds+0.067
els+0.064
ips+0.064
irs+0.064
Neg logit contributions
 there-0.024
 dark-0.022
 he-0.022
 a-0.022
 bunny-0.022
Token ch
Token ID442
Feature activation-4.71e+00

Pos logit contributions
ases+0.107
els+0.103
olds+0.102
cks+0.100
its+0.094
Neg logit contributions
 Bun-0.042
 accidentally-0.041
 he-0.038
 puppy-0.037
 bunny-0.036
Tokenocol
Token ID4668
Feature activation-1.57e+01

Pos logit contributions
ases+0.052
olds+0.051
 supervision+0.045
cks+0.044
irs+0.043
Neg logit contributions
 barrel-0.143
 shield-0.142
 hut-0.141
 little-0.140
 hunter-0.137
Tokenates
Token ID689
Feature activation-1.76e+00

Pos logit contributions
olds+0.325
 supervision+0.300
ases+0.294
 horror+0.289
 humor+0.289
Neg logit contributions
 barrel-0.311
 hut-0.299
 seed-0.299
 whole-0.284
 cave-0.279
Token.
Token ID13
Feature activation+1.54e+00

Pos logit contributions
ases+0.066
olds+0.062
els+0.061
cks+0.060
ips+0.060
Neg logit contributions
 he-0.015
 barrel-0.014
 bunny-0.014
 hut-0.013
 puppy-0.013
Token They
Token ID1119
Feature activation+1.38e+00

Pos logit contributions
 barrel+0.022
 bunny+0.021
 puppy+0.021
 Bun+0.021
 dark+0.021
Neg logit contributions
ases-0.048
olds-0.045
els-0.045
cks-0.043
ips-0.042
Token are
Token ID389
Feature activation-1.55e+00

Pos logit contributions
 barrel+0.024
 bunny+0.024
 dark+0.024
 he+0.024
 hut+0.024
Neg logit contributions
ases-0.038
olds-0.036
els-0.036
cks-0.034
ips-0.034
Token happy
Token ID3772
Feature activation+7.91e-03

Pos logit contributions
ases+0.051
olds+0.048
els+0.048
cks+0.047
ips+0.045
Neg logit contributions
 barrel-0.019
 Bun-0.019
 puppy-0.018
 bunny-0.018
 hut-0.018
Token and
Token ID290
Feature activation+1.00e+00

Pos logit contributions
 barrel+0.017
 bunny+0.016
 puppy+0.016
 dark+0.016
 hut+0.016
Neg logit contributions
ases-0.046
olds-0.044
els-0.043
cks-0.042
ips-0.041
Token they
Token ID484
Feature activation+1.30e-01

Pos logit contributions
 barrel+0.013
 hut+0.012
 dark+0.012
 puppy+0.012
 cabin+0.012
Neg logit contributions
ases-0.033
olds-0.031
els-0.030
cks-0.029
ips-0.029
Token shared
Token ID4888
Feature activation-1.31e+00

Pos logit contributions
 dark+0.002
 hut+0.002
 barrel+0.002
 wolf+0.002
 puppy+0.002
Neg logit contributions
ases-0.004
els-0.004
olds-0.003
cks-0.003
ips-0.003
Token the
Token ID262
Feature activation-3.56e+00

Pos logit contributions
ases+0.045
olds+0.042
els+0.041
cks+0.040
ips+0.040
Neg logit contributions
 dark-0.016
 barrel-0.016
 he-0.015
 there-0.015
 puppy-0.015
Token ch
Token ID442
Feature activation-4.46e+00

Pos logit contributions
ases+0.111
olds+0.105
els+0.104
cks+0.100
ips+0.098
Neg logit contributions
 Bun-0.048
 barrel-0.048
 hut-0.047
 bunny-0.046
 puppy-0.046
Tokenocol
Token ID4668
Feature activation-1.56e+01

Pos logit contributions
cks+0.057
ases+0.055
irs+0.053
els+0.047
 supervision+0.046
Neg logit contributions
 little-0.132
 barrel-0.124
 bunny-0.120
 toy-0.120
 boy-0.119
Tokenates
Token ID689
Feature activation-2.06e+00

Pos logit contributions
 horror+0.315
 supervision+0.315
olds+0.313
irs+0.300
ases+0.295
Neg logit contributions
 barrel-0.276
 seed-0.265
 in-0.263
 outside-0.257
 there-0.255
Token with
Token ID351
Feature activation-3.91e+00

Pos logit contributions
ases+0.075
olds+0.069
els+0.069
cks+0.068
irs+0.067
Neg logit contributions
 he-0.021
 barrel-0.020
 bunny-0.019
 while-0.018
 puppy-0.018
Token everyone
Token ID2506
Feature activation-1.48e+00

Pos logit contributions
ases+0.112
olds+0.104
els+0.104
cks+0.102
ips+0.101
Neg logit contributions
 he-0.066
 puppy-0.064
 dark-0.063
 a-0.063
 little-0.063
Token in
Token ID287
Feature activation-4.09e+00

Pos logit contributions
ases+0.050
olds+0.047
els+0.046
cks+0.045
ips+0.044
Neg logit contributions
 barrel-0.017
 Bun-0.017
 dark-0.017
 puppy-0.017
 bunny-0.017
Token the
Token ID262
Feature activation-1.99e+00

Pos logit contributions
ases+0.143
olds+0.141
els+0.137
its+0.135
cks+0.134
Neg logit contributions
 there-0.047
 dark-0.044
 little-0.043
 a-0.042
 he-0.042
Token reward
Token ID6721
Feature activation+4.42e-01

Pos logit contributions
 Bun+0.029
 barrel+0.026
 dark+0.026
 he+0.025
 cozy+0.025
Neg logit contributions
ases-0.081
els-0.077
olds-0.075
cks-0.071
ips-0.070
Token.
Token ID13
Feature activation+4.45e+00

Pos logit contributions
 barrel+0.005
 puppy+0.005
 bunny+0.005
 Bun+0.005
 dark+0.005
Neg logit contributions
ases-0.015
olds-0.014
els-0.014
cks-0.014
ips-0.013
Token It
Token ID632
Feature activation+3.59e+00

Pos logit contributions
 barrel+0.066
 dark+0.065
 hut+0.063
 shield+0.061
 bunny+0.061
Neg logit contributions
ases-0.133
olds-0.127
els-0.122
cks-0.117
irs-0.117
Token was
Token ID373
Feature activation+1.71e+00

Pos logit contributions
 barrel+0.041
 puppy+0.039
 dark+0.039
 hut+0.038
 Bun+0.038
Neg logit contributions
ases-0.120
olds-0.113
els-0.112
cks-0.109
its-0.106
Token ch
Token ID442
Feature activation-3.57e+00

Pos logit contributions
 barrel+0.015
 bunny+0.014
 puppy+0.014
 hut+0.013
 Bun+0.013
Neg logit contributions
ases-0.062
olds-0.059
els-0.059
cks-0.057
ips-0.056
Tokenocol
Token ID4668
Feature activation-1.55e+01

Pos logit contributions
ases+0.059
olds+0.057
els+0.054
cks+0.053
irs+0.049
Neg logit contributions
 dark-0.098
 bunny-0.097
 barrel-0.096
 Bun-0.096
 hut-0.095
Tokenates
Token ID689
Feature activation+4.01e-01

Pos logit contributions
olds+0.305
ases+0.276
its+0.266
irs+0.252
oke+0.244
Neg logit contributions
 there-0.340
 barrel-0.332
 in-0.323
 a-0.323
 outside-0.320
Token and
Token ID290
Feature activation+2.91e+00

Pos logit contributions
 barrel+0.005
 puppy+0.005
 Bun+0.005
 hut+0.005
 dark+0.005
Neg logit contributions
ases-0.013
els-0.012
olds-0.012
cks-0.012
ips-0.012
Token sweets
Token ID42402
Feature activation+1.29e+00

Pos logit contributions
 barrel+0.036
 hut+0.035
 puppy+0.035
 Bun+0.034
 dark+0.034
Neg logit contributions
ases-0.093
els-0.088
olds-0.087
cks-0.086
ips-0.082
Token!
Token ID0
Feature activation+2.63e+00

Pos logit contributions
 barrel+0.017
 hut+0.017
 Bun+0.017
 dark+0.016
 puppy+0.016
Neg logit contributions
ases-0.038
els-0.037
olds-0.036
cks-0.035
ips-0.034
Token
Token ID198
Feature activation-3.34e+00

Pos logit contributions
 barrel+0.038
 dark+0.037
 hut+0.036
 bunny+0.036
 puppy+0.036
Neg logit contributions
ases-0.081
olds-0.076
els-0.075
cks-0.073
ips-0.071
Token temper
Token ID4124
Feature activation+2.97e+00

Pos logit contributions
 Bun+0.027
 barrel+0.026
 dark+0.026
 hut+0.026
 bunny+0.026
Neg logit contributions
ases-0.051
olds-0.048
els-0.047
cks-0.044
its-0.044
Token and
Token ID290
Feature activation+3.73e+00

Pos logit contributions
 barrel+0.038
 hut+0.037
 Bun+0.037
 bunny+0.037
 puppy+0.036
Neg logit contributions
ases-0.095
olds-0.091
els-0.089
cks-0.086
ips-0.084
Token often
Token ID1690
Feature activation+2.38e+00

Pos logit contributions
 hut+0.040
 barrel+0.038
 bunny+0.036
 cabin+0.035
 puppy+0.034
Neg logit contributions
olds-0.124
ases-0.124
els-0.118
cks-0.112
its-0.110
Token threw
Token ID9617
Feature activation+5.82e-01

Pos logit contributions
 barrel+0.027
 hut+0.025
 bunny+0.025
 Bun+0.025
 puppy+0.024
Neg logit contributions
ases-0.081
olds-0.076
els-0.075
cks-0.073
ips-0.071
Token temper
Token ID4124
Feature activation+1.65e-01

Pos logit contributions
 barrel+0.007
 dark+0.007
 puppy+0.007
 bunny+0.007
 Bun+0.007
Neg logit contributions
ases-0.019
olds-0.018
els-0.018
cks-0.017
ips-0.017
Token tant
Token ID24246
Feature activation-1.55e+01

Pos logit contributions
 barrel+0.003
 dark+0.003
 puppy+0.003
 bunny+0.003
 he+0.003
Neg logit contributions
ases-0.005
olds-0.005
els-0.004
cks-0.004
ips-0.004
Tokenrums
Token ID45241
Feature activation-2.92e+00

Pos logit contributions
ases+0.263
ips+0.258
olds+0.228
irs+0.219
ucks+0.218
Neg logit contributions
 Bun-0.360
 he-0.346
 wolf-0.329
 wanted-0.327
 barrel-0.321
Token.
Token ID13
Feature activation+3.04e+00

Pos logit contributions
ases+0.101
els+0.095
olds+0.095
cks+0.092
ips+0.090
Neg logit contributions
 barrel-0.032
 hut-0.030
 dark-0.030
 bunny-0.029
 puppy-0.029
Token One
Token ID1881
Feature activation+1.68e+00

Pos logit contributions
 bunny+0.040
 barrel+0.039
 puppy+0.039
 Bun+0.038
 hut+0.038
Neg logit contributions
ases-0.095
olds-0.093
els-0.089
cks-0.086
ips-0.084
Token day
Token ID1110
Feature activation+4.80e+00

Pos logit contributions
 Bun+0.021
 hut+0.020
 barrel+0.019
 puppy+0.018
 shield+0.017
Neg logit contributions
ases-0.052
olds-0.050
els-0.048
its-0.045
ips-0.044
Token,
Token ID11
Feature activation+2.57e+00

Pos logit contributions
 bunny+0.075
 barrel+0.074
 Bun+0.073
 hut+0.072
 puppy+0.071
Neg logit contributions
olds-0.131
ases-0.129
els-0.124
irs-0.115
cks-0.115
Token she
Token ID673
Feature activation+1.91e+00

Pos logit contributions
 barrel+0.015
 hut+0.014
 shield+0.014
 Bun+0.014
 hunter+0.014
Neg logit contributions
ases-0.032
olds-0.032
els-0.030
ips-0.029
cks-0.028
Token paid
Token ID3432
Feature activation-6.06e+00

Pos logit contributions
 barrel+0.025
 Bun+0.025
 dark+0.025
 puppy+0.024
 hut+0.024
Neg logit contributions
ases-0.059
els-0.056
olds-0.056
cks-0.053
its-0.052
Token for
Token ID329
Feature activation-4.93e+00

Pos logit contributions
ases+0.198
els+0.185
olds+0.182
cks+0.182
ips+0.177
Neg logit contributions
 he-0.083
 Bun-0.079
 puppy-0.077
 bunny-0.077
 little-0.076
Token the
Token ID262
Feature activation-1.98e+00

Pos logit contributions
ases+0.177
els+0.164
olds+0.162
cks+0.160
its+0.157
Neg logit contributions
 he-0.059
 dark-0.056
 puppy-0.055
 bunny-0.054
 Bun-0.054
Token ch
Token ID442
Feature activation-4.27e+00

Pos logit contributions
ases+0.057
olds+0.056
els+0.054
its+0.051
cks+0.051
Neg logit contributions
 Bun-0.029
 barrel-0.027
 hut-0.027
 dark-0.026
 Benny-0.026
Tokenocol
Token ID4668
Feature activation-1.54e+01

Pos logit contributions
ases+0.048
cks+0.043
irs+0.041
olds+0.040
els+0.036
Neg logit contributions
 little-0.135
 bunny-0.133
 barrel-0.131
 superhero-0.130
 thief-0.129
Tokenates
Token ID689
Feature activation-1.84e+00

Pos logit contributions
olds+0.317
irs+0.291
ases+0.290
its+0.290
 horror+0.274
Neg logit contributions
 barrel-0.290
 seed-0.276
 carrot-0.275
 hut-0.271
 whole-0.270
Token and
Token ID290
Feature activation+1.30e+00

Pos logit contributions
ases+0.060
olds+0.057
els+0.057
cks+0.055
ips+0.054
Neg logit contributions
 barrel-0.022
 Bun-0.022
 dark-0.022
 puppy-0.022
 bunny-0.022
Token the
Token ID262
Feature activation-1.52e+00

Pos logit contributions
 barrel+0.018
 hut+0.017
 dark+0.017
 Bun+0.017
 bunny+0.017
Neg logit contributions
ases-0.040
olds-0.038
els-0.038
cks-0.036
ips-0.035
Token two
Token ID734
Feature activation-1.56e+00

Pos logit contributions
ases+0.043
olds+0.043
els+0.041
cks+0.038
its+0.038
Neg logit contributions
 Bun-0.023
 barrel-0.021
 hut-0.021
 Benny-0.020
 dark-0.020
Token of
Token ID286
Feature activation-3.97e+00

Pos logit contributions
ases+0.045
olds+0.041
els+0.041
cks+0.041
ips+0.039
Neg logit contributions
 he-0.026
 barrel-0.026
 bunny-0.026
 dark-0.026
 puppy-0.026
Token son
Token ID3367
Feature activation-5.97e-01

Pos logit contributions
ases+0.062
olds+0.059
els+0.058
cks+0.055
ips+0.054
Neg logit contributions
 Bun-0.034
 barrel-0.033
 hut-0.033
 dark-0.032
 he-0.032
Token is
Token ID318
Feature activation-5.33e-01

Pos logit contributions
ases+0.018
olds+0.017
els+0.017
cks+0.017
ips+0.016
Neg logit contributions
 barrel-0.008
 dark-0.008
 hut-0.008
 Bun-0.008
 puppy-0.008
Token eating
Token ID6600
Feature activation+5.99e-01

Pos logit contributions
ases+0.017
olds+0.016
els+0.016
cks+0.016
ips+0.015
Neg logit contributions
 barrel-0.007
 Bun-0.007
 hut-0.007
 bunny-0.006
 puppy-0.006
Token our
Token ID674
Feature activation-2.75e+00

Pos logit contributions
 barrel+0.008
 Bun+0.008
 puppy+0.008
 hut+0.008
 bunny+0.008
Neg logit contributions
ases-0.019
els-0.018
olds-0.017
cks-0.017
ips-0.016
Token ch
Token ID442
Feature activation-4.17e+00

Pos logit contributions
ases+0.094
olds+0.089
els+0.088
cks+0.086
ips+0.084
Neg logit contributions
 barrel-0.031
 bunny-0.030
 dark-0.030
 puppy-0.030
 Bun-0.029
Tokenocol
Token ID4668
Feature activation-1.53e+01

Pos logit contributions
olds+0.044
ases+0.043
cks+0.042
irs+0.038
 supervision+0.037
Neg logit contributions
 little-0.121
 superhero-0.119
 bunny-0.118
 barrel-0.117
 shield-0.116
Tokenates
Token ID689
Feature activation-8.31e-01

Pos logit contributions
olds+0.316
ases+0.295
irs+0.292
its+0.289
 horror+0.288
Neg logit contributions
 barrel-0.277
 seed-0.264
 whole-0.260
 outside-0.260
 hut-0.259
Token!"
Token ID2474
Feature activation-1.90e+00

Pos logit contributions
ases+0.026
els+0.024
olds+0.024
cks+0.023
ips+0.023
Neg logit contributions
 Bun-0.012
 barrel-0.011
 puppy-0.011
 hut-0.011
 dark-0.011
Token
Token ID220
Feature activation-5.28e+00

Pos logit contributions
ases+0.056
olds+0.054
els+0.052
cks+0.051
ips+0.050
Neg logit contributions
 barrel-0.029
 hut-0.028
 dark-0.028
 bunny-0.027
 puppy-0.027
Token
Token ID198
Feature activation-5.15e+00

Pos logit contributions
ases+0.201
els+0.194
cks+0.183
olds+0.180
ocol+0.178
Neg logit contributions
 he-0.045
 Bun-0.040
 there-0.038
 little-0.036
 Benny-0.035
Token
Token ID198
Feature activation-4.24e+00

Pos logit contributions
ases+0.173
els+0.164
olds+0.157
cks+0.156
ips+0.150
Neg logit contributions
 Bun-0.066
 he-0.066
 puppy-0.063
 bunny-0.063
 little-0.062
Token started
Token ID2067
Feature activation+3.53e+00

Pos logit contributions
 barrel+0.041
 Bun+0.040
 dark+0.040
 puppy+0.039
 hut+0.039
Neg logit contributions
ases-0.116
els-0.113
olds-0.110
cks-0.106
irs-0.106
Token eating
Token ID6600
Feature activation+1.49e+00

Pos logit contributions
 barrel+0.036
 dark+0.035
 bunny+0.035
 hut+0.035
 puppy+0.035
Neg logit contributions
ases-0.124
olds-0.117
els-0.116
cks-0.113
ips-0.111
Token the
Token ID262
Feature activation-1.48e+00

Pos logit contributions
 barrel+0.018
 dark+0.017
 bunny+0.017
 hut+0.017
 puppy+0.017
Neg logit contributions
ases-0.050
olds-0.047
els-0.046
cks-0.045
ips-0.044
Token delicious
Token ID12625
Feature activation-2.45e-02

Pos logit contributions
ases+0.051
els+0.048
olds+0.048
cks+0.047
ips+0.045
Neg logit contributions
 barrel-0.015
 Bun-0.015
 hut-0.015
 puppy-0.015
 bunny-0.015
Token ch
Token ID442
Feature activation-3.60e+00

Pos logit contributions
ases+0.001
olds+0.001
els+0.001
cks+0.001
ips+0.001
Neg logit contributions
 barrel-0.000
 dark-0.000
 bunny-0.000
 puppy-0.000
 hut-0.000
Tokenocol
Token ID4668
Feature activation-1.52e+01

Pos logit contributions
ases+0.039
cks+0.034
olds+0.033
irs+0.029
rs+0.029
Neg logit contributions
 barrel-0.109
 little-0.108
 seed-0.106
 thief-0.105
 hut-0.104
Tokenates
Token ID689
Feature activation-4.34e-01

Pos logit contributions
olds+0.294
ases+0.284
 humor+0.267
its+0.264
 supervision+0.258
Neg logit contributions
 barrel-0.321
 hut-0.302
 outside-0.300
 seed-0.299
 whole-0.288
Token.
Token ID13
Feature activation+2.35e+00

Pos logit contributions
ases+0.015
els+0.014
olds+0.014
cks+0.013
ips+0.013
Neg logit contributions
 barrel-0.005
 Bun-0.005
 puppy-0.005
 dark-0.005
 bunny-0.005
Token She
Token ID1375
Feature activation+3.19e+00

Pos logit contributions
 puppy+0.027
 dark+0.026
 he+0.026
 there+0.026
 Bun+0.025
Neg logit contributions
ases-0.083
els-0.077
olds-0.074
cks-0.073
ips-0.071
Token was
Token ID373
Feature activation+8.33e-01

Pos logit contributions
 barrel+0.033
 hut+0.031
 puppy+0.031
 dark+0.031
 Bun+0.031
Neg logit contributions
ases-0.110
olds-0.105
els-0.105
cks-0.101
ips-0.099
Token so
Token ID523
Feature activation+1.61e+00

Pos logit contributions
 barrel+0.005
 puppy+0.005
 Bun+0.005
 bunny+0.005
 hut+0.005
Neg logit contributions
ases-0.032
olds-0.031
els-0.031
cks-0.030
ips-0.029
Tokenates
Token ID689
Feature activation+1.27e+00

Pos logit contributions
olds+0.295
ases+0.265
its+0.263
oke+0.248
 humor+0.242
Neg logit contributions
 barrel-0.315
 hut-0.307
 there-0.301
 outside-0.297
 seed-0.293
Token.
Token ID13
Feature activation+2.69e+00

Pos logit contributions
 Bun+0.016
 barrel+0.016
 puppy+0.016
 dark+0.015
 hut+0.015
Neg logit contributions
ases-0.040
els-0.039
olds-0.038
cks-0.037
ips-0.036
Token Lily
Token ID20037
Feature activation-2.32e+00

Pos logit contributions
 barrel+0.032
 puppy+0.032
 dark+0.031
 hut+0.031
 Bun+0.031
Neg logit contributions
ases-0.089
olds-0.085
els-0.082
cks-0.081
ips-0.079
Token loved
Token ID6151
Feature activation+1.92e+00

Pos logit contributions
ases+0.076
els+0.073
olds+0.073
cks+0.070
ips+0.068
Neg logit contributions
 barrel-0.026
 dark-0.026
 puppy-0.026
 Bun-0.025
 hut-0.025
Token ch
Token ID442
Feature activation-4.29e+00

Pos logit contributions
 he+0.027
 bunny+0.027
 barrel+0.027
 puppy+0.027
 dark+0.027
Neg logit contributions
ases-0.060
olds-0.057
els-0.055
cks-0.054
ips-0.054
Tokenocol
Token ID4668
Feature activation-1.52e+01

Pos logit contributions
 supervision+0.052
olds+0.051
ases+0.043
 angles+0.037
irs+0.036
Neg logit contributions
 bunny-0.122
 little-0.120
 he-0.119
 there-0.117
 shield-0.115
Tokenates
Token ID689
Feature activation-1.05e+00

Pos logit contributions
olds+0.321
its+0.286
ases+0.284
 apology+0.277
 supervision+0.274
Neg logit contributions
 barrel-0.292
 there-0.280
 outside-0.278
 hut-0.278
 in-0.276
Token.
Token ID13
Feature activation+2.13e+00

Pos logit contributions
ases+0.034
els+0.033
olds+0.033
cks+0.032
ips+0.031
Neg logit contributions
 barrel-0.013
 Bun-0.012
 puppy-0.012
 hut-0.012
 dark-0.012
Token She
Token ID1375
Feature activation+2.63e+00

Pos logit contributions
 barrel+0.025
 bunny+0.024
 Bun+0.024
 puppy+0.024
 hut+0.023
Neg logit contributions
ases-0.072
olds-0.068
els-0.068
cks-0.066
ips-0.064
Token thanked
Token ID26280
Feature activation-4.25e+00

Pos logit contributions
 barrel+0.032
 puppy+0.030
 dark+0.030
 hut+0.030
 Bun+0.030
Neg logit contributions
ases-0.085
els-0.081
olds-0.080
cks-0.077
its-0.074
Token Ben
Token ID3932
Feature activation-4.96e+00

Pos logit contributions
ases+0.132
olds+0.126
cks+0.121
its+0.120
els+0.119
Neg logit contributions
 bunny-0.071
 he-0.071
 puppy-0.066
 Benny-0.066
 Bun-0.066
Token and
Token ID290
Feature activation+3.94e+00

Pos logit contributions
 Bun+0.041
 bunny+0.040
 puppy+0.040
 barrel+0.040
 hut+0.039
Neg logit contributions
ases-0.090
olds-0.085
els-0.085
cks-0.081
ips-0.081
Token started
Token ID2067
Feature activation+3.79e+00

Pos logit contributions
 barrel+0.051
 Bun+0.051
 wolf+0.051
 hut+0.050
 hunter+0.050
Neg logit contributions
ases-0.109
olds-0.108
els-0.108
cks-0.100
irs-0.099
Token eating
Token ID6600
Feature activation+1.57e+00

Pos logit contributions
 barrel+0.040
 puppy+0.039
 bunny+0.039
 Bun+0.039
 dark+0.038
Neg logit contributions
ases-0.132
olds-0.125
els-0.124
cks-0.120
ips-0.118
Token the
Token ID262
Feature activation-9.08e-01

Pos logit contributions
 Bun+0.020
 barrel+0.020
 puppy+0.020
 bunny+0.019
 hut+0.019
Neg logit contributions
ases-0.050
els-0.048
olds-0.048
cks-0.046
ips-0.045
Token ch
Token ID442
Feature activation-3.05e+00

Pos logit contributions
els+0.024
olds+0.024
ases+0.023
its+0.022
ocol+0.021
Neg logit contributions
 Bun-0.013
 accidentally-0.013
 hunter-0.013
 shield-0.012
 wolf-0.012
Tokenocol
Token ID4668
Feature activation-1.51e+01

Pos logit contributions
ases+0.029
olds+0.026
cks+0.025
els+0.021
irs+0.021
Neg logit contributions
 barrel-0.100
 little-0.098
 bunny-0.098
 hut-0.097
 dark-0.097
Tokenates
Token ID689
Feature activation+3.93e-01

Pos logit contributions
olds+0.312
ases+0.294
its+0.282
 supervision+0.278
 humor+0.277
Neg logit contributions
 barrel-0.297
 seed-0.280
 hut-0.278
 whole-0.272
 outside-0.270
Token.
Token ID13
Feature activation+2.46e+00

Pos logit contributions
 Bun+0.005
 barrel+0.005
 puppy+0.004
 dark+0.004
 hut+0.004
Neg logit contributions
ases-0.013
els-0.012
olds-0.012
cks-0.012
ips-0.012
Token The
Token ID383
Feature activation-2.15e-01

Pos logit contributions
 barrel+0.030
 hut+0.029
 dark+0.029
 shield+0.028
 bunny+0.028
Neg logit contributions
ases-0.078
olds-0.077
els-0.072
ips-0.071
cks-0.070
Token shop
Token ID6128
Feature activation+1.28e+00

Pos logit contributions
ases+0.006
olds+0.006
els+0.006
ips+0.005
cks+0.005
Neg logit contributions
 Bun-0.004
 barrel-0.004
 hut-0.003
 dark-0.003
 shield-0.003
Tokenkeeper
Token ID13884
Feature activation-6.66e-01

Pos logit contributions
 barrel+0.018
 Bun+0.018
 dark+0.018
 hut+0.018
 bunny+0.018
Neg logit contributions
ases-0.038
olds-0.037
els-0.036
cks-0.034
ips-0.034
Token wear
Token ID5806
Feature activation+2.52e+00

Pos logit contributions
 barrel+0.000
 puppy+0.000
 bunny+0.000
 dark+0.000
 Bun+0.000
Neg logit contributions
ases-0.001
olds-0.001
els-0.001
cks-0.001
ips-0.001
Token her
Token ID607
Feature activation+1.71e+00

Pos logit contributions
 barrel+0.045
 hut+0.043
 hunter+0.041
 thief+0.041
 cabin+0.040
Neg logit contributions
ases-0.067
els-0.065
olds-0.062
cks-0.061
irs-0.060
Token new
Token ID649
Feature activation+2.70e+00

Pos logit contributions
 barrel+0.021
 Bun+0.021
 hunter+0.020
 hut+0.020
 thief+0.019
Neg logit contributions
els-0.051
ases-0.051
olds-0.048
ips-0.047
cks-0.046
Token jacket
Token ID15224
Feature activation+3.00e+00

Pos logit contributions
 barrel+0.042
 Bun+0.042
 he+0.042
 hunter+0.040
 hut+0.040
Neg logit contributions
ases-0.075
els-0.073
olds-0.069
ips-0.066
cks-0.064
Token to
Token ID284
Feature activation-6.96e-01

Pos logit contributions
 barrel+0.044
 hut+0.043
 hunter+0.040
 wolf+0.040
 dark+0.040
Neg logit contributions
ases-0.085
els-0.082
olds-0.081
ips-0.079
ums-0.073
Token school
Token ID1524
Feature activation+6.28e+00

Pos logit contributions
ases+0.021
olds+0.020
els+0.020
cks+0.020
ips+0.019
Neg logit contributions
 dark-0.010
 he-0.010
 puppy-0.010
 Bun-0.010
 bunny-0.010
Token.
Token ID13
Feature activation+3.99e+00

Pos logit contributions
 barrel+0.095
 hut+0.088
 wolf+0.087
 bunny+0.085
 Bun+0.084
Neg logit contributions
ases-0.191
olds-0.182
els-0.180
ips-0.174
cks-0.165
Token It
Token ID632
Feature activation+4.15e+00

Pos logit contributions
 barrel+0.055
 bunny+0.053
 puppy+0.053
 Bun+0.053
 hut+0.053
Neg logit contributions
ases-0.126
olds-0.118
els-0.117
cks-0.113
ips-0.111
Token was
Token ID373
Feature activation+2.61e+00

Pos logit contributions
 barrel+0.056
 hut+0.053
 thief+0.049
 puppy+0.048
 hunter+0.047
Neg logit contributions
ases-0.125
olds-0.119
els-0.118
ips-0.113
its-0.112
Token pink
Token ID11398
Feature activation+1.79e+00

Pos logit contributions
 barrel+0.025
 hut+0.023
 bunny+0.022
 puppy+0.021
 Bun+0.021
Neg logit contributions
ases-0.092
olds-0.088
els-0.088
cks-0.084
ips-0.084
Token and
Token ID290
Feature activation+4.18e+00

Pos logit contributions
 barrel+0.033
 hunter+0.033
 Bun+0.032
 wolf+0.032
 hut+0.031
Neg logit contributions
ases-0.044
els-0.042
ips-0.040
olds-0.040
rs-0.037
Token.
Token ID13
Feature activation+2.19e+00

Pos logit contributions
 puppy+0.013
 dark+0.013
 barrel+0.013
 cabin+0.013
 wolf+0.013
Neg logit contributions
ases-0.030
olds-0.028
els-0.027
cks-0.027
ips-0.026
Token<|endoftext|>
Token ID50256
Feature activation+1.99e+00

Pos logit contributions
 barrel+0.033
 dark+0.033
 hut+0.033
 shield+0.032
 puppy+0.032
Neg logit contributions
ases-0.064
olds-0.061
els-0.058
cks-0.058
ips-0.056
TokenOne
Token ID3198
Feature activation+2.14e+00

Pos logit contributions
 barrel+0.025
 Bun+0.025
 dark+0.025
 bunny+0.024
 puppy+0.024
Neg logit contributions
ases-0.065
olds-0.061
els-0.061
cks-0.059
ips-0.057
Token day
Token ID1110
Feature activation+5.60e+00

Pos logit contributions
 Bun+0.023
 barrel+0.023
 puppy+0.022
 hut+0.021
 bunny+0.021
Neg logit contributions
ases-0.072
olds-0.069
els-0.066
cks-0.066
ips-0.064
Token,
Token ID11
Feature activation+3.75e+00

Pos logit contributions
 barrel+0.074
 puppy+0.072
 hut+0.071
 bunny+0.071
 Bun+0.070
Neg logit contributions
ases-0.178
olds-0.167
els-0.166
cks-0.161
ips-0.159
Token a
Token ID257
Feature activation+1.03e+01

Pos logit contributions
 vest+0.038
 shield+0.038
 superhero+0.038
 barrel+0.036
 cabin+0.036
Neg logit contributions
ases-0.126
cks-0.119
els-0.116
olds-0.115
ips-0.110
Token sm
Token ID895
Feature activation+2.50e+00

Pos logit contributions
 barrel+0.096
 Bun+0.094
 hut+0.090
 cabin+0.086
 decided+0.084
Neg logit contributions
ases-0.297
olds-0.284
oke-0.283
els-0.265
cks-0.263
Tokenelly
Token ID6148
Feature activation+7.31e+00

Pos logit contributions
 barrel+0.056
 Bun+0.055
 bunny+0.055
 puppy+0.055
 hut+0.055
Neg logit contributions
ases-0.058
olds-0.053
els-0.051
cks-0.049
ips-0.048
Token cat
Token ID3797
Feature activation+3.85e+00

Pos logit contributions
 Bun+0.090
There+0.089
 While+0.088
 deserted+0.087
Under+0.086
Neg logit contributions
ases-0.197
els-0.187
olds-0.185
ocol-0.176
oke-0.173
Token named
Token ID3706
Feature activation+3.03e+00

Pos logit contributions
 ju+0.066
 perfect+0.066
 cozy+0.066
 brightly+0.064
 bicycle+0.064
Neg logit contributions
ases-0.105
olds-0.094
els-0.093
cks-0.090
rs-0.082
Token Tom
Token ID4186
Feature activation-1.24e+00

Pos logit contributions
 hut+0.053
 cabin+0.052
 barrel+0.052
 shield+0.052
 bicycle+0.051
Neg logit contributions
ases-0.081
olds-0.074
cks-0.073
els-0.072
irs-0.068
Token.
Token ID13
Feature activation+5.60e+00

Pos logit contributions
 Bun+0.082
 cozy+0.080
 thief+0.079
 dark+0.079
 puppy+0.078
Neg logit contributions
ases-0.122
els-0.115
olds-0.111
cks-0.110
ums-0.100
Token He
Token ID679
Feature activation+4.52e+00

Pos logit contributions
 barrel+0.074
 puppy+0.072
 hut+0.072
 bunny+0.071
 Bun+0.070
Neg logit contributions
ases-0.180
olds-0.168
els-0.166
cks-0.162
ips-0.157
Token was
Token ID373
Feature activation+3.76e+00

Pos logit contributions
 hut+0.063
 puppy+0.060
 cabin+0.059
 barrel+0.059
 thief+0.057
Neg logit contributions
ases-0.140
cks-0.133
els-0.130
its-0.124
olds-0.124
Token a
Token ID257
Feature activation+8.21e+00

Pos logit contributions
 barrel+0.038
 hut+0.036
 puppy+0.033
 cabin+0.033
 Bun+0.033
Neg logit contributions
ases-0.129
cks-0.123
olds-0.122
els-0.121
ips-0.114
Token very
Token ID845
Feature activation+6.99e+00

Pos logit contributions
 Bun+0.111
 barrel+0.099
 hut+0.097
 cabin+0.094
 decided+0.090
Neg logit contributions
ases-0.196
olds-0.180
 humor-0.179
oke-0.178
ums-0.176
Token charming
Token ID23332
Feature activation+6.48e+00

Pos logit contributions
 Bun+0.088
 puppy+0.085
 hut+0.079
 cabin+0.079
 barrel+0.077
Neg logit contributions
ases-0.228
olds-0.218
cks-0.207
els-0.204
its-0.202
Token triangle
Token ID22950
Feature activation+4.40e+00

Pos logit contributions
 Bun+0.123
 Bug+0.116
 hut+0.116
 cabin+0.116
 barrel+0.113
Neg logit contributions
ases-0.148
els-0.130
olds-0.125
ums-0.121
 angles-0.118
Token,
Token ID11
Feature activation+3.04e+00

Pos logit contributions
 Bun+0.081
 puppy+0.077
 dark+0.077
 thief+0.077
 hut+0.076
Neg logit contributions
ases-0.110
els-0.101
olds-0.096
cks-0.095
ips-0.088
Token and
Token ID290
Feature activation+5.68e+00

Pos logit contributions
 hut+0.047
 barrel+0.045
 puppy+0.044
 cabin+0.044
 thief+0.044
Neg logit contributions
ases-0.080
cks-0.080
olds-0.074
els-0.074
its-0.069
Token he
Token ID339
Feature activation+2.92e+00

Pos logit contributions
 hut+0.073
 cabin+0.065
 barrel+0.062
 puppy+0.061
 thief+0.057
Neg logit contributions
ases-0.173
olds-0.168
els-0.166
cks-0.163
ks-0.150
Token loved
Token ID6151
Feature activation+5.05e+00

Pos logit contributions
 hut+0.041
 barrel+0.039
 puppy+0.038
 cabin+0.037
 thief+0.036
Neg logit contributions
ases-0.090
els-0.083
cks-0.083
olds-0.083
its-0.078
Token the
Token ID262
Feature activation-1.28e+00

Pos logit contributions
 Bun+0.005
 there+0.005
 dark+0.005
 he+0.005
 bunny+0.005
Neg logit contributions
ases-0.016
olds-0.015
cks-0.014
els-0.014
irs-0.014
Token key
Token ID1994
Feature activation+9.63e-01

Pos logit contributions
els+0.037
ases+0.037
olds+0.036
cks+0.034
its+0.034
Neg logit contributions
 Bun-0.019
 Benny-0.018
 he-0.017
 barrel-0.017
 bunny-0.017
Token and
Token ID290
Feature activation+2.20e+00

Pos logit contributions
 barrel+0.011
 puppy+0.011
 bunny+0.011
 Bun+0.011
 hut+0.011
Neg logit contributions
ases-0.032
olds-0.030
els-0.030
cks-0.029
ips-0.029
Token it
Token ID340
Feature activation+2.25e+00

Pos logit contributions
 barrel+0.029
 puppy+0.028
 hut+0.028
 bunny+0.027
 cabin+0.027
Neg logit contributions
ases-0.070
olds-0.065
els-0.065
cks-0.063
ips-0.061
Token made
Token ID925
Feature activation-1.09e+00

Pos logit contributions
 barrel+0.024
 puppy+0.024
 hut+0.023
 bunny+0.023
 dark+0.022
Neg logit contributions
ases-0.077
els-0.073
olds-0.072
cks-0.070
ips-0.069
Token a
Token ID257
Feature activation+4.40e+00

Pos logit contributions
ases+0.036
olds+0.033
els+0.033
cks+0.032
ips+0.031
Neg logit contributions
 barrel-0.014
 puppy-0.014
 bunny-0.013
 hut-0.013
 Bun-0.013
Token '
Token ID705
Feature activation-2.56e+00

Pos logit contributions
 barrel+0.052
 Bun+0.052
 he+0.051
 there+0.051
 Benny+0.049
Neg logit contributions
ases-0.127
olds-0.123
its-0.121
cks-0.120
els-0.119
Tokenclick
Token ID12976
Feature activation-1.44e+00

Pos logit contributions
ases+0.071
olds+0.066
els+0.066
cks+0.064
ips+0.062
Neg logit contributions
 barrel-0.044
 puppy-0.043
 bunny-0.043
 dark-0.043
 Bun-0.043
Token'
Token ID6
Feature activation-1.56e+00

Pos logit contributions
ases+0.039
olds+0.036
els+0.036
cks+0.034
ips+0.034
Neg logit contributions
 barrel-0.027
 hut-0.026
 dark-0.026
 bunny-0.025
 puppy-0.025
Token sound
Token ID2128
Feature activation+1.72e+00

Pos logit contributions
ases+0.046
olds+0.044
els+0.043
its+0.041
cks+0.041
Neg logit contributions
 barrel-0.024
 hut-0.023
 bunny-0.023
 puppy-0.023
 cabin-0.022
Token.
Token ID13
Feature activation+3.02e+00

Pos logit contributions
 barrel+0.026
 hut+0.024
 Bun+0.024
 puppy+0.024
 bunny+0.024
Neg logit contributions
ases-0.052
olds-0.049
els-0.048
cks-0.047
its-0.046
Token playing
Token ID2712
Feature activation+3.46e+00

Pos logit contributions
 puppy+0.025
 bunny+0.024
 Bun+0.024
 barrel+0.023
 hut+0.023
Neg logit contributions
ases-0.036
olds-0.034
els-0.034
cks-0.033
ips-0.032
Token,
Token ID11
Feature activation+1.96e+00

Pos logit contributions
 puppy+0.054
 Bun+0.051
 bunny+0.050
 wolf+0.047
 hut+0.046
Neg logit contributions
ases-0.103
els-0.094
olds-0.094
ips-0.091
cks-0.089
Token he
Token ID339
Feature activation+3.20e+00

Pos logit contributions
 hut+0.022
 bicycle+0.021
 barrel+0.020
case+0.020
 wagon+0.019
Neg logit contributions
ases-0.052
els-0.050
olds-0.050
irs-0.049
ocol-0.047
Token saw
Token ID2497
Feature activation+1.42e+00

Pos logit contributions
 puppy+0.046
 Bun+0.044
 bicycle+0.044
 hut+0.042
 bunny+0.042
Neg logit contributions
ases-0.094
els-0.091
olds-0.086
cks-0.084
ks-0.082
Token a
Token ID257
Feature activation+6.94e+00

Pos logit contributions
 Bun+0.014
 hut+0.014
 puppy+0.014
 bunny+0.014
 cabin+0.014
Neg logit contributions
ases-0.048
olds-0.046
els-0.044
cks-0.042
its-0.040
Token silly
Token ID14397
Feature activation+6.05e+00

Pos logit contributions
 Bun+0.088
 While+0.070
 Bug+0.070
 Benny+0.070
 he+0.064
Neg logit contributions
ases-0.188
olds-0.188
els-0.187
oke-0.183
its-0.182
Token crab
Token ID32202
Feature activation+1.99e+00

Pos logit contributions
 Bun+0.082
 hut+0.071
 cozy+0.070
 While+0.070
 cabin+0.069
Neg logit contributions
ases-0.171
els-0.164
olds-0.160
its-0.157
cks-0.152
Token near
Token ID1474
Feature activation-5.15e-01

Pos logit contributions
 Bun+0.030
 cozy+0.028
 dark+0.028
 puppy+0.028
 barrel+0.027
Neg logit contributions
ases-0.059
els-0.056
cks-0.055
olds-0.054
its-0.051
Token the
Token ID262
Feature activation+4.11e-01

Pos logit contributions
ases+0.017
olds+0.016
els+0.016
ips+0.016
cks+0.016
Neg logit contributions
 barrel-0.006
 dark-0.006
 puppy-0.006
 he-0.006
 bunny-0.006
Token sand
Token ID6450
Feature activation+2.75e+00

Pos logit contributions
 Bun+0.007
 puppy+0.006
 Benny+0.006
 bunny+0.006
 Bug+0.006
Neg logit contributions
ases-0.011
els-0.010
olds-0.010
cks-0.010
its-0.009
Token.
Token ID13
Feature activation+2.70e+00

Pos logit contributions
 Bun+0.034
 puppy+0.034
 barrel+0.033
 bunny+0.033
 dark+0.033
Neg logit contributions
ases-0.090
els-0.085
olds-0.084
cks-0.082
ips-0.080
Token either
Token ID2035
Feature activation-7.06e-01

Pos logit contributions
ases+0.017
olds+0.016
cks+0.015
ips+0.015
els+0.015
Neg logit contributions
 there-0.005
 he-0.005
 dark-0.004
 Bun-0.004
 bunny-0.004
Token.
Token ID13
Feature activation+1.88e+00

Pos logit contributions
ases+0.029
cks+0.027
ips+0.026
olds+0.026
irs+0.026
Neg logit contributions
 he-0.004
 dark-0.004
 puppy-0.004
 there-0.004
 bunny-0.004
Token Lily
Token ID20037
Feature activation-2.37e+00

Pos logit contributions
 shield+0.031
 barrel+0.030
 hunter+0.030
 hut+0.029
 cabin+0.029
Neg logit contributions
olds-0.053
ases-0.052
els-0.049
ips-0.047
rs-0.046
Token decided
Token ID3066
Feature activation+4.28e+00

Pos logit contributions
ases+0.072
els+0.070
olds+0.070
its+0.065
cks+0.065
Neg logit contributions
 barrel-0.032
 hut-0.032
 cabin-0.031
 dark-0.030
 Bun-0.029
Token to
Token ID284
Feature activation-2.19e+00

Pos logit contributions
 barrel+0.069
 cabin+0.068
 hut+0.067
 bunny+0.061
 shield+0.061
Neg logit contributions
olds-0.121
ases-0.115
els-0.111
 supervision-0.103
cks-0.103
Token touch
Token ID3638
Feature activation-5.50e-01

Pos logit contributions
ases+0.060
olds+0.056
els+0.055
cks+0.053
ips+0.052
Neg logit contributions
 barrel-0.039
 dark-0.038
 puppy-0.038
 Bun-0.038
 bunny-0.038
Token it
Token ID340
Feature activation+1.09e+00

Pos logit contributions
ases+0.022
olds+0.021
cks+0.020
ips+0.020
its+0.019
Neg logit contributions
 dark-0.004
 there-0.004
 he-0.004
 bunny-0.004
 puppy-0.004
Token to
Token ID284
Feature activation-2.80e+00

Pos logit contributions
 barrel+0.015
 puppy+0.015
 hut+0.015
 Bun+0.014
 cabin+0.014
Neg logit contributions
ases-0.033
els-0.032
olds-0.031
cks-0.030
ips-0.029
Token see
Token ID766
Feature activation-4.19e-01

Pos logit contributions
ases+0.090
ips+0.085
els+0.084
olds+0.084
cks+0.080
Neg logit contributions
 dark-0.042
 he-0.042
 little-0.040
 bunny-0.039
 a-0.039
Token what
Token ID644
Feature activation+2.01e+00

Pos logit contributions
ases+0.013
olds+0.012
ips+0.012
els+0.012
cks+0.012
Neg logit contributions
 bunny-0.006
 puppy-0.006
 there-0.006
 he-0.006
 dark-0.006
Token it
Token ID340
Feature activation+9.36e-01

Pos logit contributions
 barrel+0.020
 hut+0.019
 Bun+0.019
 puppy+0.019
 bunny+0.019
Neg logit contributions
ases-0.070
els-0.067
olds-0.066
cks-0.064
ips-0.062
Token.
Token ID13
Feature activation+1.89e+00

Pos logit contributions
 barrel+0.023
 Bun+0.022
 hut+0.022
 dark+0.022
 puppy+0.021
Neg logit contributions
ases-0.043
olds-0.041
els-0.040
ips-0.038
cks-0.038
Token<|endoftext|>
Token ID50256
Feature activation+6.29e-01

Pos logit contributions
 Bun+0.023
 barrel+0.023
 he+0.023
 puppy+0.023
 bunny+0.023
Neg logit contributions
ases-0.063
els-0.060
olds-0.058
cks-0.058
ips-0.055
TokenOnce
Token ID7454
Feature activation+2.05e-01

Pos logit contributions
 barrel+0.010
 puppy+0.009
 hut+0.009
 dark+0.009
 bunny+0.009
Neg logit contributions
ases-0.019
olds-0.017
els-0.017
cks-0.017
ips-0.017
Token upon
Token ID2402
Feature activation+3.60e+00

Pos logit contributions
 he+0.002
 dark+0.002
 there+0.002
 barrel+0.002
 hut+0.002
Neg logit contributions
ases-0.007
els-0.007
olds-0.007
cks-0.006
ips-0.006
Token a
Token ID257
Feature activation+7.00e+00

Pos logit contributions
 barrel+0.062
 wagon+0.053
 cabin+0.053
 miner+0.053
 hut+0.052
Neg logit contributions
ases-0.097
olds-0.091
cks-0.091
its-0.087
ks-0.085
Token time
Token ID640
Feature activation+4.12e+00

Pos logit contributions
 barrel+0.099
 puppy+0.096
 bunny+0.096
 Bun+0.096
 hut+0.095
Neg logit contributions
ases-0.217
olds-0.204
els-0.202
cks-0.196
ips-0.191
Token there
Token ID612
Feature activation+4.23e+00

Pos logit contributions
 he+0.039
 barrel+0.038
 there+0.038
 Bun+0.038
 dark+0.038
Neg logit contributions
ases-0.151
els-0.142
olds-0.142
cks-0.138
ips-0.135
Token was
Token ID373
Feature activation+5.18e+00

Pos logit contributions
 barrel+0.029
 bunny+0.027
 puppy+0.027
 dark+0.027
 Bun+0.027
Neg logit contributions
ases-0.163
olds-0.155
els-0.154
cks-0.150
ips-0.147
Token a
Token ID257
Feature activation+9.81e+00

Pos logit contributions
 barrel+0.064
 bicycle+0.059
 cabin+0.057
 thief+0.055
 hunter+0.054
Neg logit contributions
ases-0.168
els-0.152
cks-0.151
olds-0.149
irs-0.148
Token hungry
Token ID14720
Feature activation+7.07e+00

Pos logit contributions
 barrel+0.097
 Bun+0.096
 he+0.093
case+0.088
 buried+0.085
Neg logit contributions
oke-0.252
ases-0.245
els-0.236
olds-0.236
avi-0.235
Token girl
Token ID2576
Feature activation+3.27e+00

Pos logit contributions
 Bun+0.075
 lost+0.070
 accidentally+0.070
 there+0.066
 dark+0.065
Neg logit contributions
ases-0.207
els-0.199
olds-0.198
oke-0.192
ocol-0.188
Token them
Token ID606
Feature activation-1.43e+00

Pos logit contributions
ases+0.004
olds+0.004
els+0.004
cks+0.003
ips+0.003
Neg logit contributions
 he-0.002
 bunny-0.002
 dark-0.002
 barrel-0.002
 puppy-0.002
Token.
Token ID13
Feature activation+1.69e+00

Pos logit contributions
ases+0.046
els+0.044
olds+0.044
cks+0.042
ips+0.041
Neg logit contributions
 barrel-0.018
 puppy-0.017
 Bun-0.017
 hut-0.017
 bunny-0.016
Token It
Token ID632
Feature activation+2.23e+00

Pos logit contributions
 barrel+0.025
 hut+0.024
 shield+0.023
 cabin+0.023
 dark+0.023
Neg logit contributions
ases-0.051
olds-0.049
els-0.046
ips-0.046
cks-0.045
Token was
Token ID373
Feature activation+2.28e-01

Pos logit contributions
 barrel+0.030
 bicycle+0.029
 cabin+0.028
 hut+0.028
 puppy+0.027
Neg logit contributions
ases-0.067
els-0.064
cks-0.064
olds-0.062
its-0.061
Token so
Token ID523
Feature activation+7.11e-01

Pos logit contributions
 barrel+0.002
 puppy+0.002
 Bun+0.002
 hut+0.002
 bunny+0.002
Neg logit contributions
ases-0.009
olds-0.008
els-0.008
cks-0.008
ips-0.008
Token happy
Token ID3772
Feature activation+2.28e+00

Pos logit contributions
 barrel+0.006
 puppy+0.006
 Bun+0.006
 bunny+0.006
 hut+0.006
Neg logit contributions
ases-0.026
olds-0.025
els-0.025
cks-0.024
ips-0.023
Token that
Token ID326
Feature activation+8.65e-01

Pos logit contributions
 barrel+0.033
 hut+0.032
 cabin+0.031
 shield+0.031
 bicycle+0.031
Neg logit contributions
ases-0.069
olds-0.066
els-0.064
cks-0.062
ips-0.061
Token it
Token ID340
Feature activation-6.76e-02

Pos logit contributions
 barrel+0.008
 puppy+0.008
 bunny+0.008
 dark+0.008
 Bun+0.008
Neg logit contributions
ases-0.031
olds-0.030
els-0.029
cks-0.029
ips-0.028
Token started
Token ID2067
Feature activation+2.48e+00

Pos logit contributions
ases+0.002
els+0.002
cks+0.002
olds+0.002
its+0.002
Neg logit contributions
 bicycle-0.001
 barrel-0.001
 hut-0.001
 cabin-0.001
 dark-0.001
Token to
Token ID284
Feature activation-2.83e+00

Pos logit contributions
 dark+0.018
 barrel+0.018
 bunny+0.018
 puppy+0.017
 Bun+0.017
Neg logit contributions
ases-0.094
els-0.089
olds-0.089
cks-0.087
ips-0.085
Token sing
Token ID1702
Feature activation-9.51e-01

Pos logit contributions
ases+0.088
olds+0.082
els+0.082
cks+0.080
ips+0.077
Neg logit contributions
 barrel-0.041
 puppy-0.039
 bunny-0.039
 Bun-0.039
 hut-0.039
TokenYes
Token ID5297
Feature activation-3.93e+00

Pos logit contributions
ases+0.078
els+0.073
olds+0.073
cks+0.071
ips+0.069
Neg logit contributions
 barrel-0.031
 bunny-0.031
 puppy-0.031
 dark-0.031
 Bun-0.030
Token,
Token ID11
Feature activation-3.53e+00

Pos logit contributions
ases+0.131
olds+0.124
els+0.123
cks+0.119
ips+0.117
Neg logit contributions
 barrel-0.048
 puppy-0.046
 bunny-0.046
 hut-0.045
 Bun-0.045
Token please
Token ID3387
Feature activation-4.12e+00

Pos logit contributions
ases+0.102
olds+0.098
els+0.096
cks+0.090
its+0.088
Neg logit contributions
 barrel-0.054
 Bun-0.052
 hut-0.052
 dark-0.051
 cabin-0.050
Token.
Token ID13
Feature activation+1.33e+00

Pos logit contributions
ases+0.136
olds+0.129
els+0.127
cks+0.124
ips+0.120
Neg logit contributions
 barrel-0.051
 Bun-0.049
 puppy-0.049
 hut-0.049
 bunny-0.049
Token Milk
Token ID24796
Feature activation-1.33e+00

Pos logit contributions
 barrel+0.019
 dark+0.018
 hut+0.018
 puppy+0.018
 Bun+0.018
Neg logit contributions
ases-0.041
olds-0.039
els-0.038
cks-0.037
ips-0.037
Token makes
Token ID1838
Feature activation-2.23e+00

Pos logit contributions
ases+0.036
olds+0.034
els+0.034
cks+0.033
ips+0.032
Neg logit contributions
 barrel-0.023
 bunny-0.023
 puppy-0.023
 dark-0.023
 Bun-0.023
Token cereal
Token ID33158
Feature activation-4.58e-02

Pos logit contributions
ases+0.071
olds+0.067
els+0.065
cks+0.064
ips+0.063
Neg logit contributions
 bunny-0.031
 dark-0.031
 Bun-0.031
 puppy-0.030
 barrel-0.030
Token y
Token ID331
Feature activation-5.54e+00

Pos logit contributions
ases+0.001
olds+0.001
els+0.001
cks+0.001
its+0.001
Neg logit contributions
 barrel-0.001
 puppy-0.001
 Bun-0.001
 bunny-0.001
 dark-0.001
Tokenummy
Token ID13513
Feature activation-1.13e+00

Pos logit contributions
ases+0.147
olds+0.140
cks+0.135
els+0.134
ips+0.126
Neg logit contributions
 barrel-0.101
 dark-0.100
 hut-0.098
 bunny-0.097
 Bun-0.097
Token,"
Token ID553
Feature activation-3.54e+00

Pos logit contributions
ases+0.034
els+0.033
olds+0.033
cks+0.031
its+0.031
Neg logit contributions
 barrel-0.016
 Bun-0.015
 puppy-0.015
 hunter-0.014
 thief-0.014
Token Lily
Token ID20037
Feature activation-4.89e+00

Pos logit contributions
ases+0.129
olds+0.122
els+0.121
cks+0.119
ips+0.116
Neg logit contributions
 barrel-0.032
 bunny-0.032
 puppy-0.032
 Bun-0.031
 dark-0.031
Token it
Token ID340
Feature activation+9.62e-01

Pos logit contributions
ases+0.031
olds+0.029
els+0.029
cks+0.028
ips+0.028
Neg logit contributions
 barrel-0.015
 bunny-0.014
 dark-0.014
 puppy-0.014
 Bun-0.014
Token pop
Token ID1461
Feature activation-1.61e+00

Pos logit contributions
 barrel+0.011
 Bun+0.011
 puppy+0.011
 bunny+0.010
 hut+0.010
Neg logit contributions
ases-0.032
olds-0.030
cks-0.030
els-0.030
its-0.029
Token in
Token ID287
Feature activation-1.84e+00

Pos logit contributions
ases+0.055
els+0.052
olds+0.051
cks+0.050
ips+0.049
Neg logit contributions
 barrel-0.018
 Bun-0.017
 puppy-0.017
 bunny-0.017
 hut-0.017
Token the
Token ID262
Feature activation+1.65e+00

Pos logit contributions
ases+0.062
olds+0.059
els+0.057
cks+0.055
ips+0.055
Neg logit contributions
 dark-0.023
 barrel-0.022
 hut-0.022
 puppy-0.022
 bunny-0.022
Token big
Token ID1263
Feature activation+2.11e+00

Pos logit contributions
 Bun+0.026
 puppy+0.023
 he+0.023
 bunny+0.022
 Benny+0.022
Neg logit contributions
ases-0.051
olds-0.047
els-0.046
cks-0.045
ips-0.045
Token pot
Token ID1787
Feature activation+1.47e+00

Pos logit contributions
 Bun+0.028
 barrel+0.027
 puppy+0.027
 bunny+0.027
 hut+0.026
Neg logit contributions
ases-0.067
els-0.062
olds-0.062
cks-0.060
ips-0.059
Token.
Token ID13
Feature activation+3.27e+00

Pos logit contributions
 Bun+0.017
 barrel+0.017
 puppy+0.017
 bunny+0.016
 dark+0.016
Neg logit contributions
ases-0.049
olds-0.046
els-0.046
cks-0.045
ips-0.044
Token They
Token ID1119
Feature activation+2.72e+00

Pos logit contributions
 dark+0.038
 he+0.036
 barrel+0.036
 there+0.035
 little+0.033
Neg logit contributions
ases-0.112
els-0.107
olds-0.104
cks-0.103
irs-0.100
Token also
Token ID635
Feature activation+2.32e+00

Pos logit contributions
 barrel+0.047
 Bun+0.047
 puppy+0.047
 hut+0.046
 bunny+0.045
Neg logit contributions
ases-0.075
els-0.070
olds-0.069
cks-0.067
its-0.064
Token like
Token ID588
Feature activation+3.39e+00

Pos logit contributions
 dark+0.034
 barrel+0.033
 bunny+0.033
 he+0.032
 puppy+0.032
Neg logit contributions
ases-0.072
els-0.067
olds-0.067
cks-0.064
ips-0.064
Token to
Token ID284
Feature activation-6.16e-01

Pos logit contributions
 barrel+0.040
 Bun+0.039
 hut+0.037
 puppy+0.037
 dark+0.037
Neg logit contributions
ases-0.113
olds-0.108
els-0.105
cks-0.103
ips-0.100
Token herself
Token ID5223
Feature activation+7.24e-01

Pos logit contributions
ases+0.145
olds+0.133
els+0.133
cks+0.129
ips+0.127
Neg logit contributions
 he-0.081
 there-0.076
 Bun-0.075
 dark-0.075
 puppy-0.074
Token.
Token ID13
Feature activation+2.18e+00

Pos logit contributions
 barrel+0.012
 dark+0.011
 Bun+0.011
 hut+0.011
 cabin+0.011
Neg logit contributions
ases-0.020
olds-0.019
els-0.019
cks-0.017
ips-0.017
Token She
Token ID1375
Feature activation+2.62e+00

Pos logit contributions
 barrel+0.031
 dark+0.030
 hut+0.030
 bunny+0.030
 puppy+0.030
Neg logit contributions
ases-0.067
olds-0.064
els-0.062
cks-0.060
ips-0.059
Token was
Token ID373
Feature activation+6.56e-01

Pos logit contributions
 barrel+0.032
 hut+0.030
 dark+0.030
 Bun+0.029
 puppy+0.029
Neg logit contributions
ases-0.087
olds-0.082
els-0.081
cks-0.079
ips-0.077
Token excited
Token ID6568
Feature activation+2.00e+00

Pos logit contributions
 barrel+0.007
 hut+0.006
 puppy+0.006
 Bun+0.006
 bunny+0.006
Neg logit contributions
ases-0.023
olds-0.022
els-0.022
cks-0.021
ips-0.021
Token to
Token ID284
Feature activation-3.04e+00

Pos logit contributions
 barrel+0.025
 hut+0.023
 Bun+0.023
 bunny+0.023
 puppy+0.022
Neg logit contributions
ases-0.065
olds-0.063
els-0.061
cks-0.059
ips-0.058
Token show
Token ID905
Feature activation-5.28e-01

Pos logit contributions
ases+0.089
olds+0.083
els+0.083
cks+0.081
ips+0.079
Neg logit contributions
 he-0.048
 bunny-0.048
 puppy-0.048
 dark-0.048
 barrel-0.047
Token the
Token ID262
Feature activation-2.07e+00

Pos logit contributions
ases+0.017
cks+0.016
els+0.016
olds+0.016
ips+0.015
Neg logit contributions
 he-0.007
 puppy-0.007
 Bun-0.007
 little-0.007
 bunny-0.007
Token stranger
Token ID16195
Feature activation+7.50e-02

Pos logit contributions
ases+0.062
olds+0.061
els+0.060
its+0.056
irs+0.054
Neg logit contributions
 Bun-0.027
 barrel-0.025
 hut-0.025
 he-0.024
 accidentally-0.023
Token what
Token ID644
Feature activation+1.55e+00

Pos logit contributions
 barrel+0.001
 dark+0.001
 Bun+0.001
 hut+0.001
 bunny+0.001
Neg logit contributions
ases-0.002
olds-0.002
els-0.002
cks-0.002
ips-0.002
Token she
Token ID673
Feature activation+5.92e-01

Pos logit contributions
 barrel+0.015
 hut+0.014
 Bun+0.014
 bunny+0.014
 dark+0.014
Neg logit contributions
ases-0.054
olds-0.052
els-0.051
cks-0.049
ips-0.048
Token
Token ID198
Feature activation-6.07e+00

Pos logit contributions
ases+0.068
els+0.064
olds+0.063
cks+0.063
ips+0.060
Neg logit contributions
 dark-0.023
 Bun-0.023
 barrel-0.023
 puppy-0.023
 bunny-0.023
Token
Token ID198
Feature activation-5.17e+00

Pos logit contributions
ases+0.224
els+0.214
olds+0.205
cks+0.204
ips+0.204
Neg logit contributions
 Bun-0.060
 he-0.057
 dark-0.056
 little-0.054
 bunny-0.053
TokenL
Token ID43
Feature activation-9.77e+00

Pos logit contributions
ases+0.147
olds+0.140
els+0.137
cks+0.132
ips+0.128
Neg logit contributions
 barrel-0.089
 hut-0.084
 bunny-0.084
 puppy-0.084
 dark-0.083
Tokenily
Token ID813
Feature activation-3.73e+00

Pos logit contributions
ases+0.240
olds+0.223
els+0.222
cks+0.217
irs+0.205
Neg logit contributions
 barrel-0.197
 bunny-0.195
 dark-0.194
 Bun-0.194
 puppy-0.194
Token feels
Token ID5300
Feature activation-1.66e+00

Pos logit contributions
ases+0.096
olds+0.089
els+0.088
cks+0.085
ips+0.083
Neg logit contributions
 barrel-0.073
 bunny-0.071
 puppy-0.071
 dark-0.071
 hut-0.071
Token better
Token ID1365
Feature activation-3.87e+00

Pos logit contributions
ases+0.055
olds+0.052
els+0.052
cks+0.050
ips+0.049
Neg logit contributions
 barrel-0.020
 dark-0.019
 bunny-0.019
 puppy-0.019
 Bun-0.019
Token.
Token ID13
Feature activation+6.49e-01

Pos logit contributions
ases+0.151
els+0.146
irs+0.144
cks+0.142
olds+0.138
Neg logit contributions
 he-0.028
 there-0.026
 dark-0.025
 while-0.025
 little-0.025
Token She
Token ID1375
Feature activation+8.55e-01

Pos logit contributions
 barrel+0.012
 hunter+0.011
 shield+0.011
 cabin+0.011
 Bun+0.011
Neg logit contributions
ases-0.017
olds-0.017
els-0.016
ips-0.015
rs-0.014
Token says
Token ID1139
Feature activation-2.41e+00

Pos logit contributions
 barrel+0.021
 Bun+0.021
 hut+0.021
 dark+0.020
 puppy+0.020
Neg logit contributions
ases-0.017
olds-0.016
els-0.015
cks-0.015
its-0.014
Token,
Token ID11
Feature activation-2.06e+00

Pos logit contributions
ases+0.084
els+0.079
olds+0.078
cks+0.077
ips+0.075
Neg logit contributions
 barrel-0.025
 bunny-0.025
 puppy-0.025
 dark-0.025
 he-0.025
Token "
Token ID366
Feature activation-3.52e+00

Pos logit contributions
ases+0.070
olds+0.066
els+0.065
cks+0.064
ips+0.063
Neg logit contributions
 barrel-0.023
 hut-0.022
 dark-0.022
 puppy-0.022
 Bun-0.022
Token.
Token ID13
Feature activation-1.48e+00

Pos logit contributions
ases+0.155
els+0.146
olds+0.146
cks+0.143
irs+0.139
Neg logit contributions
 bunny-0.037
 barrel-0.036
 he-0.036
 puppy-0.036
 Bun-0.036
Token
Token ID198
Feature activation-6.88e+00

Pos logit contributions
ases+0.051
els+0.048
olds+0.047
cks+0.047
irs+0.045
Neg logit contributions
 Bun-0.017
 bunny-0.017
 puppy-0.016
 dark-0.016
 barrel-0.016
Token
Token ID198
Feature activation-5.99e+00

Pos logit contributions
ases+0.267
els+0.262
ocol+0.247
cks+0.247
olds+0.246
Neg logit contributions
 Bun-0.057
 he-0.051
 Benny-0.046
 there-0.043
 little-0.042
TokenThey
Token ID2990
Feature activation-1.32e-01

Pos logit contributions
ases+0.181
olds+0.169
els+0.169
cks+0.164
ips+0.159
Neg logit contributions
 barrel-0.091
 Bun-0.091
 puppy-0.089
 dark-0.089
 bunny-0.089
Token took
Token ID1718
Feature activation-5.30e+00

Pos logit contributions
ases+0.004
olds+0.004
els+0.004
ips+0.004
cks+0.004
Neg logit contributions
 barrel-0.002
 hut-0.002
 puppy-0.002
 Bun-0.002
 bunny-0.002
Token the
Token ID262
Feature activation-2.92e+00

Pos logit contributions
ases+0.157
olds+0.150
els+0.147
cks+0.145
ips+0.139
Neg logit contributions
 barrel-0.081
 dark-0.081
 puppy-0.080
 bunny-0.080
 Bun-0.080
Token equipment
Token ID5112
Feature activation+1.56e+00

Pos logit contributions
ases+0.092
olds+0.086
els+0.085
cks+0.083
ips+0.081
Neg logit contributions
 barrel-0.040
 Bun-0.040
 bunny-0.040
 puppy-0.040
 hut-0.039
Token to
Token ID284
Feature activation-3.76e+00

Pos logit contributions
 barrel+0.017
 dark+0.016
 hut+0.016
 he+0.016
 puppy+0.016
Neg logit contributions
ases-0.054
olds-0.051
els-0.050
cks-0.050
irs-0.048
Token a
Token ID257
Feature activation+4.00e+00

Pos logit contributions
ases+0.128
olds+0.124
els+0.122
cks+0.120
ips+0.117
Neg logit contributions
 dark-0.045
 Bun-0.045
 puppy-0.045
 little-0.044
 bunny-0.043
Token nearby
Token ID6716
Feature activation+3.00e+00

Pos logit contributions
 Bun+0.050
 bunny+0.045
 puppy+0.044
 he+0.044
 barrel+0.043
Neg logit contributions
ases-0.122
olds-0.119
els-0.112
cks-0.108
ips-0.108
Token fountain
Token ID29420
Feature activation+1.40e-01

Pos logit contributions
 Bun+0.037
 bunny+0.034
 puppy+0.033
 he+0.033
 barrel+0.033
Neg logit contributions
ases-0.097
olds-0.091
els-0.090
cks-0.085
ips-0.084
Token They
Token ID1119
Feature activation+5.67e-01

Pos logit contributions
 dark+0.019
 Bun+0.018
 puppy+0.018
 barrel+0.018
 hut+0.018
Neg logit contributions
ases-0.053
els-0.050
olds-0.049
cks-0.048
ips-0.047
Token will
Token ID481
Feature activation-1.28e+00

Pos logit contributions
 barrel+0.012
 bunny+0.012
 puppy+0.012
 dark+0.012
 Bun+0.012
Neg logit contributions
ases-0.014
olds-0.013
els-0.013
cks-0.012
ips-0.012
Token listen
Token ID6004
Feature activation-7.03e-01

Pos logit contributions
ases+0.040
els+0.038
olds+0.038
cks+0.036
ips+0.036
Neg logit contributions
 Bun-0.018
 puppy-0.018
 dark-0.018
 bunny-0.018
 he-0.018
Token to
Token ID284
Feature activation-6.77e+00

Pos logit contributions
ases+0.024
olds+0.023
els+0.023
cks+0.022
ips+0.022
Neg logit contributions
 barrel-0.008
 hut-0.007
 Bun-0.007
 puppy-0.007
 bunny-0.007
Token each
Token ID1123
Feature activation-5.86e+00

Pos logit contributions
ases+0.217
olds+0.209
ips+0.208
els+0.201
its+0.197
Neg logit contributions
 dark-0.098
 puppy-0.097
 little-0.094
 a-0.092
 bunny-0.092
Token other
Token ID584
Feature activation-4.88e+00

Pos logit contributions
ases+0.207
cks+0.202
ips+0.199
els+0.196
olds+0.196
Neg logit contributions
 little-0.066
 bunny-0.062
 puppy-0.062
 dark-0.062
 boy-0.058
Token.
Token ID13
Feature activation+1.33e+00

Pos logit contributions
ases+0.168
olds+0.159
els+0.158
cks+0.154
ips+0.151
Neg logit contributions
 barrel-0.052
 puppy-0.050
 bunny-0.050
 Bun-0.050
 dark-0.050
Token They
Token ID1119
Feature activation+3.31e-01

Pos logit contributions
 dark+0.014
 Bun+0.014
 puppy+0.014
 he+0.014
 barrel+0.014
Neg logit contributions
ases-0.046
els-0.044
cks-0.042
olds-0.042
ips-0.041
Token will
Token ID481
Feature activation-1.42e+00

Pos logit contributions
 barrel+0.007
 bunny+0.007
 puppy+0.007
 dark+0.007
 hut+0.007
Neg logit contributions
ases-0.008
els-0.008
olds-0.008
cks-0.007
ips-0.007
Token be
Token ID307
Feature activation-4.55e+00

Pos logit contributions
ases+0.044
els+0.042
olds+0.041
cks+0.040
ips+0.040
Neg logit contributions
 Bun-0.020
 puppy-0.020
 bunny-0.020
 dark-0.020
 he-0.020
Token safe
Token ID3338
Feature activation-2.29e+00

Pos logit contributions
ases+0.150
olds+0.139
els+0.138
cks+0.137
ips+0.132
Neg logit contributions
 barrel-0.060
 Bun-0.056
 bunny-0.056
 hut-0.055
 puppy-0.054
Token,
Token ID11
Feature activation-1.39e+00

Pos logit contributions
ases+0.137
els+0.132
olds+0.128
cks+0.125
its+0.117
Neg logit contributions
 dark-0.064
 hut-0.063
 barrel-0.062
 Bun-0.062
 bunny-0.061
Token but
Token ID475
Feature activation-3.21e-01

Pos logit contributions
ases+0.040
olds+0.038
els+0.038
cks+0.036
irs+0.035
Neg logit contributions
 barrel-0.021
 hut-0.021
 dark-0.020
 Bun-0.020
 puppy-0.020
Token be
Token ID307
Feature activation-1.93e+00

Pos logit contributions
ases+0.009
els+0.008
olds+0.008
cks+0.008
ips+0.008
Neg logit contributions
 barrel-0.005
 hut-0.005
 puppy-0.005
 Bun-0.005
 bunny-0.005
Token careful
Token ID8161
Feature activation-1.65e+00

Pos logit contributions
ases+0.053
olds+0.049
cks+0.048
els+0.047
ips+0.046
Neg logit contributions
 barrel-0.035
 puppy-0.034
 bunny-0.034
 Bun-0.034
 hut-0.033
Token and
Token ID290
Feature activation+6.84e-01

Pos logit contributions
ases+0.054
olds+0.051
els+0.050
cks+0.049
ips+0.048
Neg logit contributions
 barrel-0.021
 puppy-0.020
 bunny-0.020
 hut-0.020
 Bun-0.020
Token don
Token ID836
Feature activation-4.15e+00

Pos logit contributions
 barrel+0.011
 puppy+0.011
 Bun+0.011
 bunny+0.011
 hut+0.011
Neg logit contributions
ases-0.020
olds-0.019
els-0.018
cks-0.018
ips-0.017
Token't
Token ID470
Feature activation-3.44e+00

Pos logit contributions
ases+0.125
olds+0.118
els+0.116
cks+0.112
ips+0.109
Neg logit contributions
 Bun-0.062
 dark-0.061
 barrel-0.061
 bunny-0.061
 he-0.061
Token get
Token ID651
Feature activation-3.81e+00

Pos logit contributions
ases+0.090
olds+0.083
els+0.080
cks+0.079
its+0.076
Neg logit contributions
 barrel-0.065
 hut-0.062
 Bun-0.061
 puppy-0.061
 bunny-0.061
Token too
Token ID1165
Feature activation-7.76e-01

Pos logit contributions
ases+0.125
olds+0.119
els+0.117
cks+0.117
ips+0.110
Neg logit contributions
 barrel-0.049
 hut-0.046
 cabin-0.044
 bunny-0.043
 puppy-0.042
Token close
Token ID1969
Feature activation-2.06e+00

Pos logit contributions
ases+0.025
olds+0.024
cks+0.023
els+0.023
its+0.022
Neg logit contributions
 Bun-0.010
 puppy-0.009
 bunny-0.009
 barrel-0.009
 Benny-0.009
Token to
Token ID284
Feature activation-4.53e+00

Pos logit contributions
ases+0.072
olds+0.068
els+0.067
cks+0.065
ips+0.064
Neg logit contributions
 barrel-0.022
 bunny-0.021
 puppy-0.021
 Bun-0.021
 hut-0.021
Token perfect
Token ID2818
Feature activation+6.42e-01

Pos logit contributions
 barrel+0.040
 Bun+0.040
 hut+0.039
 cabin+0.038
 puppy+0.038
Neg logit contributions
ases-0.107
olds-0.103
els-0.101
cks-0.099
ips-0.093
Token.
Token ID13
Feature activation+2.98e+00

Pos logit contributions
 Bun+0.009
 barrel+0.008
 dark+0.008
 puppy+0.008
 bunny+0.008
Neg logit contributions
ases-0.020
olds-0.019
els-0.019
ips-0.018
cks-0.018
Token
Token ID220
Feature activation-3.46e+00

Pos logit contributions
 barrel+0.045
 dark+0.043
 hut+0.043
 bunny+0.042
 puppy+0.042
Neg logit contributions
ases-0.089
olds-0.085
els-0.082
cks-0.080
ips-0.079
Token
Token ID198
Feature activation-3.49e+00

Pos logit contributions
ases+0.128
els+0.123
cks+0.117
olds+0.117
ocol+0.113
Neg logit contributions
 he-0.029
 there-0.028
 Bun-0.028
 little-0.025
 barrel-0.025
Token
Token ID198
Feature activation-3.00e+00

Pos logit contributions
ases+0.124
els+0.118
olds+0.114
cks+0.112
ips+0.110
Neg logit contributions
 Bun-0.038
 he-0.037
 bunny-0.035
 barrel-0.034
 there-0.034
TokenPe
Token ID6435
Feature activation-1.02e+01

Pos logit contributions
ases+0.088
olds+0.083
els+0.082
cks+0.079
ips+0.077
Neg logit contributions
 barrel-0.048
 dark-0.046
 puppy-0.046
 hut-0.046
 bunny-0.046
Tokenggy
Token ID19970
Feature activation-1.00e+00

Pos logit contributions
ases+0.236
olds+0.208
els+0.202
irs+0.197
ips+0.196
Neg logit contributions
 he-0.229
 lost-0.224
 Bun-0.223
 there-0.222
 hunter-0.221
Token was
Token ID373
Feature activation+6.32e-01

Pos logit contributions
ases+0.033
olds+0.031
els+0.031
cks+0.030
ips+0.029
Neg logit contributions
 barrel-0.012
 hut-0.011
 dark-0.011
 cabin-0.011
 puppy-0.010
Token so
Token ID523
Feature activation+1.48e+00

Pos logit contributions
 barrel+0.005
 Bun+0.005
 hut+0.005
 puppy+0.005
 bunny+0.005
Neg logit contributions
ases-0.023
olds-0.022
els-0.022
cks-0.022
ips-0.021
Token very
Token ID845
Feature activation+1.75e+00

Pos logit contributions
 barrel+0.017
 puppy+0.016
 bunny+0.016
 Bun+0.016
 dark+0.016
Neg logit contributions
ases-0.051
olds-0.048
els-0.047
cks-0.046
ips-0.045
Token happy
Token ID3772
Feature activation+2.20e+00

Pos logit contributions
 barrel+0.023
 Bun+0.023
 puppy+0.022
 bunny+0.022
 hut+0.022
Neg logit contributions
ases-0.056
olds-0.054
els-0.052
cks-0.051
its-0.049
Token Go
Token ID1514
Feature activation-4.73e+00

Pos logit contributions
 barrel+0.016
 puppy+0.016
 Bun+0.016
 bunny+0.016
 dark+0.016
Neg logit contributions
ases-0.076
els-0.072
olds-0.072
cks-0.070
ips-0.069
Token away
Token ID1497
Feature activation-2.40e+00

Pos logit contributions
ases+0.139
olds+0.129
els+0.127
cks+0.122
ips+0.121
Neg logit contributions
 barrel-0.076
 hut-0.074
 bunny-0.073
 dark-0.073
 Bun-0.072
Token!"
Token ID2474
Feature activation-1.91e+00

Pos logit contributions
ases+0.076
olds+0.071
els+0.070
cks+0.068
ips+0.066
Neg logit contributions
 barrel-0.033
 puppy-0.031
 Bun-0.031
 dark-0.031
 bunny-0.031
Token
Token ID198
Feature activation-6.08e+00

Pos logit contributions
ases+0.063
els+0.059
olds+0.059
cks+0.057
ips+0.056
Neg logit contributions
 barrel-0.024
 he-0.024
 Bun-0.023
 dark-0.023
 puppy-0.023
Token
Token ID198
Feature activation-5.12e+00

Pos logit contributions
ases+0.224
els+0.217
olds+0.207
cks+0.203
ips+0.203
Neg logit contributions
 he-0.058
 Bun-0.057
 dark-0.053
 there-0.052
 little-0.052
TokenL
Token ID43
Feature activation-1.02e+01

Pos logit contributions
ases+0.156
olds+0.146
els+0.145
cks+0.141
ips+0.137
Neg logit contributions
 barrel-0.077
 puppy-0.075
 bunny-0.075
 dark-0.075
 Bun-0.075
Tokenily
Token ID813
Feature activation-4.07e+00

Pos logit contributions
ases+0.261
els+0.247
olds+0.245
cks+0.245
irs+0.233
Neg logit contributions
 he-0.180
 barrel-0.179
 there-0.178
 bunny-0.178
 puppy-0.178
Token and
Token ID290
Feature activation-1.16e+00

Pos logit contributions
ases+0.129
olds+0.123
els+0.122
cks+0.117
ips+0.114
Neg logit contributions
 barrel-0.054
 hut-0.053
 Bun-0.051
 dark-0.051
 cabin-0.050
Token Max
Token ID5436
Feature activation-5.10e+00

Pos logit contributions
ases+0.030
olds+0.027
els+0.027
cks+0.026
ips+0.025
Neg logit contributions
 barrel-0.023
 hut-0.022
 dark-0.022
 cabin-0.022
 puppy-0.022
Token felt
Token ID2936
Feature activation-1.18e+00

Pos logit contributions
ases+0.162
olds+0.153
els+0.151
cks+0.147
ips+0.143
Neg logit contributions
 barrel-0.068
 hut-0.066
 Bun-0.065
 dark-0.065
 bunny-0.065
Token sad
Token ID6507
Feature activation-1.60e+00

Pos logit contributions
ases+0.035
olds+0.034
els+0.032
cks+0.032
its+0.030
Neg logit contributions
 barrel-0.018
 Bun-0.017
 hut-0.017
 bunny-0.017
 cabin-0.017
Token.
Token ID13
Feature activation+1.48e+00

Pos logit contributions
ases+0.055
els+0.052
olds+0.052
cks+0.051
irs+0.049
Neg logit contributions
 barrel-0.014
 dark-0.014
 he-0.014
 puppy-0.014
 bunny-0.014
Token She
Token ID1375
Feature activation+1.76e+00

Pos logit contributions
 dark+0.014
 he+0.014
 puppy+0.013
 barrel+0.013
 bunny+0.013
Neg logit contributions
ases-0.054
els-0.051
cks-0.051
olds-0.050
irs-0.049
Token says
Token ID1139
Feature activation-2.21e+00

Pos logit contributions
 little+0.038
 lost+0.037
 dark+0.037
 wanted+0.037
 scary+0.036
Neg logit contributions
ases-0.042
els-0.038
irs-0.038
ips-0.037
ums-0.036
Token,
Token ID11
Feature activation-2.00e+00

Pos logit contributions
ases+0.079
els+0.074
cks+0.073
olds+0.073
ips+0.071
Neg logit contributions
 he-0.022
 dark-0.021
 barrel-0.021
 bunny-0.021
 puppy-0.021
Token "
Token ID366
Feature activation-3.84e+00

Pos logit contributions
ases+0.075
els+0.070
olds+0.070
cks+0.069
ips+0.067
Neg logit contributions
 barrel-0.017
 dark-0.016
 he-0.016
 bunny-0.016
 puppy-0.016
TokenS
Token ID50
Feature activation-1.05e+01

Pos logit contributions
ases+0.125
olds+0.117
els+0.116
cks+0.114
irs+0.110
Neg logit contributions
 dark-0.050
 puppy-0.050
 boy-0.049
 there-0.049
 bunny-0.048
Tokenara
Token ID3301
Feature activation-5.65e+00

Pos logit contributions
ases+0.231
cks+0.216
olds+0.211
els+0.198
irs+0.191
Neg logit contributions
 barrel-0.237
 puppy-0.232
 dark-0.229
 hut-0.227
 there-0.226
Token and
Token ID290
Feature activation+6.46e-02

Pos logit contributions
ases+0.200
els+0.188
olds+0.188
cks+0.186
irs+0.184
Neg logit contributions
 barrel-0.056
 puppy-0.055
 bunny-0.054
 dark-0.053
 Bun-0.053
Token Tom
Token ID4186
Feature activation-5.98e+00

Pos logit contributions
 barrel+0.001
 Bun+0.001
 puppy+0.001
 dark+0.001
 bunny+0.001
Neg logit contributions
ases-0.002
olds-0.001
els-0.001
cks-0.001
ips-0.001
Token,
Token ID11
Feature activation-1.59e+00

Pos logit contributions
ases+0.213
els+0.202
olds+0.201
cks+0.196
irs+0.195
Neg logit contributions
 barrel-0.056
 dark-0.056
 puppy-0.055
 he-0.054
 bunny-0.054
Token what
Token ID644
Feature activation+8.82e-01

Pos logit contributions
ases+0.043
olds+0.040
els+0.040
cks+0.038
ips+0.037
Neg logit contributions
 barrel-0.030
 puppy-0.029
 bunny-0.029
 dark-0.029
 he-0.029
Token.
Token ID13
Feature activation+2.26e+00

Pos logit contributions
ases+0.087
olds+0.082
els+0.081
cks+0.079
ips+0.077
Neg logit contributions
 barrel-0.043
 puppy-0.042
 dark-0.042
 bunny-0.042
 Bun-0.042
Token Now
Token ID2735
Feature activation-1.69e-01

Pos logit contributions
 barrel+0.036
 hut+0.034
 dark+0.034
 bunny+0.034
 Bun+0.034
Neg logit contributions
ases-0.068
olds-0.064
els-0.061
cks-0.060
ips-0.059
Token!"
Token ID2474
Feature activation-2.21e+00

Pos logit contributions
ases+0.005
olds+0.005
els+0.005
cks+0.005
ips+0.004
Neg logit contributions
 barrel-0.002
 Bun-0.002
 dark-0.002
 hut-0.002
 puppy-0.002
Token
Token ID198
Feature activation-7.18e+00

Pos logit contributions
ases+0.072
olds+0.067
els+0.067
cks+0.065
ips+0.063
Neg logit contributions
 barrel-0.029
 dark-0.028
 puppy-0.028
 Bun-0.028
 bunny-0.028
Token
Token ID198
Feature activation-6.21e+00

Pos logit contributions
ases+0.256
els+0.247
olds+0.236
cks+0.234
ips+0.231
Neg logit contributions
 Bun-0.076
 he-0.073
 dark-0.070
 bunny-0.069
 puppy-0.069
TokenL
Token ID43
Feature activation-1.09e+01

Pos logit contributions
ases+0.193
els+0.181
olds+0.180
cks+0.175
ips+0.171
Neg logit contributions
 barrel-0.089
 Bun-0.088
 puppy-0.088
 bunny-0.088
 dark-0.088
Tokenily
Token ID813
Feature activation-4.28e+00

Pos logit contributions
ases+0.271
olds+0.253
els+0.253
cks+0.248
irs+0.234
Neg logit contributions
 barrel-0.213
 bunny-0.209
 Bun-0.209
 puppy-0.208
 dark-0.207
Token and
Token ID290
Feature activation-1.29e+00

Pos logit contributions
ases+0.142
olds+0.134
els+0.133
cks+0.130
ips+0.127
Neg logit contributions
 barrel-0.051
 bunny-0.050
 puppy-0.050
 dark-0.049
 Bun-0.049
Token Ben
Token ID3932
Feature activation-6.15e+00

Pos logit contributions
ases+0.038
cks+0.036
olds+0.036
els+0.035
its+0.034
Neg logit contributions
 bunny-0.022
 dark-0.021
 puppy-0.021
 he-0.021
 barrel-0.020
Token are
Token ID389
Feature activation-2.67e+00

Pos logit contributions
ases+0.164
olds+0.153
els+0.151
cks+0.146
ips+0.142
Neg logit contributions
 barrel-0.114
 puppy-0.112
 bunny-0.111
 Bun-0.111
 dark-0.111
Token ashamed
Token ID22461
Feature activation-2.23e-01

Pos logit contributions
ases+0.087
olds+0.082
els+0.080
cks+0.079
ips+0.078
Neg logit contributions
 barrel-0.036
 Bun-0.034
 bunny-0.033
 puppy-0.033
 hut-0.032
Token whim
Token ID29923
Feature activation-8.22e+00

Pos logit contributions
 barrel+0.005
 hut+0.005
 cabin+0.005
 dark+0.005
 bicycle+0.005
Neg logit contributions
ases-0.011
olds-0.011
els-0.011
cks-0.010
ips-0.010
Tokenpered
Token ID13653
Feature activation-4.13e+00

Pos logit contributions
olds+0.155
ases+0.154
irs+0.148
els+0.141
ips+0.135
Neg logit contributions
 dark-0.200
 lost-0.198
 hut-0.197
 bunny-0.196
 Bun-0.196
Token.
Token ID13
Feature activation+8.64e-01

Pos logit contributions
ases+0.132
olds+0.124
els+0.121
cks+0.117
rs+0.114
Neg logit contributions
 barrel-0.055
 hut-0.051
 bunny-0.050
 cabin-0.050
 Bun-0.050
Token
Token ID198
Feature activation-5.44e+00

Pos logit contributions
 barrel+0.011
 hut+0.011
 puppy+0.011
 dark+0.011
 bunny+0.011
Neg logit contributions
ases-0.027
olds-0.026
els-0.025
cks-0.025
ips-0.024
Token
Token ID198
Feature activation-4.73e+00

Pos logit contributions
ases+0.215
els+0.209
ips+0.197
cks+0.195
olds+0.194
Neg logit contributions
 he-0.044
 Bun-0.042
 there-0.036
 Benny-0.036
 little-0.035
TokenL
Token ID43
Feature activation-9.98e+00

Pos logit contributions
ases+0.133
olds+0.125
els+0.123
cks+0.119
ips+0.116
Neg logit contributions
 barrel-0.082
 puppy-0.080
 dark-0.079
 hut-0.079
 bunny-0.079
Tokenily
Token ID813
Feature activation-3.76e+00

Pos logit contributions
ases+0.253
olds+0.238
els+0.236
cks+0.232
irs+0.220
Neg logit contributions
 bunny-0.191
 Bun-0.189
 barrel-0.189
 he-0.186
 dark-0.185
Token's
Token ID338
Feature activation-1.36e+00

Pos logit contributions
ases+0.114
olds+0.109
els+0.107
cks+0.103
ips+0.100
Neg logit contributions
 barrel-0.053
 dark-0.052
 hut-0.052
 Bun-0.050
 cabin-0.050
Token mom
Token ID1995
Feature activation-4.75e+00

Pos logit contributions
ases+0.040
olds+0.038
els+0.037
cks+0.035
ips+0.035
Neg logit contributions
 barrel-0.021
 Bun-0.020
 he-0.020
 hut-0.020
 dark-0.020
Token and
Token ID290
Feature activation+1.06e-01

Pos logit contributions
ases+0.178
olds+0.166
els+0.163
cks+0.163
irs+0.160
Neg logit contributions
 bunny-0.040
 barrel-0.040
 he-0.040
 puppy-0.040
 Bun-0.039
Token dad
Token ID9955
Feature activation-5.06e+00

Pos logit contributions
 barrel+0.002
 puppy+0.002
 bunny+0.002
 he+0.002
 hut+0.002
Neg logit contributions
ases-0.003
olds-0.003
els-0.003
cks-0.003
its-0.003