TOP ACTIVATIONS
MAX = 14.304

night in the k enn el . Fortunately ,
. She likes that past el . It is her favorite
mom told her to kne el down and put her hands
she thought that the past el was broken .
act , like sharing past el colors , could bring happiness
the ocean . The past el saw things so beautiful that
house to return the past el . Mrs . Green welcomed
he loved the pretty past el . As he walked away
past el . The past el was bright and colourful and
sign that said " Hot el ". She kept working until
Su zie y el ped in surprise , "
lying there , the past el pet als started to bloom
he was able to kne el before the star and make
and bought lots of past el colors . She had yellow
a game with a past el . The past el was
th ud as the past el landed on the floor .
needed to clean her past el toys before they could go
glad of his cool past el shirt . <|endoftext|> Jack was
Let 's tie your sho el aces together so they won
to leave the mail und el ivered . So he decided

MIN ACTIVATIONS
MIN = -18.730

. They had stopped qu arre ling . To celebrate ,
on , they never qu arre led again over clothes .
told them to stop qu arre lling and to share the
. The bears stopped qu arre ling and asked him for
but today they were qu arre ling . Jenna wanted to
and their children , qu arre ling .
and saw two birds qu arre ling ! They were squ
together . They never qu arre led again . <|endoftext|> Once
Tom and Mia stop qu arre ling . They see the
lively sound . The qu arre ling stopped and they heard
walking by saw them qu arre ling . She was very
friends didn 't stop qu arre ling and were getting louder
on , they never qu arre led again and played together
she was sorry for qu arre ling . From that day
Lily and Jack never qu arre led again . They learned
the parents were also qu arre ling . The first family
Finally , after much qu arre ling , one of the
two squirrel s kept qu arre ling until finally Sammy said
They learn that qu arre ling is bad and sharing
said , " Stop qu arre ling , boys . You

INTERVAL 6.046 - 14.304
CONTAINS 1.330%

Lily was very careful and cut the w affle into tiny
paws to tear the wrap open . Inside the wrap ,
Sam say . Mom nods and smiles . She
wonderful surprise ! M ama and Papa opened the
oll ipop hiding behind a rock . John was very excited

INTERVAL -2.213 - 6.046
CONTAINS 85.101%

proud of Lily . She said she forg ave her .
toys from his luggage and put them in his backpack .
best picture she had ever drawn . She wanted to draw
us and hit us ." But Tim did not
. He goes back to the living room and lays on

INTERVAL -10.471 - -2.213
CONTAINS 13.560%

told it to keep the message safe . From
! Tim my felt so happy and successful .
fall in ." Ben was curious . He said , "
much better without all the noise ! <|endoftext|> Once upon a
They played a fun game . Tim won the

INTERVAL -18.730 - -10.471
CONTAINS 0.009%

the birds were only qu arre ling like little children do
The bird explained about the war and how it was making
Finally , Tim my fell asleep and had a good dream
and pretend to be opera singers . " Hello
Ben ! The audience cheers and cl aps .
Token night
Token ID1755
Feature activation-4.29e-02

Pos logit contributions
 Alan+0.053
 MacDonald+0.050
 war+0.050
fires+0.049
Alan+0.049
Neg logit contributions
itten-0.042
 arm-0.036
 nail-0.033
une-0.033
 knob-0.033
Token in
Token ID287
Feature activation+7.77e-02

Pos logit contributions
 Skip+0.002
 Alan+0.002
 MacDonald+0.002
brate+0.002
Alan+0.002
Neg logit contributions
itten-0.002
 arm-0.002
el-0.002
 nail-0.001
une-0.001
Token the
Token ID262
Feature activation-1.18e+00

Pos logit contributions
itten+0.004
 arm+0.003
 nail+0.003
el+0.003
une+0.003
Neg logit contributions
fires-0.002
brate-0.002
 MacDonald-0.002
 war-0.002
 Skip-0.002
Token k
Token ID479
Feature activation-3.82e-01

Pos logit contributions
 war+0.048
 Skip+0.048
fires+0.047
 Alan+0.047
 MacDonald+0.047
Neg logit contributions
itten-0.043
une-0.039
 arm-0.038
el-0.037
 nail-0.037
Tokenenn
Token ID1697
Feature activation+4.53e+00

Pos logit contributions
 war+0.017
 cheered+0.016
fires+0.016
 Skip+0.016
 congratulated+0.016
Neg logit contributions
itten-0.012
une-0.012
 knob-0.011
 arm-0.010
 nail-0.010
Tokenel
Token ID417
Feature activation+1.41e+01

Pos logit contributions
itten+0.069
une+0.051
 nail+0.050
 knob+0.047
 injection+0.041
Neg logit contributions
 war-0.271
 Alan-0.269
 Skip-0.263
 cheered-0.259
 MacDonald-0.259
Token.
Token ID13
Feature activation+5.31e-01

Pos logit contributions
itten+0.525
une+0.482
el+0.453
 arm+0.447
 nail+0.444
Neg logit contributions
 war-0.585
 Skip-0.564
fires-0.550
 Alan-0.546
 MacDonald-0.546
Token
Token ID198
Feature activation-1.06e-01

Pos logit contributions
itten+0.025
une+0.023
el+0.022
 nail+0.022
 arm+0.021
Neg logit contributions
 war-0.017
 Skip-0.016
fires-0.016
 Alan-0.016
 MacDonald-0.016
Token
Token ID198
Feature activation-9.72e-02

Pos logit contributions
 war+0.003
 Skip+0.003
 cheered+0.003
fires+0.003
 Alan+0.003
Neg logit contributions
itten-0.005
une-0.005
el-0.005
 nail-0.005
 arm-0.005
TokenFortunately
Token ID31276
Feature activation+2.61e+00

Pos logit contributions
 war+0.003
 Skip+0.003
fires+0.003
 Alan+0.003
 MacDonald+0.003
Neg logit contributions
itten-0.004
une-0.004
el-0.004
 nail-0.004
 arm-0.004
Token,
Token ID11
Feature activation-3.65e-01

Pos logit contributions
itten+0.099
 arm+0.094
une+0.094
el+0.092
 nail+0.090
Neg logit contributions
 MacDonald-0.100
fires-0.096
 war-0.093
brate-0.093
 performers-0.090
Token.
Token ID13
Feature activation+8.96e-01

Pos logit contributions
 war+0.058
 Skip+0.054
fires+0.053
 MacDonald+0.052
 cheered+0.052
Neg logit contributions
itten-0.087
une-0.081
el-0.076
 nail-0.076
umb-0.074
Token She
Token ID1375
Feature activation+1.74e+00

Pos logit contributions
itten+0.034
une+0.031
el+0.029
 nail+0.029
 arm+0.028
Neg logit contributions
 war-0.036
 Skip-0.036
 Alan-0.035
 MacDonald-0.035
fires-0.034
Token likes
Token ID7832
Feature activation-1.29e+00

Pos logit contributions
itten+0.071
une+0.068
 arm+0.065
el+0.064
 nail+0.063
Neg logit contributions
 war-0.063
fires-0.060
 Skip-0.060
 Alan-0.059
 MacDonald-0.057
Token that
Token ID326
Feature activation-1.45e-01

Pos logit contributions
fires+0.036
 war+0.035
 Skip+0.034
 MacDonald+0.034
 cheered+0.034
Neg logit contributions
itten-0.063
une-0.060
 arm-0.058
 nail-0.058
el-0.057
Token past
Token ID1613
Feature activation+3.07e+00

Pos logit contributions
 war+0.005
fires+0.005
 Skip+0.005
 MacDonald+0.005
brate+0.005
Neg logit contributions
itten-0.006
une-0.006
 arm-0.005
 nail-0.005
el-0.005
Tokenel
Token ID417
Feature activation+1.41e+01

Pos logit contributions
itten+0.129
une+0.120
 nail+0.112
 knob+0.110
 injection+0.109
Neg logit contributions
 war-0.110
 Skip-0.108
 Alan-0.102
 seals-0.102
 MacDonald-0.101
Token.
Token ID13
Feature activation+9.31e-01

Pos logit contributions
itten+0.580
une+0.546
el+0.519
 arm+0.509
 nail+0.502
Neg logit contributions
 war-0.529
 Skip-0.510
fires-0.495
 Alan-0.493
 MacDonald-0.486
Token It
Token ID632
Feature activation+2.58e+00

Pos logit contributions
itten+0.036
une+0.032
el+0.031
 nail+0.031
 arm+0.030
Neg logit contributions
 war-0.037
 Skip-0.037
 Alan-0.035
 MacDonald-0.035
fires-0.034
Token is
Token ID318
Feature activation-3.16e-01

Pos logit contributions
itten+0.106
une+0.100
el+0.094
 arm+0.093
 nail+0.092
Neg logit contributions
 war-0.095
 Skip-0.091
fires-0.090
 Alan-0.088
 MacDonald-0.087
Token her
Token ID607
Feature activation+4.12e+00

Pos logit contributions
 war+0.010
 Skip+0.010
fires+0.010
 MacDonald+0.009
 Alan+0.009
Neg logit contributions
itten-0.015
une-0.014
 arm-0.013
el-0.013
 nail-0.013
Token favorite
Token ID4004
Feature activation+5.21e+00

Pos logit contributions
itten+0.153
el+0.134
une+0.133
umb+0.132
 injection+0.121
Neg logit contributions
 war-0.178
 games-0.158
 celebrating-0.157
 Skip-0.155
 Alan-0.154
Token mom
Token ID1995
Feature activation+5.74e+00

Pos logit contributions
itten+0.137
une+0.119
el+0.113
 nail+0.112
umb+0.111
Neg logit contributions
 war-0.195
 Skip-0.185
 Alan-0.180
 cheered-0.178
 jokes-0.177
Token told
Token ID1297
Feature activation+9.79e-01

Pos logit contributions
itten+0.286
une+0.276
el+0.256
 nail+0.254
umb+0.252
Neg logit contributions
 cheered-0.157
 war-0.154
 Skip-0.149
 congratulated-0.145
 Alan-0.142
Token her
Token ID607
Feature activation+4.19e+00

Pos logit contributions
itten+0.025
une+0.023
el+0.023
 arm+0.022
 nail+0.021
Neg logit contributions
 war-0.049
 Skip-0.049
fires-0.049
 MacDonald-0.048
 seals-0.047
Token to
Token ID284
Feature activation-2.34e-01

Pos logit contributions
itten+0.171
une+0.170
 arm+0.168
 nail+0.163
 knob+0.159
Neg logit contributions
fires-0.142
 MacDonald-0.141
 war-0.138
 Skip-0.138
 seals-0.135
Token kne
Token ID24813
Feature activation+1.80e+00

Pos logit contributions
 war+0.009
 Skip+0.008
fires+0.008
 MacDonald+0.008
 Alan+0.008
Neg logit contributions
itten-0.010
une-0.009
el-0.009
 nail-0.009
 arm-0.008
Tokenel
Token ID417
Feature activation+1.41e+01

Pos logit contributions
une+0.030
itten+0.030
 nail+0.025
 knob+0.023
 bulb+0.020
Neg logit contributions
 war-0.103
 cheered-0.102
 Alan-0.100
 Skip-0.099
 seals-0.098
Token down
Token ID866
Feature activation+8.85e-01

Pos logit contributions
itten+0.625
une+0.582
 nail+0.564
umb+0.533
 knob+0.510
Neg logit contributions
 war-0.452
 Skip-0.436
fires-0.412
 Alan-0.409
 games-0.407
Token and
Token ID290
Feature activation+1.43e-01

Pos logit contributions
itten+0.036
une+0.034
 arm+0.032
el+0.032
 nail+0.032
Neg logit contributions
 war-0.033
 Skip-0.032
 MacDonald-0.031
fires-0.031
 Alan-0.030
Token put
Token ID1234
Feature activation+2.71e+00

Pos logit contributions
itten+0.006
une+0.005
 nail+0.005
el+0.005
 arm+0.005
Neg logit contributions
 war-0.005
 Skip-0.005
fires-0.005
 MacDonald-0.005
 Alan-0.005
Token her
Token ID607
Feature activation+4.24e+00

Pos logit contributions
itten+0.125
une+0.116
 nail+0.108
umb+0.107
el+0.104
Neg logit contributions
 war-0.088
 Skip-0.085
 cheered-0.083
 Alan-0.081
 they-0.080
Token hands
Token ID2832
Feature activation+1.73e+00

Pos logit contributions
itten+0.186
une+0.175
umb+0.163
el+0.162
 nail+0.161
Neg logit contributions
 war-0.143
 Skip-0.134
 games-0.128
fires-0.128
 cheered-0.125
Token she
Token ID673
Feature activation+1.50e+00

Pos logit contributions
itten+0.090
une+0.086
el+0.078
umb+0.078
 nail+0.077
Neg logit contributions
 war-0.067
 Skip-0.064
 Alan-0.060
 cheered-0.060
 they-0.059
Token thought
Token ID1807
Feature activation+2.02e+00

Pos logit contributions
itten+0.074
une+0.070
el+0.065
 nail+0.065
 arm+0.064
Neg logit contributions
 war-0.044
 Skip-0.042
 cheered-0.040
 Alan-0.040
fires-0.039
Token that
Token ID326
Feature activation+7.94e-02

Pos logit contributions
itten+0.088
une+0.082
 nail+0.079
 arm+0.078
el+0.077
Neg logit contributions
 war-0.069
 Skip-0.067
fires-0.066
 MacDonald-0.066
 Alan-0.065
Token the
Token ID262
Feature activation-1.12e+00

Pos logit contributions
itten+0.004
une+0.003
el+0.003
 nail+0.003
 arm+0.003
Neg logit contributions
 war-0.003
 Skip-0.002
fires-0.002
 Alan-0.002
 MacDonald-0.002
Token past
Token ID1613
Feature activation+3.40e+00

Pos logit contributions
 war+0.048
 games+0.042
 celebrating+0.041
 parade+0.041
 performers+0.040
Neg logit contributions
itten-0.046
une-0.038
el-0.038
umb-0.038
orn-0.035
Tokenel
Token ID417
Feature activation+1.41e+01

Pos logit contributions
itten+0.075
une+0.067
 injection+0.065
 axe+0.063
umb+0.060
Neg logit contributions
 they-0.166
 war-0.162
 parade-0.151
 music-0.151
 games-0.150
Token was
Token ID373
Feature activation-7.06e-02

Pos logit contributions
itten+0.553
une+0.468
umb+0.457
 injection+0.448
 nail+0.445
Neg logit contributions
 war-0.533
fires-0.517
 MacDonald-0.500
 cheered-0.499
 games-0.489
Token broken
Token ID5445
Feature activation+1.22e+00

Pos logit contributions
 MacDonald+0.003
fires+0.003
 Skip+0.002
 cheered+0.002
 Alan+0.002
Neg logit contributions
itten-0.003
une-0.003
 arm-0.003
 nail-0.003
 knob-0.003
Token.
Token ID13
Feature activation+4.38e-01

Pos logit contributions
itten+0.052
une+0.049
el+0.047
 nail+0.047
 arm+0.047
Neg logit contributions
 war-0.043
 Skip-0.042
fires-0.041
 Alan-0.041
 MacDonald-0.040
Token
Token ID220
Feature activation+3.34e+00

Pos logit contributions
itten+0.022
une+0.021
el+0.019
 nail+0.019
umb+0.019
Neg logit contributions
 Skip-0.013
 war-0.012
 Alan-0.012
 cheered-0.012
 they-0.012
Token
Token ID198
Feature activation-9.63e-02

Pos logit contributions
itten+0.182
une+0.171
 egg+0.166
el+0.165
 knob+0.165
Neg logit contributions
 Skip-0.076
 cheered-0.075
 war-0.074
 Alan-0.071
 they-0.071
Token act
Token ID719
Feature activation-1.51e+00

Pos logit contributions
 Skip+0.103
fires+0.099
 war+0.099
 Alan+0.098
 MacDonald+0.097
Neg logit contributions
itten-0.086
une-0.080
 arm-0.079
 nail-0.079
 knob-0.076
Token,
Token ID11
Feature activation-5.04e-01

Pos logit contributions
 Skip+0.062
 Alan+0.059
 war+0.059
 seals+0.058
 MacDonald+0.058
Neg logit contributions
une-0.052
itten-0.050
 nail-0.049
 arm-0.048
 knob-0.047
Token like
Token ID588
Feature activation-7.03e-01

Pos logit contributions
 Skip+0.019
fires+0.019
 war+0.019
 MacDonald+0.019
 Alan+0.018
Neg logit contributions
itten-0.019
 nail-0.017
 arm-0.017
une-0.017
el-0.017
Token sharing
Token ID7373
Feature activation-5.42e+00

Pos logit contributions
fires+0.023
 MacDonald+0.023
 Skip+0.022
 war+0.022
brate+0.022
Neg logit contributions
itten-0.029
 nail-0.028
une-0.028
 arm-0.028
 knob-0.026
Token past
Token ID1613
Feature activation+3.47e+00

Pos logit contributions
 Skip+0.205
fires+0.201
 war+0.197
 Alan+0.195
 MacDonald+0.194
Neg logit contributions
itten-0.197
 nail-0.192
 arm-0.191
une-0.188
el-0.186
Tokenel
Token ID417
Feature activation+1.41e+01

Pos logit contributions
itten+0.088
une+0.077
el+0.068
 nail+0.068
 arm+0.067
Neg logit contributions
 war-0.185
 Skip-0.179
fires-0.176
 Alan-0.175
 MacDonald-0.175
Token colors
Token ID7577
Feature activation+1.38e+00

Pos logit contributions
itten+0.507
une+0.475
el+0.451
 arm+0.436
 nail+0.433
Neg logit contributions
 war-0.591
 Skip-0.583
 Alan-0.560
fires-0.555
 MacDonald-0.549
Token,
Token ID11
Feature activation-4.58e-01

Pos logit contributions
itten+0.054
une+0.052
el+0.050
 nail+0.049
 arm+0.048
Neg logit contributions
 war-0.053
 Skip-0.052
 Alan-0.050
fires-0.050
 MacDonald-0.049
Token could
Token ID714
Feature activation+5.07e+00

Pos logit contributions
 war+0.017
 Skip+0.017
fires+0.016
 Alan+0.016
 MacDonald+0.016
Neg logit contributions
itten-0.018
une-0.017
 nail-0.016
 arm-0.016
el-0.016
Token bring
Token ID2222
Feature activation+1.92e+00

Pos logit contributions
itten+0.220
une+0.204
el+0.192
 nail+0.191
 arm+0.190
Neg logit contributions
 war-0.179
 Skip-0.170
fires-0.165
 Alan-0.164
 MacDonald-0.163
Token happiness
Token ID12157
Feature activation-4.57e+00

Pos logit contributions
itten+0.080
une+0.077
el+0.075
 arm+0.075
 nail+0.075
Neg logit contributions
 war-0.063
fires-0.063
 Skip-0.062
 MacDonald-0.062
brate-0.059
Token the
Token ID262
Feature activation-1.17e+00

Pos logit contributions
itten+0.045
el+0.043
une+0.043
 arm+0.042
 nail+0.042
Neg logit contributions
 Skip-0.033
 war-0.033
 MacDonald-0.031
fires-0.031
 Alan-0.031
Token ocean
Token ID9151
Feature activation-3.40e+00

Pos logit contributions
 Skip+0.051
 Alan+0.049
 congratulated+0.048
 war+0.048
 MacDonald+0.048
Neg logit contributions
 arm-0.036
 knob-0.035
 nail-0.035
itten-0.034
une-0.033
Token.
Token ID13
Feature activation+2.27e-01

Pos logit contributions
 Skip+0.177
brate+0.167
 MacDonald+0.164
 war+0.164
Alan+0.162
Neg logit contributions
 arm-0.079
une-0.079
el-0.079
 knob-0.075
itten-0.074
Token The
Token ID383
Feature activation+8.66e-01

Pos logit contributions
itten+0.010
une+0.009
el+0.009
 nail+0.009
 arm+0.009
Neg logit contributions
 war-0.008
 Skip-0.008
 Alan-0.007
 cheered-0.007
fires-0.007
Token past
Token ID1613
Feature activation+3.39e+00

Pos logit contributions
 knob+0.029
itten+0.028
 arm+0.028
 nail+0.027
une+0.027
Neg logit contributions
 Skip-0.036
 MacDonald-0.035
 Alan-0.034
 congratulated-0.034
brate-0.034
Tokenel
Token ID417
Feature activation+1.41e+01

Pos logit contributions
itten+0.142
une+0.126
 injection+0.122
 arm+0.117
 nail+0.116
Neg logit contributions
 war-0.126
 seals-0.120
 they-0.117
 dolphins-0.113
fires-0.113
Token saw
Token ID2497
Feature activation+7.42e-01

Pos logit contributions
itten+0.601
une+0.565
el+0.540
 arm+0.526
 nail+0.524
Neg logit contributions
 war-0.501
 Skip-0.483
 MacDonald-0.460
 Alan-0.460
fires-0.459
Token things
Token ID1243
Feature activation-1.00e+00

Pos logit contributions
 arm+0.024
el+0.024
itten+0.023
une+0.023
 egg+0.023
Neg logit contributions
fires-0.030
 Skip-0.029
brate-0.029
 MacDonald-0.029
 war-0.028
Token so
Token ID523
Feature activation-2.77e-01

Pos logit contributions
 MacDonald+0.035
 war+0.035
 Skip+0.034
brate+0.032
 Alan+0.032
Neg logit contributions
itten-0.039
une-0.039
 bulb-0.038
 nail-0.038
 knob-0.038
Token beautiful
Token ID4950
Feature activation-2.33e+00

Pos logit contributions
 MacDonald+0.011
 Skip+0.011
brate+0.010
 Alan+0.010
 war+0.010
Neg logit contributions
 nail-0.009
el-0.009
 bulb-0.009
 knob-0.009
itten-0.008
Token that
Token ID326
Feature activation+6.68e-02

Pos logit contributions
 war+0.105
 Skip+0.100
Alan+0.099
 tournament+0.099
brate+0.098
Neg logit contributions
el-0.068
itten-0.066
 knob-0.063
 bulb-0.061
une-0.060
Token house
Token ID2156
Feature activation+1.57e+00

Pos logit contributions
itten+0.175
une+0.157
el+0.150
umb+0.149
 nail+0.140
Neg logit contributions
 war-0.209
 Skip-0.192
 Alan-0.188
fires-0.187
 cheered-0.187
Token to
Token ID284
Feature activation-1.91e-01

Pos logit contributions
itten+0.065
une+0.060
 arm+0.059
 knob+0.057
 nail+0.057
Neg logit contributions
 war-0.057
 Skip-0.056
 Alan-0.054
 MacDonald-0.054
brate-0.052
Token return
Token ID1441
Feature activation+3.76e+00

Pos logit contributions
 war+0.007
 Skip+0.007
 MacDonald+0.007
fires+0.007
 Alan+0.007
Neg logit contributions
itten-0.007
une-0.007
 nail-0.007
 arm-0.007
el-0.006
Token the
Token ID262
Feature activation-1.03e+00

Pos logit contributions
itten+0.187
une+0.172
 nail+0.161
umb+0.158
el+0.158
Neg logit contributions
 war-0.113
 Skip-0.107
 Alan-0.103
 cheered-0.102
fires-0.101
Token past
Token ID1613
Feature activation+3.49e+00

Pos logit contributions
 war+0.042
 Skip+0.038
fires+0.038
 Alan+0.037
 MacDonald+0.036
Neg logit contributions
itten-0.041
une-0.037
el-0.035
umb-0.034
 arm-0.033
Tokenel
Token ID417
Feature activation+1.41e+01

Pos logit contributions
itten+0.134
une+0.121
 nail+0.115
 injection+0.113
 arm+0.111
Neg logit contributions
 war-0.134
 they-0.122
fires-0.122
 Skip-0.122
 cheered-0.120
Token.
Token ID13
Feature activation+2.98e-01

Pos logit contributions
itten+0.583
 nail+0.513
une+0.510
umb+0.484
 injection+0.483
Neg logit contributions
 war-0.484
fires-0.456
 MacDonald-0.437
 games-0.435
 Skip-0.432
Token Mrs
Token ID9074
Feature activation-2.84e-01

Pos logit contributions
itten+0.013
une+0.012
el+0.011
 arm+0.011
 nail+0.011
Neg logit contributions
 war-0.011
 Skip-0.010
fires-0.010
 MacDonald-0.010
 Alan-0.010
Token.
Token ID13
Feature activation+2.99e-01

Pos logit contributions
 war+0.012
 Skip+0.011
brate+0.011
fires+0.011
 cheered+0.010
Neg logit contributions
itten-0.011
une-0.010
el-0.010
 arm-0.009
 knob-0.009
Token Green
Token ID3469
Feature activation+4.24e-01

Pos logit contributions
itten+0.013
une+0.012
el+0.012
 nail+0.012
 arm+0.011
Neg logit contributions
 war-0.010
 Skip-0.010
 Alan-0.010
fires-0.010
 MacDonald-0.009
Token welcomed
Token ID15846
Feature activation-3.46e-01

Pos logit contributions
itten+0.018
une+0.017
el+0.017
 arm+0.016
 nail+0.016
Neg logit contributions
 war-0.015
 Skip-0.015
fires-0.015
 MacDonald-0.014
brate-0.014
Token he
Token ID339
Feature activation+4.20e-02

Pos logit contributions
itten+0.088
une+0.082
el+0.080
 arm+0.079
 nail+0.079
Neg logit contributions
 war-0.060
 Skip-0.056
 MacDonald-0.056
fires-0.055
 Alan-0.053
Token loved
Token ID6151
Feature activation-7.49e-01

Pos logit contributions
itten+0.002
une+0.002
el+0.002
 nail+0.002
 arm+0.002
Neg logit contributions
 war-0.001
 Skip-0.001
fires-0.001
 Alan-0.001
 MacDonald-0.001
Token the
Token ID262
Feature activation-8.70e-01

Pos logit contributions
 war+0.024
 Skip+0.023
fires+0.023
 MacDonald+0.022
 Alan+0.022
Neg logit contributions
itten-0.034
une-0.032
 arm-0.031
 nail-0.031
el-0.031
Token pretty
Token ID2495
Feature activation+2.71e+00

Pos logit contributions
 war+0.035
 Skip+0.034
fires+0.033
 Alan+0.032
 MacDonald+0.032
Neg logit contributions
itten-0.034
une-0.031
 nail-0.029
 arm-0.029
el-0.029
Token past
Token ID1613
Feature activation+3.49e+00

Pos logit contributions
itten+0.091
une+0.083
el+0.076
 nail+0.075
 arm+0.074
Neg logit contributions
 war-0.123
 Skip-0.118
fires-0.115
 MacDonald-0.115
 Alan-0.114
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.058
une+0.049
 injection+0.047
 nail+0.041
umb+0.037
Neg logit contributions
 seals-0.199
 war-0.198
 they-0.196
 Skip-0.195
 Alan-0.194
Token.
Token ID13
Feature activation+4.76e-01

Pos logit contributions
itten+0.540
une+0.483
 nail+0.472
 injection+0.452
 arm+0.445
Neg logit contributions
 war-0.511
 Skip-0.494
 Alan-0.491
fires-0.490
 seals-0.484
Token As
Token ID1081
Feature activation+2.27e+00

Pos logit contributions
itten+0.025
une+0.023
 nail+0.023
 knob+0.022
el+0.022
Neg logit contributions
 Skip-0.013
 cheered-0.012
 Alan-0.012
 war-0.012
 they-0.011
Token he
Token ID339
Feature activation+8.90e-02

Pos logit contributions
itten+0.109
 arm+0.098
une+0.098
el+0.098
 nail+0.098
Neg logit contributions
 war-0.066
 MacDonald-0.065
fires-0.064
brate-0.062
 Skip-0.060
Token walked
Token ID6807
Feature activation-8.44e-01

Pos logit contributions
itten+0.004
une+0.004
el+0.004
 nail+0.004
 arm+0.004
Neg logit contributions
 war-0.003
 Skip-0.003
fires-0.002
 Alan-0.002
 MacDonald-0.002
Token away
Token ID1497
Feature activation+1.34e-01

Pos logit contributions
 war+0.035
 MacDonald+0.033
fires+0.033
 Skip+0.032
brate+0.032
Neg logit contributions
itten-0.031
une-0.029
el-0.027
 arm-0.027
 nail-0.027
Token past
Token ID1613
Feature activation+3.45e+00

Pos logit contributions
fires+0.060
 MacDonald+0.059
 Skip+0.056
 war+0.056
brate+0.056
Neg logit contributions
itten-0.064
 nail-0.060
une-0.060
 arm-0.059
 knob-0.058
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.151
une+0.138
 nail+0.127
umb+0.125
 arm+0.125
Neg logit contributions
 war-0.123
 Skip-0.119
 Alan-0.114
 MacDonald-0.111
fires-0.110
Token.
Token ID13
Feature activation+4.44e-01

Pos logit contributions
itten+0.589
une+0.545
el+0.512
 nail+0.509
 arm+0.504
Neg logit contributions
 war-0.512
 Skip-0.487
fires-0.473
 Alan-0.469
 MacDonald-0.469
Token The
Token ID383
Feature activation+7.09e-01

Pos logit contributions
itten+0.018
une+0.017
el+0.016
 nail+0.016
 arm+0.016
Neg logit contributions
 war-0.016
fires-0.016
 Skip-0.016
 MacDonald-0.015
brate-0.015
Token past
Token ID1613
Feature activation+3.44e+00

Pos logit contributions
itten+0.024
 arm+0.022
une+0.022
 nail+0.022
 knob+0.021
Neg logit contributions
 Skip-0.030
fires-0.029
 MacDonald-0.029
 war-0.029
brate-0.028
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.132
une+0.119
 nail+0.108
 arm+0.107
 knob+0.105
Neg logit contributions
 war-0.143
 Skip-0.132
 Alan-0.130
fires-0.129
 cheered-0.127
Token was
Token ID373
Feature activation-7.93e-02

Pos logit contributions
itten+0.537
une+0.498
el+0.468
 nail+0.462
 arm+0.461
Neg logit contributions
 war-0.566
 Skip-0.545
fires-0.530
 MacDonald-0.528
 Alan-0.524
Token bright
Token ID6016
Feature activation+1.79e+00

Pos logit contributions
 MacDonald+0.003
fires+0.003
 war+0.003
 Skip+0.003
brate+0.002
Neg logit contributions
itten-0.003
une-0.003
 arm-0.003
 nail-0.003
 knob-0.003
Token and
Token ID290
Feature activation+1.49e-01

Pos logit contributions
itten+0.063
une+0.059
el+0.058
 arm+0.057
 nail+0.056
Neg logit contributions
 Skip-0.075
fires-0.075
 war-0.074
brate-0.072
 MacDonald-0.071
Token colourful
Token ID44799
Feature activation+1.69e+00

Pos logit contributions
itten+0.006
 nail+0.005
 arm+0.005
 knob+0.005
une+0.005
Neg logit contributions
fires-0.005
 MacDonald-0.005
 war-0.005
brate-0.005
 Skip-0.005
Token and
Token ID290
Feature activation+1.79e-01

Pos logit contributions
itten+0.058
 arm+0.057
 nail+0.056
une+0.056
 knob+0.054
Neg logit contributions
brate-0.068
 war-0.067
fires-0.066
 Skip-0.066
Alan-0.066
Token sign
Token ID1051
Feature activation+2.95e-01

Pos logit contributions
 Skip+0.063
 war+0.062
fires+0.062
 MacDonald+0.061
 Alan+0.061
Neg logit contributions
itten-0.062
une-0.057
 nail-0.055
 arm-0.055
 knob-0.055
Token that
Token ID326
Feature activation+1.14e-01

Pos logit contributions
itten+0.012
une+0.011
 arm+0.011
 knob+0.011
 nail+0.010
Neg logit contributions
 war-0.011
 Skip-0.011
 MacDonald-0.010
fires-0.010
 Alan-0.010
Token said
Token ID531
Feature activation+6.97e-01

Pos logit contributions
itten+0.005
une+0.005
 nail+0.005
 knob+0.005
el+0.005
Neg logit contributions
 war-0.004
 Skip-0.004
 MacDonald-0.003
 Alan-0.003
fires-0.003
Token "
Token ID366
Feature activation+1.56e+00

Pos logit contributions
une+0.026
itten+0.026
 arm+0.024
 knob+0.024
 nail+0.023
Neg logit contributions
 war-0.025
 Skip-0.025
 MacDonald-0.025
 tournament-0.025
 Alan-0.025
TokenHot
Token ID21352
Feature activation+4.81e+00

Pos logit contributions
itten+0.068
une+0.063
el+0.059
 nail+0.059
 arm+0.059
Neg logit contributions
 war-0.054
 Skip-0.052
fires-0.051
 MacDonald-0.050
 Alan-0.050
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.189
une+0.175
el+0.164
 arm+0.161
 nail+0.159
Neg logit contributions
 war-0.189
 Skip-0.183
 Alan-0.178
fires-0.177
 cheered-0.177
Token".
Token ID1911
Feature activation-2.84e+00

Pos logit contributions
itten+0.579
une+0.539
el+0.506
 arm+0.500
 nail+0.499
Neg logit contributions
 war-0.521
 Skip-0.501
fires-0.484
 Alan-0.482
 MacDonald-0.480
Token She
Token ID1375
Feature activation+1.47e+00

Pos logit contributions
 war+0.104
 Skip+0.099
 MacDonald+0.096
 Alan+0.096
fires+0.096
Neg logit contributions
itten-0.118
une-0.111
el-0.105
 nail-0.104
 arm-0.104
Token kept
Token ID4030
Feature activation+9.89e-01

Pos logit contributions
itten+0.067
une+0.062
el+0.059
 nail+0.058
 arm+0.058
Neg logit contributions
 war-0.048
 Skip-0.046
fires-0.045
 Alan-0.044
 MacDonald-0.044
Token working
Token ID1762
Feature activation-8.50e-01

Pos logit contributions
itten+0.048
une+0.044
el+0.043
 arm+0.042
 nail+0.042
Neg logit contributions
 war-0.030
 Skip-0.028
fires-0.028
 MacDonald-0.027
 Alan-0.027
Token until
Token ID1566
Feature activation+2.27e+00

Pos logit contributions
 war+0.030
 Skip+0.029
 MacDonald+0.029
 Alan+0.028
fires+0.027
Neg logit contributions
itten-0.036
une-0.033
 arm-0.032
 nail-0.032
el-0.032
Token
Token ID220
Feature activation+3.27e+00

Pos logit contributions
itten+0.015
une+0.014
el+0.013
 arm+0.013
 nail+0.013
Neg logit contributions
 war-0.012
 Skip-0.011
 cheered-0.011
 Alan-0.011
 MacDonald-0.011
Token
Token ID198
Feature activation-1.58e-01

Pos logit contributions
itten+0.181
 egg+0.170
une+0.166
 knob+0.165
 arm+0.164
Neg logit contributions
 cheered-0.068
 they-0.066
 war-0.065
 Skip-0.063
fires-0.062
TokenSu
Token ID5606
Feature activation+4.48e+00

Pos logit contributions
 cheered+0.005
 war+0.005
 Skip+0.005
 congratulated+0.004
 Alan+0.004
Neg logit contributions
itten-0.007
une-0.007
 egg-0.007
el-0.007
 arm-0.007
Tokenzie
Token ID49746
Feature activation+1.38e+00

Pos logit contributions
itten+0.156
une+0.146
 nail+0.146
 clip+0.144
 finger+0.140
Neg logit contributions
 cheered-0.149
 MacDonald-0.149
 Alan-0.149
 congratulated-0.149
 Skip-0.147
Token y
Token ID331
Feature activation+1.40e+00

Pos logit contributions
itten+0.057
une+0.052
 arm+0.052
el+0.051
 nail+0.051
Neg logit contributions
 war-0.051
fires-0.050
 Skip-0.049
 MacDonald-0.048
 Alan-0.046
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.027
une+0.023
 nail+0.021
 arm+0.020
 knob+0.020
Neg logit contributions
 war-0.080
 Skip-0.077
 Alan-0.077
 MacDonald-0.076
fires-0.075
Tokenped
Token ID9124
Feature activation+1.98e+00

Pos logit contributions
itten+0.628
une+0.589
 nail+0.557
 knob+0.554
umb+0.546
Neg logit contributions
 war-0.407
 cheered-0.405
 Skip-0.400
 Alan-0.373
fires-0.369
Token in
Token ID287
Feature activation+3.66e-02

Pos logit contributions
 arm+0.062
itten+0.057
el+0.055
une+0.053
 finger+0.049
Neg logit contributions
fires-0.094
brate-0.092
 war-0.090
 MacDonald-0.090
 seals-0.089
Token surprise
Token ID5975
Feature activation+4.47e-01

Pos logit contributions
itten+0.002
une+0.002
el+0.001
 arm+0.001
 nail+0.001
Neg logit contributions
 war-0.001
 Skip-0.001
fires-0.001
 MacDonald-0.001
 Alan-0.001
Token,
Token ID11
Feature activation-4.15e-01

Pos logit contributions
itten+0.018
el+0.016
 arm+0.016
une+0.016
 nail+0.016
Neg logit contributions
 war-0.017
 Skip-0.017
fires-0.016
 MacDonald-0.016
 Alan-0.016
Token "
Token ID366
Feature activation+1.68e+00

Pos logit contributions
 war+0.015
 Skip+0.014
fires+0.014
 MacDonald+0.013
brate+0.013
Neg logit contributions
itten-0.018
une-0.016
 arm-0.016
 nail-0.016
 knob-0.015
Token lying
Token ID9105
Feature activation-6.67e-01

Pos logit contributions
 war+0.005
 MacDonald+0.005
 Skip+0.005
fires+0.005
 Alan+0.005
Neg logit contributions
itten-0.008
une-0.007
 arm-0.007
el-0.007
 nail-0.007
Token there
Token ID612
Feature activation+5.72e-01

Pos logit contributions
 war+0.022
 MacDonald+0.021
 Skip+0.021
fires+0.021
 Alan+0.020
Neg logit contributions
itten-0.030
une-0.028
el-0.027
 arm-0.027
 knob-0.027
Token,
Token ID11
Feature activation-4.88e-01

Pos logit contributions
itten+0.026
une+0.024
el+0.024
 arm+0.023
 knob+0.023
Neg logit contributions
 war-0.019
 Skip-0.018
fires-0.018
 MacDonald-0.017
 Alan-0.017
Token the
Token ID262
Feature activation-9.42e-01

Pos logit contributions
 war+0.020
 Skip+0.019
fires+0.019
 MacDonald+0.019
 Alan+0.018
Neg logit contributions
itten-0.018
une-0.016
 arm-0.016
 knob-0.016
 nail-0.016
Token past
Token ID1613
Feature activation+3.54e+00

Pos logit contributions
 war+0.040
 Skip+0.038
fires+0.037
 MacDonald+0.037
 cheered+0.037
Neg logit contributions
itten-0.034
une-0.031
el-0.029
 nail-0.029
umb-0.028
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.125
une+0.118
 nail+0.113
 arm+0.104
umb+0.103
Neg logit contributions
 war-0.141
 Skip-0.137
 Alan-0.134
 MacDonald-0.132
fires-0.132
Token pet
Token ID4273
Feature activation+3.14e+00

Pos logit contributions
itten+0.568
une+0.519
 nail+0.493
umb+0.484
el+0.483
Neg logit contributions
 war-0.510
fires-0.487
 Skip-0.480
 cheered-0.473
 MacDonald-0.470
Tokenals
Token ID874
Feature activation+2.32e+00

Pos logit contributions
itten+0.115
une+0.105
el+0.099
 arm+0.097
 knob+0.096
Neg logit contributions
 war-0.135
 Skip-0.128
fires-0.128
 MacDonald-0.125
brate-0.124
Token started
Token ID2067
Feature activation+4.15e+00

Pos logit contributions
itten+0.110
une+0.102
el+0.098
 nail+0.097
 arm+0.096
Neg logit contributions
 war-0.073
 Skip-0.071
 MacDonald-0.068
fires-0.067
 Alan-0.067
Token to
Token ID284
Feature activation-3.21e-01

Pos logit contributions
itten+0.162
une+0.151
 arm+0.148
el+0.148
 nail+0.141
Neg logit contributions
 Skip-0.161
 war-0.160
brate-0.154
fires-0.153
 MacDonald-0.152
Token bloom
Token ID29955
Feature activation+4.04e-01

Pos logit contributions
 war+0.013
 Skip+0.013
fires+0.012
 MacDonald+0.012
 Alan+0.012
Neg logit contributions
itten-0.012
une-0.011
el-0.011
 nail-0.011
 arm-0.011
Token he
Token ID339
Feature activation+3.73e-02

Pos logit contributions
 war+0.015
brate+0.014
fires+0.014
 MacDonald+0.014
 Skip+0.014
Neg logit contributions
itten-0.021
une-0.020
 nail-0.019
 arm-0.019
el-0.019
Token was
Token ID373
Feature activation-3.95e-02

Pos logit contributions
itten+0.002
une+0.002
el+0.001
 arm+0.001
 nail+0.001
Neg logit contributions
 war-0.001
 Skip-0.001
fires-0.001
 MacDonald-0.001
 Alan-0.001
Token able
Token ID1498
Feature activation-2.08e-01

Pos logit contributions
 war+0.001
 Skip+0.001
 MacDonald+0.001
fires+0.001
 Alan+0.001
Neg logit contributions
itten-0.002
une-0.002
 arm-0.002
el-0.002
 nail-0.002
Token to
Token ID284
Feature activation-1.76e-01

Pos logit contributions
 war+0.008
 Skip+0.008
 MacDonald+0.008
fires+0.008
brate+0.008
Neg logit contributions
itten-0.008
une-0.007
 arm-0.007
 nail-0.007
el-0.007
Token kne
Token ID24813
Feature activation+1.94e+00

Pos logit contributions
 war+0.006
 Skip+0.006
fires+0.006
 Alan+0.006
 cheered+0.006
Neg logit contributions
itten-0.008
une-0.007
el-0.007
 arm-0.006
 nail-0.006
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.028
une+0.026
 nail+0.023
 knob+0.022
 injection+0.019
Neg logit contributions
 Alan-0.113
 cheered-0.113
 war-0.113
 Skip-0.110
Alan-0.108
Token before
Token ID878
Feature activation+1.36e+00

Pos logit contributions
itten+0.637
une+0.590
 nail+0.571
umb+0.542
 knob+0.523
Neg logit contributions
 war-0.433
 Skip-0.425
fires-0.409
 Alan-0.408
 cheered-0.401
Token the
Token ID262
Feature activation-1.03e+00

Pos logit contributions
itten+0.058
el+0.054
 arm+0.054
une+0.053
 nail+0.052
Neg logit contributions
fires-0.046
brate-0.045
 MacDonald-0.045
 war-0.043
 Skip-0.042
Token star
Token ID3491
Feature activation+1.55e+00

Pos logit contributions
 war+0.043
 Skip+0.038
 laughter+0.038
 crowd+0.037
 MacDonald+0.037
Neg logit contributions
itten-0.037
umb-0.034
une-0.034
el-0.032
idget-0.030
Token and
Token ID290
Feature activation+7.76e-02

Pos logit contributions
itten+0.069
une+0.064
el+0.060
 nail+0.060
 arm+0.060
Neg logit contributions
 war-0.053
 Skip-0.050
fires-0.049
 Alan-0.048
 MacDonald-0.048
Token make
Token ID787
Feature activation+8.46e-01

Pos logit contributions
itten+0.003
une+0.003
 arm+0.003
 nail+0.003
el+0.003
Neg logit contributions
 war-0.003
 MacDonald-0.003
fires-0.003
 Skip-0.003
brate-0.003
Token and
Token ID290
Feature activation+2.25e-02

Pos logit contributions
itten+0.242
une+0.224
el+0.212
 nail+0.212
 arm+0.212
Neg logit contributions
 war-0.204
 Skip-0.197
fires-0.189
 MacDonald-0.188
 Alan-0.187
Token bought
Token ID5839
Feature activation+2.27e+00

Pos logit contributions
itten+0.001
une+0.001
el+0.001
umb+0.001
 arm+0.001
Neg logit contributions
 cheered-0.001
 war-0.001
 they-0.001
fires-0.001
 congratulated-0.001
Token lots
Token ID6041
Feature activation-1.18e+00

Pos logit contributions
itten+0.117
une+0.108
umb+0.101
el+0.101
 nail+0.100
Neg logit contributions
 war-0.064
 Skip-0.059
 cheered-0.059
 Alan-0.058
 games-0.056
Token of
Token ID286
Feature activation+2.62e+00

Pos logit contributions
 war+0.036
 cheered+0.034
 games+0.033
 they+0.033
 Skip+0.032
Neg logit contributions
itten-0.056
une-0.052
umb-0.049
 arm-0.049
 nail-0.048
Token past
Token ID1613
Feature activation+3.43e+00

Pos logit contributions
itten+0.106
une+0.100
umb+0.093
el+0.086
 arm+0.086
Neg logit contributions
 war-0.104
 cheered-0.098
 games-0.097
 jokes-0.093
 performers-0.092
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.091
une+0.079
 injection+0.075
umb+0.074
 arm+0.065
Neg logit contributions
 they-0.174
 war-0.173
 games-0.167
 cheered-0.166
 MacDonald-0.163
Token colors
Token ID7577
Feature activation+1.33e+00

Pos logit contributions
itten+0.537
une+0.484
 nail+0.453
 arm+0.449
umb+0.446
Neg logit contributions
 war-0.550
fires-0.516
 MacDonald-0.514
 cheered-0.509
 games-0.500
Token.
Token ID13
Feature activation+2.69e-01

Pos logit contributions
itten+0.060
une+0.056
el+0.052
 nail+0.052
 arm+0.052
Neg logit contributions
 war-0.045
 Skip-0.042
fires-0.041
 MacDonald-0.041
 Alan-0.041
Token She
Token ID1375
Feature activation+1.54e+00

Pos logit contributions
itten+0.012
une+0.010
el+0.010
 egg+0.010
umb+0.010
Neg logit contributions
 war-0.010
 games-0.009
 Skip-0.009
 cheered-0.009
 they-0.009
Token had
Token ID550
Feature activation-2.92e-01

Pos logit contributions
itten+0.082
une+0.077
umb+0.074
 injection+0.071
 axe+0.071
Neg logit contributions
 cheered-0.044
 they-0.040
 celebrated-0.038
 congratulated-0.037
 impressed-0.036
Token yellow
Token ID7872
Feature activation+4.88e+00

Pos logit contributions
 war+0.008
 Skip+0.007
fires+0.007
 cheered+0.007
 Alan+0.007
Neg logit contributions
itten-0.015
une-0.014
el-0.014
 nail-0.013
 arm-0.013
Token a
Token ID257
Feature activation-1.62e+00

Pos logit contributions
 MacDonald+0.091
fires+0.090
 chatting+0.090
 seals+0.086
brate+0.086
Neg logit contributions
 arm-0.071
 nail-0.069
 block-0.067
 foot-0.066
 screw-0.062
Token game
Token ID983
Feature activation-3.99e+00

Pos logit contributions
 MacDonald+0.047
fires+0.046
 cheered+0.045
 Skip+0.044
 war+0.043
Neg logit contributions
itten-0.076
 nail-0.072
une-0.071
 arm-0.070
 knob-0.069
Token with
Token ID351
Feature activation-6.64e-01

Pos logit contributions
 war+0.141
 Skip+0.136
 MacDonald+0.136
fires+0.134
 Alan+0.130
Neg logit contributions
itten-0.166
une-0.155
 nail-0.150
 arm-0.148
el-0.145
Token a
Token ID257
Feature activation-1.62e+00

Pos logit contributions
 MacDonald+0.023
fires+0.022
brate+0.021
 war+0.021
 Skip+0.021
Neg logit contributions
itten-0.026
el-0.026
 arm-0.026
 nail-0.026
une-0.026
Token past
Token ID1613
Feature activation+3.45e+00

Pos logit contributions
fires+0.060
 MacDonald+0.059
 Skip+0.056
 war+0.056
brate+0.056
Neg logit contributions
itten-0.064
 nail-0.060
une-0.060
 arm-0.059
 knob-0.058
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.151
une+0.138
 nail+0.127
umb+0.125
 arm+0.125
Neg logit contributions
 war-0.123
 Skip-0.119
 Alan-0.114
 MacDonald-0.111
fires-0.110
Token.
Token ID13
Feature activation+4.44e-01

Pos logit contributions
itten+0.589
une+0.545
el+0.512
 nail+0.509
 arm+0.504
Neg logit contributions
 war-0.512
 Skip-0.487
fires-0.473
 Alan-0.469
 MacDonald-0.469
Token The
Token ID383
Feature activation+7.09e-01

Pos logit contributions
itten+0.018
une+0.017
el+0.016
 nail+0.016
 arm+0.016
Neg logit contributions
 war-0.016
fires-0.016
 Skip-0.016
 MacDonald-0.015
brate-0.015
Token past
Token ID1613
Feature activation+3.44e+00

Pos logit contributions
itten+0.024
 arm+0.022
une+0.022
 nail+0.022
 knob+0.021
Neg logit contributions
 Skip-0.030
fires-0.029
 MacDonald-0.029
 war-0.029
brate-0.028
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.132
une+0.119
 nail+0.108
 arm+0.107
 knob+0.105
Neg logit contributions
 war-0.143
 Skip-0.132
 Alan-0.130
fires-0.129
 cheered-0.127
Token was
Token ID373
Feature activation-7.93e-02

Pos logit contributions
itten+0.537
une+0.498
el+0.468
 nail+0.462
 arm+0.461
Neg logit contributions
 war-0.566
 Skip-0.545
fires-0.530
 MacDonald-0.528
 Alan-0.524
Token th
Token ID294
Feature activation-3.47e-01

Pos logit contributions
 Alan+0.056
 Skip+0.056
fires+0.055
 seals+0.054
 celebrating+0.054
Neg logit contributions
itten-0.070
 knob-0.069
 nail-0.068
 arm-0.066
 bulb-0.065
Tokenud
Token ID463
Feature activation+5.51e+00

Pos logit contributions
 cheered+0.013
 war+0.012
 congratulated+0.012
 MacDonald+0.012
 celebrated+0.012
Neg logit contributions
itten-0.013
une-0.013
 knob-0.012
 nail-0.012
 axe-0.012
Token as
Token ID355
Feature activation-1.16e+00

Pos logit contributions
itten+0.248
une+0.234
el+0.219
 nail+0.216
 arm+0.214
Neg logit contributions
 war-0.181
 Skip-0.171
 cheered-0.166
fires-0.165
 Alan-0.163
Token the
Token ID262
Feature activation-1.18e+00

Pos logit contributions
 war+0.047
 MacDonald+0.045
 Skip+0.044
fires+0.044
brate+0.044
Neg logit contributions
itten-0.043
une-0.040
 nail-0.039
 knob-0.038
 arm-0.038
Token past
Token ID1613
Feature activation+3.38e+00

Pos logit contributions
 war+0.051
 cheered+0.045
 games+0.045
 celebrating+0.045
 laughter+0.044
Neg logit contributions
itten-0.044
une-0.040
umb-0.037
el-0.037
 injection-0.033
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.061
une+0.059
 axe+0.053
 injection+0.045
 nail+0.045
Neg logit contributions
 they-0.177
 war-0.175
 Skip-0.169
 MacDonald-0.169
 cheered-0.168
Token landed
Token ID11406
Feature activation+2.29e+00

Pos logit contributions
itten+0.545
une+0.483
 nail+0.456
umb+0.453
 arm+0.447
Neg logit contributions
 war-0.532
fires-0.506
 cheered-0.497
 MacDonald-0.495
 performers-0.484
Token on
Token ID319
Feature activation+3.32e-01

Pos logit contributions
itten+0.103
une+0.097
el+0.093
 arm+0.091
 nail+0.091
Neg logit contributions
 war-0.078
 Skip-0.077
 Alan-0.072
 MacDonald-0.072
fires-0.072
Token the
Token ID262
Feature activation-1.16e+00

Pos logit contributions
itten+0.017
une+0.016
el+0.015
 nail+0.015
 arm+0.015
Neg logit contributions
 war-0.010
 Skip-0.009
fires-0.009
 Alan-0.009
 MacDonald-0.008
Token floor
Token ID4314
Feature activation+2.27e+00

Pos logit contributions
 war+0.051
fires+0.047
 games+0.047
 cheered+0.047
 celebrating+0.046
Neg logit contributions
itten-0.041
une-0.035
el-0.034
umb-0.032
 injection-0.030
Token.
Token ID13
Feature activation+3.99e-01

Pos logit contributions
itten+0.097
une+0.090
el+0.085
 nail+0.085
 arm+0.084
Neg logit contributions
 war-0.081
 Skip-0.078
fires-0.075
 MacDonald-0.075
 Alan-0.074
Token needed
Token ID2622
Feature activation+3.45e+00

Pos logit contributions
itten+0.070
une+0.066
el+0.062
 nail+0.062
 arm+0.061
Neg logit contributions
 war-0.040
 Skip-0.037
fires-0.036
 cheered-0.036
 MacDonald-0.035
Token to
Token ID284
Feature activation-4.11e-01

Pos logit contributions
itten+0.195
une+0.180
umb+0.175
el+0.170
 knob+0.162
Neg logit contributions
 war-0.087
 they-0.076
 games-0.075
 celebrating-0.069
 jokes-0.068
Token clean
Token ID3424
Feature activation+9.21e-01

Pos logit contributions
 war+0.014
 Skip+0.013
fires+0.013
 cheered+0.013
 games+0.013
Neg logit contributions
itten-0.018
une-0.017
el-0.015
umb-0.015
 nail-0.015
Token her
Token ID607
Feature activation+3.95e+00

Pos logit contributions
itten+0.042
une+0.039
umb+0.035
 nail+0.034
el+0.034
Neg logit contributions
 war-0.032
 Skip-0.030
 games-0.029
 MacDonald-0.029
fires-0.029
Token past
Token ID1613
Feature activation+3.21e+00

Pos logit contributions
itten+0.177
une+0.156
umb+0.148
el+0.142
 nail+0.137
Neg logit contributions
 war-0.148
 games-0.138
 jokes-0.129
fires-0.129
 celebrating-0.126
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.102
une+0.085
 injection+0.079
umb+0.078
 stem+0.075
Neg logit contributions
 war-0.146
 games-0.143
 they-0.137
 sports-0.132
 players-0.131
Token toys
Token ID14958
Feature activation+5.01e-01

Pos logit contributions
itten+0.588
une+0.518
 nail+0.490
 injection+0.478
 knob+0.473
Neg logit contributions
 war-0.494
 games-0.482
fires-0.457
 jokes-0.451
 MacDonald-0.438
Token before
Token ID878
Feature activation+1.33e+00

Pos logit contributions
itten+0.024
une+0.022
el+0.020
 nail+0.020
 arm+0.020
Neg logit contributions
 war-0.016
fires-0.015
 Skip-0.015
 cheered-0.014
 Alan-0.014
Token they
Token ID484
Feature activation-5.12e+00

Pos logit contributions
itten+0.058
une+0.053
 arm+0.053
 nail+0.052
el+0.052
Neg logit contributions
 Skip-0.045
 war-0.044
 Alan-0.043
 MacDonald-0.043
fires-0.043
Token could
Token ID714
Feature activation+5.12e+00

Pos logit contributions
 war+0.154
 cheered+0.141
fires+0.137
 they+0.134
 celebrated+0.129
Neg logit contributions
itten-0.257
une-0.232
el-0.218
umb-0.216
 nail-0.213
Token go
Token ID467
Feature activation+9.65e-01

Pos logit contributions
itten+0.277
une+0.243
umb+0.235
 egg+0.229
el+0.225
Neg logit contributions
 war-0.135
 they-0.132
 cheered-0.114
 games-0.113
 celebrating-0.111
Token glad
Token ID9675
Feature activation-2.62e+00

Pos logit contributions
 MacDonald+0.007
 Skip+0.007
 war+0.007
fires+0.007
brate+0.007
Neg logit contributions
itten-0.010
une-0.010
 arm-0.010
 nail-0.009
el-0.009
Token of
Token ID286
Feature activation+2.70e+00

Pos logit contributions
brate+0.107
fires+0.106
 war+0.102
 MacDonald+0.098
 tournament+0.095
Neg logit contributions
 arm-0.085
itten-0.083
el-0.081
une-0.079
 nail-0.076
Token his
Token ID465
Feature activation+2.98e+00

Pos logit contributions
el+0.102
 arm+0.099
itten+0.098
une+0.097
 nail+0.097
Neg logit contributions
 MacDonald-0.092
fires-0.091
 war-0.091
brate-0.090
 cheered-0.089
Token cool
Token ID3608
Feature activation+2.79e+00

Pos logit contributions
itten+0.124
une+0.115
el+0.109
 nail+0.108
 arm+0.108
Neg logit contributions
 war-0.110
 Skip-0.106
fires-0.103
 MacDonald-0.102
 Alan-0.102
Token past
Token ID1613
Feature activation+3.48e+00

Pos logit contributions
itten+0.086
une+0.077
el+0.071
 nail+0.070
 arm+0.070
Neg logit contributions
 war-0.134
 Skip-0.130
fires-0.127
 Alan-0.126
 MacDonald-0.126
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.079
une+0.071
 nail+0.060
 arm+0.057
umb+0.056
Neg logit contributions
 war-0.193
 Skip-0.187
 MacDonald-0.185
 Alan-0.184
fires-0.183
Token shirt
Token ID10147
Feature activation+3.58e+00

Pos logit contributions
itten+0.564
une+0.522
 nail+0.487
el+0.486
 arm+0.480
Neg logit contributions
 war-0.536
 Skip-0.513
fires-0.500
 MacDonald-0.497
 Alan-0.496
Token.
Token ID13
Feature activation+2.63e-01

Pos logit contributions
itten+0.134
une+0.126
 arm+0.123
 nail+0.117
el+0.116
Neg logit contributions
 war-0.145
 Skip-0.142
 MacDonald-0.138
brate-0.137
fires-0.137
Token<|endoftext|>
Token ID50256
Feature activation-3.93e+00

Pos logit contributions
itten+0.010
une+0.009
el+0.009
 arm+0.009
 nail+0.009
Neg logit contributions
 war-0.010
fires-0.010
 MacDonald-0.009
brate-0.009
 Skip-0.009
TokenJack
Token ID14295
Feature activation-3.15e+00

Pos logit contributions
 war+0.171
fires+0.160
brate+0.159
 MacDonald+0.158
 jokes+0.157
Neg logit contributions
itten-0.131
une-0.121
el-0.121
 arm-0.113
umb-0.112
Token was
Token ID373
Feature activation-1.25e-01

Pos logit contributions
 war+0.111
 Skip+0.106
fires+0.104
 MacDonald+0.102
 Alan+0.101
Neg logit contributions
itten-0.136
une-0.127
el-0.121
 arm-0.119
 nail-0.119
Token Let
Token ID3914
Feature activation+1.31e+00

Pos logit contributions
itten+0.020
une+0.018
el+0.018
 nail+0.017
 arm+0.017
Neg logit contributions
 war-0.015
 Skip-0.014
 Alan-0.013
fires-0.013
 MacDonald-0.013
Token's
Token ID338
Feature activation+4.81e+00

Pos logit contributions
itten+0.048
une+0.045
el+0.044
 arm+0.043
 nail+0.042
Neg logit contributions
fires-0.053
 war-0.053
 Skip-0.052
 MacDonald-0.051
 Alan-0.050
Token tie
Token ID9839
Feature activation+4.03e+00

Pos logit contributions
itten+0.224
une+0.196
umb+0.187
el+0.185
 arm+0.182
Neg logit contributions
 war-0.161
 Skip-0.147
 Alan-0.143
brate-0.137
 cheered-0.135
Token your
Token ID534
Feature activation+1.35e+00

Pos logit contributions
itten+0.183
une+0.173
el+0.170
 arm+0.166
 nail+0.166
Neg logit contributions
 war-0.126
fires-0.123
 MacDonald-0.118
 Skip-0.118
 cheered-0.116
Token sho
Token ID7354
Feature activation+4.26e+00

Pos logit contributions
itten+0.052
umb+0.048
une+0.048
el+0.046
olk+0.045
Neg logit contributions
 war-0.051
 Skip-0.050
 games-0.048
 MacDonald-0.046
 jokes-0.046
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
 knob+0.117
itten+0.098
 nail+0.098
une+0.093
 bulb+0.093
Neg logit contributions
 Skip-0.205
 Alan-0.203
 cheered-0.192
Alan-0.187
 congratulated-0.185
Tokenaces
Token ID2114
Feature activation+2.40e+00

Pos logit contributions
itten+0.525
 nail+0.474
 knob+0.463
une+0.461
 bulb+0.444
Neg logit contributions
 Skip-0.498
 war-0.487
 games-0.486
 MacDonald-0.463
fires-0.457
Token together
Token ID1978
Feature activation-4.34e+00

Pos logit contributions
itten+0.112
une+0.105
el+0.099
 nail+0.098
 arm+0.098
Neg logit contributions
 war-0.076
 Skip-0.072
fires-0.070
 Alan-0.069
 MacDonald-0.069
Token so
Token ID523
Feature activation-1.29e-01

Pos logit contributions
 war+0.146
 Skip+0.139
fires+0.135
 Alan+0.133
 cheered+0.132
Neg logit contributions
itten-0.195
une-0.180
el-0.170
 nail-0.169
 arm-0.166
Token they
Token ID484
Feature activation-5.04e+00

Pos logit contributions
 war+0.003
 MacDonald+0.003
fires+0.003
 Skip+0.003
 Alan+0.003
Neg logit contributions
itten-0.007
une-0.006
 nail-0.006
el-0.006
 arm-0.006
Token won
Token ID1839
Feature activation-1.38e+00

Pos logit contributions
 war+0.190
 Skip+0.181
fires+0.176
 Alan+0.174
 MacDonald+0.174
Neg logit contributions
itten-0.207
une-0.189
el-0.178
 arm-0.176
 nail-0.176
Token to
Token ID284
Feature activation-3.19e-01

Pos logit contributions
itten+0.037
une+0.034
el+0.032
 nail+0.032
umb+0.032
Neg logit contributions
 war-0.022
 Skip-0.020
 Alan-0.019
fires-0.019
 jokes-0.019
Token leave
Token ID2666
Feature activation-1.03e+00

Pos logit contributions
 war+0.013
 Skip+0.013
fires+0.013
 MacDonald+0.012
 Alan+0.012
Neg logit contributions
itten-0.012
une-0.011
 arm-0.011
 nail-0.011
el-0.011
Token the
Token ID262
Feature activation-9.34e-01

Pos logit contributions
 war+0.035
 Skip+0.033
fires+0.032
 MacDonald+0.032
 Alan+0.032
Neg logit contributions
itten-0.045
une-0.042
el-0.040
 arm-0.040
 nail-0.040
Token mail
Token ID6920
Feature activation+3.59e+00

Pos logit contributions
 war+0.044
 Skip+0.043
fires+0.042
 Alan+0.042
 MacDonald+0.042
Neg logit contributions
itten-0.029
une-0.026
el-0.024
 nail-0.024
 arm-0.024
Token und
Token ID3318
Feature activation+2.98e+00

Pos logit contributions
itten+0.155
une+0.143
el+0.135
 nail+0.133
 arm+0.132
Neg logit contributions
 war-0.128
 Skip-0.121
fires-0.118
 Alan-0.116
 cheered-0.116
Tokenel
Token ID417
Feature activation+1.40e+01

Pos logit contributions
itten+0.112
une+0.101
 nail+0.099
 knob+0.098
 arm+0.095
Neg logit contributions
 war-0.116
fires-0.114
 MacDonald-0.111
 Skip-0.110
 Alan-0.108
Tokenivered
Token ID6396
Feature activation-1.62e+00

Pos logit contributions
itten+0.602
une+0.531
 nail+0.519
el+0.502
umb+0.495
Neg logit contributions
 war-0.491
fires-0.456
 Skip-0.454
 MacDonald-0.441
 Alan-0.439
Token.
Token ID13
Feature activation+5.32e-01

Pos logit contributions
 war+0.067
 Skip+0.066
 MacDonald+0.065
 Alan+0.064
brate+0.063
Neg logit contributions
itten-0.057
 arm-0.054
une-0.053
el-0.051
 knob-0.051
Token So
Token ID1406
Feature activation+2.18e+00

Pos logit contributions
itten+0.025
une+0.023
 nail+0.022
el+0.022
 arm+0.021
Neg logit contributions
 war-0.017
 Skip-0.017
 Alan-0.016
fires-0.016
 cheered-0.016
Token he
Token ID339
Feature activation+4.67e-02

Pos logit contributions
itten+0.096
 arm+0.091
el+0.090
une+0.089
 nail+0.087
Neg logit contributions
fires-0.072
 war-0.071
 MacDonald-0.070
 Skip-0.067
brate-0.066
Token decided
Token ID3066
Feature activation+2.60e+00

Pos logit contributions
itten+0.002
une+0.002
 arm+0.002
el+0.002
 nail+0.002
Neg logit contributions
 war-0.002
 Skip-0.002
fires-0.002
 MacDonald-0.002
 Alan-0.002
Token.
Token ID13
Feature activation+9.19e-01

Pos logit contributions
 war+0.113
 Skip+0.112
brate+0.111
fires+0.110
Alan+0.107
Neg logit contributions
itten-0.085
 arm-0.079
el-0.078
une-0.076
 egg-0.074
Token They
Token ID1119
Feature activation-5.75e+00

Pos logit contributions
itten+0.047
une+0.044
el+0.042
 nail+0.042
 arm+0.041
Neg logit contributions
 war-0.026
 Skip-0.024
 Alan-0.023
fires-0.023
 MacDonald-0.023
Token had
Token ID550
Feature activation-5.08e-01

Pos logit contributions
 war+0.208
fires+0.201
 Skip+0.199
 MacDonald+0.199
brate+0.187
Neg logit contributions
itten-0.231
une-0.220
 arm-0.215
 nail-0.211
el-0.208
Token stopped
Token ID5025
Feature activation+9.41e-01

Pos logit contributions
 Skip+0.020
 MacDonald+0.020
fires+0.020
brate+0.019
 Alan+0.019
Neg logit contributions
 arm-0.019
itten-0.017
une-0.017
 egg-0.017
 nail-0.016
Token qu
Token ID627
Feature activation-5.09e+00

Pos logit contributions
el+0.043
itten+0.042
 arm+0.042
une+0.041
 nail+0.040
Neg logit contributions
 Skip-0.029
fires-0.028
 MacDonald-0.028
brate-0.028
 cheered-0.027
Tokenarre
Token ID9624
Feature activation-1.78e+01

Pos logit contributions
 Skip+0.145
 war+0.135
 MacDonald+0.135
 Alan+0.132
fires+0.129
Neg logit contributions
itten-0.263
une-0.253
el-0.251
umb-0.244
 arm-0.233
Tokenling
Token ID1359
Feature activation-2.42e+00

Pos logit contributions
 Skip+0.825
 MacDonald+0.776
 Alan+0.773
 Bow+0.749
 war+0.727
Neg logit contributions
el-0.586
els-0.498
 arm-0.496
umb-0.491
 ornament-0.472
Token.
Token ID13
Feature activation+6.21e-01

Pos logit contributions
brate+0.123
 MacDonald+0.120
 Skip+0.117
Alan+0.115
fires+0.114
Neg logit contributions
 arm-0.062
el-0.055
itten-0.048
une-0.048
 knob-0.047
Token To
Token ID1675
Feature activation+7.12e-01

Pos logit contributions
itten+0.028
une+0.026
el+0.025
 arm+0.024
 nail+0.024
Neg logit contributions
 war-0.021
fires-0.019
 Skip-0.019
 MacDonald-0.019
 Alan-0.018
Token celebrate
Token ID10648
Feature activation-7.20e+00

Pos logit contributions
el+0.030
 arm+0.030
une+0.029
itten+0.029
 nail+0.028
Neg logit contributions
fires-0.022
 MacDonald-0.022
 Skip-0.021
 war-0.020
 warriors-0.020
Token,
Token ID11
Feature activation-7.71e-01

Pos logit contributions
 villains+0.290
 Skip+0.287
 war+0.281
Alan+0.280
 warriors+0.280
Neg logit contributions
el-0.244
 arm-0.236
 knob-0.233
itten-0.223
 egg-0.216
Token on
Token ID319
Feature activation-1.39e-01

Pos logit contributions
 war+0.071
fires+0.070
 MacDonald+0.070
 Skip+0.067
 Alan+0.066
Neg logit contributions
itten-0.083
une-0.076
el-0.075
 arm-0.074
 nail-0.071
Token,
Token ID11
Feature activation-9.50e-01

Pos logit contributions
fires+0.006
 MacDonald+0.005
brate+0.005
 cheered+0.005
 performers+0.005
Neg logit contributions
el-0.005
itten-0.005
 arm-0.005
 nail-0.005
une-0.005
Token they
Token ID484
Feature activation-5.84e+00

Pos logit contributions
fires+0.030
 MacDonald+0.029
brate+0.028
 cheered+0.025
 announcements+0.024
Neg logit contributions
 nail-0.040
une-0.038
 arm-0.038
el-0.037
itten-0.037
Token never
Token ID1239
Feature activation+4.22e+00

Pos logit contributions
 war+0.189
fires+0.188
 Skip+0.186
 MacDonald+0.185
 Alan+0.174
Neg logit contributions
itten-0.256
une-0.248
el-0.242
 nail-0.237
 arm-0.236
Token qu
Token ID627
Feature activation-5.02e+00

Pos logit contributions
une+0.146
 nail+0.146
 arm+0.144
itten+0.142
raid+0.142
Neg logit contributions
 Skip-0.165
fires-0.164
 MacDonald-0.162
 Alan-0.155
 war-0.149
Tokenarre
Token ID9624
Feature activation-1.75e+01

Pos logit contributions
 Skip+0.116
 war+0.115
 MacDonald+0.111
 Alan+0.107
fires+0.106
Neg logit contributions
itten-0.277
une-0.268
el-0.258
umb-0.252
 nail-0.249
Tokenled
Token ID992
Feature activation-4.15e+00

Pos logit contributions
 MacDonald+0.642
 Skip+0.637
 Alan+0.617
 Bow+0.557
Alan+0.555
Neg logit contributions
el-0.728
 nail-0.655
els-0.641
 ornament-0.639
umb-0.635
Token again
Token ID757
Feature activation-2.06e+00

Pos logit contributions
 MacDonald+0.179
 Skip+0.172
fires+0.171
brate+0.171
 war+0.164
Neg logit contributions
une-0.128
 arm-0.126
el-0.126
 nail-0.123
itten-0.122
Token over
Token ID625
Feature activation+5.90e-01

Pos logit contributions
 Skip+0.096
 MacDonald+0.093
 Alan+0.090
brate+0.089
 war+0.087
Neg logit contributions
 arm-0.060
itten-0.059
el-0.057
 nail-0.054
une-0.053
Token clothes
Token ID8242
Feature activation-1.11e+00

Pos logit contributions
el+0.023
 arm+0.023
 nail+0.023
une+0.023
itten+0.022
Neg logit contributions
 Skip-0.021
 MacDonald-0.021
brate-0.021
fires-0.020
 Alan-0.019
Token.
Token ID13
Feature activation+2.03e-01

Pos logit contributions
 Skip+0.047
 MacDonald+0.045
 war+0.045
 Alan+0.043
brate+0.043
Neg logit contributions
itten-0.039
 arm-0.037
une-0.037
el-0.036
 nail-0.034
Token told
Token ID1297
Feature activation+4.23e-01

Pos logit contributions
itten+0.002
 nail+0.002
une+0.002
 knob+0.002
el+0.002
Neg logit contributions
 war-0.002
 Skip-0.002
 MacDonald-0.002
fires-0.002
 Alan-0.002
Token them
Token ID606
Feature activation-2.58e+00

Pos logit contributions
itten+0.017
el+0.017
une+0.017
 nail+0.016
 arm+0.016
Neg logit contributions
fires-0.015
 Skip-0.015
 war-0.014
 Alan-0.014
 MacDonald-0.014
Token to
Token ID284
Feature activation-4.72e-01

Pos logit contributions
 MacDonald+0.095
fires+0.094
 Skip+0.091
Alan+0.090
rob+0.089
Neg logit contributions
une-0.097
 nail-0.096
 arm-0.096
itten-0.092
 knob-0.089
Token stop
Token ID2245
Feature activation-7.48e-01

Pos logit contributions
 Skip+0.018
 war+0.018
 MacDonald+0.017
fires+0.017
 Alan+0.017
Neg logit contributions
itten-0.018
une-0.017
 nail-0.017
 arm-0.017
el-0.017
Token qu
Token ID627
Feature activation-4.86e+00

Pos logit contributions
 Skip+0.025
 war+0.024
 MacDonald+0.023
fires+0.023
 Alan+0.023
Neg logit contributions
itten-0.032
el-0.032
 arm-0.031
une-0.031
 nail-0.031
Tokenarre
Token ID9624
Feature activation-1.74e+01

Pos logit contributions
 war+0.106
 Skip+0.098
fires+0.093
 Alan+0.092
 MacDonald+0.092
Neg logit contributions
itten-0.277
une-0.262
el-0.251
 nail-0.250
 arm-0.248
Tokenlling
Token ID2680
Feature activation-3.93e+00

Pos logit contributions
 Skip+0.720
 MacDonald+0.718
 Alan+0.695
 seals+0.668
 war+0.664
Neg logit contributions
el-0.617
itten-0.571
 arm-0.566
umb-0.559
 nail-0.558
Token and
Token ID290
Feature activation+1.05e-01

Pos logit contributions
 MacDonald+0.175
 Skip+0.172
 war+0.168
 seals+0.168
brate+0.167
Neg logit contributions
 arm-0.121
itten-0.118
une-0.114
el-0.111
 nail-0.110
Token to
Token ID284
Feature activation-4.66e-01

Pos logit contributions
itten+0.004
 nail+0.004
 arm+0.004
une+0.004
 knob+0.004
Neg logit contributions
 MacDonald-0.004
 Skip-0.004
fires-0.004
 war-0.004
 Alan-0.004
Token share
Token ID2648
Feature activation-3.12e+00

Pos logit contributions
 Skip+0.018
 MacDonald+0.018
fires+0.018
 war+0.017
 Alan+0.017
Neg logit contributions
 nail-0.017
 arm-0.016
itten-0.016
une-0.016
 knob-0.015
Token the
Token ID262
Feature activation-1.90e+00

Pos logit contributions
 war+0.090
 Skip+0.086
fires+0.083
 MacDonald+0.082
 Alan+0.082
Neg logit contributions
itten-0.154
une-0.145
el-0.139
 nail-0.138
 arm-0.137
Token.
Token ID13
Feature activation+5.98e-01

Pos logit contributions
 war+0.026
 Skip+0.025
 Alan+0.024
 MacDonald+0.024
fires+0.024
Neg logit contributions
itten-0.032
une-0.030
el-0.028
 nail-0.028
 arm-0.028
Token The
Token ID383
Feature activation+5.72e-01

Pos logit contributions
itten+0.026
une+0.024
el+0.022
 nail+0.022
 arm+0.022
Neg logit contributions
 war-0.021
 Skip-0.020
fires-0.020
 MacDonald-0.020
 Alan-0.019
Token bears
Token ID13062
Feature activation-5.62e+00

Pos logit contributions
itten+0.025
une+0.023
el+0.022
 nail+0.022
 arm+0.021
Neg logit contributions
 war-0.020
 Skip-0.019
fires-0.019
 MacDonald-0.019
 Alan-0.019
Token stopped
Token ID5025
Feature activation+6.94e-01

Pos logit contributions
 war+0.171
 MacDonald+0.169
 Skip+0.169
fires+0.156
 Alan+0.156
Neg logit contributions
itten-0.264
une-0.249
el-0.247
 arm-0.244
 nail-0.243
Token qu
Token ID627
Feature activation-4.86e+00

Pos logit contributions
itten+0.032
el+0.030
une+0.030
 arm+0.029
 nail+0.029
Neg logit contributions
 war-0.022
 Skip-0.022
fires-0.022
brate-0.021
 MacDonald-0.021
Tokenarre
Token ID9624
Feature activation-1.74e+01

Pos logit contributions
 war+0.151
 Skip+0.148
 MacDonald+0.139
fires+0.139
 Alan+0.138
Neg logit contributions
itten-0.235
une-0.222
el-0.215
umb-0.206
 arm-0.205
Tokenling
Token ID1359
Feature activation-2.00e+00

Pos logit contributions
 Skip+0.752
 MacDonald+0.734
 war+0.722
 Alan+0.713
 Bow+0.684
Neg logit contributions
el-0.624
itten-0.548
 arm-0.528
 nail-0.516
umb-0.516
Token and
Token ID290
Feature activation-4.90e-02

Pos logit contributions
brate+0.102
 MacDonald+0.102
 Skip+0.097
fires+0.097
 war+0.096
Neg logit contributions
 arm-0.049
el-0.049
itten-0.041
une-0.041
 knob-0.039
Token asked
Token ID1965
Feature activation+4.57e+00

Pos logit contributions
 war+0.002
fires+0.002
brate+0.002
 MacDonald+0.002
 tournament+0.002
Neg logit contributions
itten-0.002
 arm-0.002
el-0.002
 knob-0.002
 nail-0.002
Token him
Token ID683
Feature activation+4.75e-01

Pos logit contributions
une+0.170
itten+0.168
 arm+0.164
el+0.159
 nail+0.156
Neg logit contributions
fires-0.166
 MacDonald-0.163
 war-0.163
brate-0.158
 tournament-0.150
Token for
Token ID329
Feature activation-1.56e+00

Pos logit contributions
itten+0.019
une+0.019
 arm+0.017
 nail+0.017
el+0.016
Neg logit contributions
 war-0.018
 MacDonald-0.017
fires-0.017
 Skip-0.016
brate-0.016
Token but
Token ID475
Feature activation+1.74e+00

Pos logit contributions
brate+0.025
fires+0.025
 war+0.023
 MacDonald+0.023
 Skip+0.023
Neg logit contributions
itten-0.019
 arm-0.018
el-0.017
 nail-0.017
 knob-0.017
Token today
Token ID1909
Feature activation+4.71e-01

Pos logit contributions
itten+0.078
el+0.074
une+0.072
 arm+0.072
 nail+0.071
Neg logit contributions
fires-0.054
 war-0.054
 MacDonald-0.052
 Skip-0.052
brate-0.050
Token they
Token ID484
Feature activation-5.75e+00

Pos logit contributions
el+0.022
 nail+0.021
itten+0.021
 knob+0.021
 bulb+0.021
Neg logit contributions
 Skip-0.013
 MacDonald-0.013
fires-0.013
Alan-0.012
brate-0.012
Token were
Token ID547
Feature activation-2.10e+00

Pos logit contributions
 MacDonald+0.217
 Skip+0.209
 war+0.208
fires+0.205
brate+0.191
Neg logit contributions
une-0.212
itten-0.208
el-0.208
 knob-0.197
 nail-0.197
Token qu
Token ID627
Feature activation-4.82e+00

Pos logit contributions
 MacDonald+0.083
fires+0.078
brate+0.078
 Skip+0.075
 tournament+0.072
Neg logit contributions
une-0.076
 arm-0.073
el-0.072
itten-0.071
 bulb-0.068
Tokenarre
Token ID9624
Feature activation-1.74e+01

Pos logit contributions
 war+0.122
 Skip+0.121
 MacDonald+0.115
fires+0.111
 Alan+0.110
Neg logit contributions
itten-0.257
une-0.244
el-0.238
umb-0.234
 nail-0.228
Tokenling
Token ID1359
Feature activation-1.97e+00

Pos logit contributions
 Skip+0.711
 MacDonald+0.695
 Alan+0.658
 Bow+0.652
 war+0.638
Neg logit contributions
el-0.667
umb-0.591
itten-0.590
 nail-0.585
 bulb-0.582
Token.
Token ID13
Feature activation+7.60e-01

Pos logit contributions
brate+0.086
 MacDonald+0.084
 Skip+0.084
fires+0.081
 war+0.080
Neg logit contributions
el-0.061
 arm-0.060
itten-0.054
une-0.051
 knob-0.051
Token Jenna
Token ID45377
Feature activation-1.72e+00

Pos logit contributions
itten+0.034
une+0.032
el+0.030
 nail+0.030
 arm+0.030
Neg logit contributions
 war-0.025
 Skip-0.024
fires-0.023
 MacDonald-0.023
 Alan-0.023
Token wanted
Token ID2227
Feature activation+2.55e+00

Pos logit contributions
 war+0.069
fires+0.067
 Skip+0.066
 MacDonald+0.064
brate+0.062
Neg logit contributions
itten-0.064
el-0.059
 arm-0.058
une-0.057
 nail-0.057
Token to
Token ID284
Feature activation-2.22e-01

Pos logit contributions
itten+0.098
une+0.093
 nail+0.089
 arm+0.089
el+0.089
Neg logit contributions
fires-0.096
 war-0.095
 MacDonald-0.094
 Skip-0.093
brate-0.090
Token and
Token ID290
Feature activation+5.14e-02

Pos logit contributions
 Skip+0.172
 war+0.168
 MacDonald+0.164
 Alan+0.160
Alan+0.157
Neg logit contributions
itten-0.206
une-0.198
el-0.196
 nail-0.192
 arm-0.191
Token their
Token ID511
Feature activation-2.81e+00

Pos logit contributions
 nail+0.002
 arm+0.002
 knob+0.002
 hammer+0.002
une+0.002
Neg logit contributions
 MacDonald-0.002
 Skip-0.002
brate-0.002
fires-0.002
 Alan-0.002
Token children
Token ID1751
Feature activation-5.36e+00

Pos logit contributions
 Skip+0.110
 war+0.108
 MacDonald+0.106
fires+0.106
 Alan+0.105
Neg logit contributions
itten-0.104
une-0.101
 arm-0.097
 nail-0.095
 knob-0.093
Token,
Token ID11
Feature activation-8.06e-01

Pos logit contributions
 Skip+0.214
 MacDonald+0.207
 war+0.207
 Alan+0.201
Alan+0.200
Neg logit contributions
itten-0.202
une-0.190
 arm-0.188
el-0.184
 nail-0.182
Token qu
Token ID627
Feature activation-4.70e+00

Pos logit contributions
brate+0.028
 Skip+0.028
 war+0.027
 MacDonald+0.027
fires+0.027
Neg logit contributions
itten-0.031
 arm-0.031
 nail-0.029
 knob-0.029
une-0.029
Tokenarre
Token ID9624
Feature activation-1.73e+01

Pos logit contributions
 Skip+0.139
 war+0.138
 MacDonald+0.129
fires+0.128
 Alan+0.128
Neg logit contributions
itten-0.229
une-0.216
el-0.214
umb-0.206
 arm-0.202
Tokenling
Token ID1359
Feature activation-1.72e+00

Pos logit contributions
 Skip+0.721
 MacDonald+0.691
 Alan+0.690
 war+0.683
 tournament+0.649
Neg logit contributions
el-0.619
itten-0.602
 nail-0.564
 knob-0.563
 bulb-0.558
Token.
Token ID13
Feature activation+5.38e-01

Pos logit contributions
brate+0.075
 Skip+0.074
 tournament+0.073
Alan+0.072
 MacDonald+0.071
Neg logit contributions
 arm-0.056
el-0.054
une-0.049
 knob-0.049
itten-0.048
Token
Token ID220
Feature activation+2.48e+00

Pos logit contributions
itten+0.025
une+0.023
el+0.022
 nail+0.022
 arm+0.022
Neg logit contributions
 war-0.017
 Skip-0.016
fires-0.016
 MacDonald-0.016
 Alan-0.016
Token
Token ID198
Feature activation-2.03e-01

Pos logit contributions
itten+0.122
une+0.113
 nail+0.108
el+0.108
 arm+0.107
Neg logit contributions
 war-0.073
 Skip-0.070
fires-0.067
 Alan-0.067
 cheered-0.067
Token
Token ID198
Feature activation-2.11e-01

Pos logit contributions
 war+0.007
 Skip+0.006
fires+0.006
 Alan+0.006
 cheered+0.006
Neg logit contributions
itten-0.009
une-0.009
el-0.008
 nail-0.008
 arm-0.008
Token and
Token ID290
Feature activation-8.33e-02

Pos logit contributions
 war+0.006
 MacDonald+0.006
 Skip+0.006
fires+0.006
brate+0.005
Neg logit contributions
itten-0.005
une-0.005
el-0.005
 arm-0.005
 nail-0.005
Token saw
Token ID2497
Feature activation+5.32e-02

Pos logit contributions
 war+0.003
 Skip+0.003
fires+0.003
 players+0.003
 seals+0.003
Neg logit contributions
itten-0.003
el-0.003
 knob-0.003
 arm-0.003
 nail-0.003
Token two
Token ID734
Feature activation+1.62e+00

Pos logit contributions
itten+0.002
une+0.002
 nail+0.002
 arm+0.002
el+0.002
Neg logit contributions
 war-0.002
 MacDonald-0.002
fires-0.002
brate-0.002
 Skip-0.002
Token birds
Token ID10087
Feature activation-3.36e+00

Pos logit contributions
itten+0.065
une+0.062
el+0.060
 nail+0.059
 arm+0.059
Neg logit contributions
fires-0.059
 Skip-0.058
 war-0.058
 Alan-0.056
 MacDonald-0.056
Token qu
Token ID627
Feature activation-4.85e+00

Pos logit contributions
 war+0.117
 Skip+0.115
fires+0.114
 MacDonald+0.113
brate+0.111
Neg logit contributions
itten-0.144
el-0.135
une-0.131
 bulb-0.125
 arm-0.124
Tokenarre
Token ID9624
Feature activation-1.73e+01

Pos logit contributions
 war+0.167
 Skip+0.164
fires+0.155
 MacDonald+0.154
 Alan+0.154
Neg logit contributions
itten-0.216
une-0.203
el-0.198
umb-0.190
 nail-0.186
Tokenling
Token ID1359
Feature activation-1.88e+00

Pos logit contributions
 Skip+0.713
 MacDonald+0.695
 war+0.688
 Alan+0.677
 tournament+0.654
Neg logit contributions
el-0.627
itten-0.578
 nail-0.546
els-0.546
 bulb-0.544
Token!
Token ID0
Feature activation-1.13e+00

Pos logit contributions
brate+0.083
 tournament+0.080
 MacDonald+0.079
fires+0.078
 Skip+0.077
Neg logit contributions
el-0.060
 arm-0.056
une-0.054
itten-0.053
 bulb-0.050
Token They
Token ID1119
Feature activation-5.73e+00

Pos logit contributions
 war+0.043
fires+0.042
brate+0.042
 MacDonald+0.040
 performers+0.040
Neg logit contributions
une-0.041
itten-0.041
el-0.037
 arm-0.037
 nail-0.037
Token were
Token ID547
Feature activation-2.14e+00

Pos logit contributions
 war+0.191
 MacDonald+0.185
fires+0.184
 Skip+0.178
brate+0.170
Neg logit contributions
itten-0.245
el-0.234
une-0.230
 nail-0.229
 arm-0.226
Token squ
Token ID2809
Feature activation+1.45e+00

Pos logit contributions
 MacDonald+0.074
fires+0.072
brate+0.072
 war+0.070
 tournament+0.069
Neg logit contributions
une-0.086
itten-0.086
 arm-0.083
el-0.083
 nail-0.078
Token together
Token ID1978
Feature activation-4.95e+00

Pos logit contributions
 MacDonald+0.099
 seals+0.089
brate+0.086
 Alan+0.085
 performers+0.085
Neg logit contributions
 arm-0.099
 nail-0.098
 block-0.093
 foot-0.093
 hammer-0.086
Token.
Token ID13
Feature activation+3.24e-01

Pos logit contributions
 MacDonald+0.214
 Skip+0.197
 war+0.197
brate+0.196
fires+0.192
Neg logit contributions
itten-0.156
 arm-0.155
une-0.155
 nail-0.150
el-0.147
Token They
Token ID1119
Feature activation-5.92e+00

Pos logit contributions
itten+0.015
une+0.015
el+0.014
 arm+0.014
 nail+0.014
Neg logit contributions
 war-0.010
 Skip-0.009
fires-0.009
 MacDonald-0.009
brate-0.009
Token never
Token ID1239
Feature activation+4.34e+00

Pos logit contributions
 MacDonald+0.200
fires+0.191
 war+0.187
 Skip+0.180
brate+0.171
Neg logit contributions
itten-0.255
 arm-0.246
une-0.246
 nail-0.244
el-0.236
Token qu
Token ID627
Feature activation-4.76e+00

Pos logit contributions
 nail+0.140
une+0.138
 arm+0.137
 eye+0.133
 cut+0.132
Neg logit contributions
fires-0.178
 MacDonald-0.176
 Skip-0.175
 films-0.165
 Alan-0.161
Tokenarre
Token ID9624
Feature activation-1.73e+01

Pos logit contributions
 MacDonald+0.132
 Skip+0.131
 war+0.126
 Alan+0.121
 they+0.120
Neg logit contributions
itten-0.239
une-0.237
umb-0.228
el-0.227
 arm-0.212
Tokenled
Token ID992
Feature activation-3.89e+00

Pos logit contributions
 MacDonald+0.694
 Skip+0.664
 Alan+0.649
 Bow+0.602
 seals+0.601
Neg logit contributions
el-0.648
els-0.577
 nail-0.576
umb-0.566
 arm-0.559
Token again
Token ID757
Feature activation-1.87e+00

Pos logit contributions
 MacDonald+0.178
brate+0.174
fires+0.169
 Skip+0.166
rob+0.158
Neg logit contributions
 arm-0.107
el-0.103
une-0.103
 nail-0.101
 foot-0.095
Token.
Token ID13
Feature activation+2.70e-01

Pos logit contributions
 Skip+0.086
 MacDonald+0.086
brate+0.082
 Alan+0.079
fires+0.079
Neg logit contributions
 arm-0.053
itten-0.050
el-0.049
 nail-0.047
une-0.045
Token<|endoftext|>
Token ID50256
Feature activation-3.74e+00

Pos logit contributions
itten+0.012
une+0.011
el+0.011
 arm+0.011
 nail+0.011
Neg logit contributions
 war-0.009
 Skip-0.009
fires-0.008
 MacDonald-0.008
brate-0.008
TokenOnce
Token ID7454
Feature activation+2.33e+00

Pos logit contributions
 war+0.156
fires+0.145
brate+0.144
 Skip+0.143
 MacDonald+0.143
Neg logit contributions
itten-0.135
une-0.125
el-0.122
 arm-0.116
umb-0.115
Token Tom
Token ID4186
Feature activation-2.25e+00

Pos logit contributions
itten+0.041
une+0.039
el+0.036
 nail+0.036
 arm+0.036
Neg logit contributions
 war-0.037
 Skip-0.035
fires-0.035
 MacDonald-0.034
 Alan-0.034
Token and
Token ID290
Feature activation+8.48e-02

Pos logit contributions
 war+0.095
fires+0.092
 Skip+0.089
 Alan+0.088
brate+0.088
Neg logit contributions
itten-0.079
une-0.074
 arm-0.072
el-0.070
 nail-0.068
Token Mia
Token ID32189
Feature activation-1.95e-01

Pos logit contributions
itten+0.004
une+0.004
el+0.003
umb+0.003
 nail+0.003
Neg logit contributions
 war-0.003
 Skip-0.003
 Alan-0.003
 MacDonald-0.003
 cheered-0.003
Token stop
Token ID2245
Feature activation-9.62e-01

Pos logit contributions
 war+0.007
 Skip+0.007
 MacDonald+0.007
fires+0.007
 Alan+0.007
Neg logit contributions
itten-0.008
une-0.008
 arm-0.007
el-0.007
 nail-0.007
Token qu
Token ID627
Feature activation-4.95e+00

Pos logit contributions
fires+0.034
brate+0.034
 Skip+0.034
 war+0.034
 MacDonald+0.033
Neg logit contributions
itten-0.038
 arm-0.038
el-0.038
 nail-0.036
une-0.036
Tokenarre
Token ID9624
Feature activation-1.73e+01

Pos logit contributions
 Skip+0.149
 war+0.146
fires+0.140
 MacDonald+0.140
 Alan+0.137
Neg logit contributions
itten-0.238
une-0.228
el-0.225
umb-0.216
 arm-0.215
Tokenling
Token ID1359
Feature activation-1.58e+00

Pos logit contributions
 Skip+0.719
 Alan+0.702
 MacDonald+0.677
 war+0.676
Alan+0.648
Neg logit contributions
el-0.631
 arm-0.576
itten-0.565
umb-0.545
els-0.537
Token.
Token ID13
Feature activation+9.38e-01

Pos logit contributions
brate+0.082
 Skip+0.078
 MacDonald+0.077
 Alan+0.076
fires+0.075
Neg logit contributions
 arm-0.044
el-0.039
itten-0.037
une-0.035
 knob-0.035
Token They
Token ID1119
Feature activation-5.77e+00

Pos logit contributions
une+0.039
itten+0.039
 arm+0.037
 nail+0.037
el+0.037
Neg logit contributions
brate-0.031
 war-0.030
fires-0.029
 celebrating-0.028
 Skip-0.028
Token see
Token ID766
Feature activation+5.54e-01

Pos logit contributions
 war+0.219
fires+0.217
 MacDonald+0.213
 Skip+0.213
 celebrating+0.204
Neg logit contributions
une-0.212
itten-0.212
 nail-0.205
 arm-0.204
 knob-0.200
Token the
Token ID262
Feature activation-1.52e+00

Pos logit contributions
 arm+0.023
 nail+0.023
une+0.023
itten+0.022
el+0.022
Neg logit contributions
fires-0.019
brate-0.018
 MacDonald-0.018
 Skip-0.018
 Alan-0.017
Token lively
Token ID29696
Feature activation-4.01e+00

Pos logit contributions
 Skip+0.035
fires+0.035
brate+0.034
 MacDonald+0.034
 Alan+0.034
Neg logit contributions
itten-0.036
 arm-0.036
 nail-0.036
 knob-0.035
 rag-0.033
Token sound
Token ID2128
Feature activation-4.82e+00

Pos logit contributions
fires+0.152
 Skip+0.144
brate+0.143
 Alan+0.140
Alan+0.137
Neg logit contributions
 arm-0.161
itten-0.159
 nail-0.153
 knob-0.152
 rag-0.147
Token.
Token ID13
Feature activation+2.23e-01

Pos logit contributions
 Skip+0.239
Alan+0.235
 Alan+0.232
brate+0.226
 tournament+0.224
Neg logit contributions
 arm-0.127
 knob-0.126
itten-0.121
 bulb-0.114
une-0.114
Token The
Token ID383
Feature activation+2.19e-01

Pos logit contributions
itten+0.010
une+0.009
el+0.009
 arm+0.009
 nail+0.009
Neg logit contributions
 war-0.008
fires-0.007
 MacDonald-0.007
 Skip-0.007
brate-0.007
Token qu
Token ID627
Feature activation-4.80e+00

Pos logit contributions
itten+0.008
 arm+0.008
 nail+0.008
 knob+0.007
une+0.007
Neg logit contributions
fires-0.009
 Skip-0.009
 MacDonald-0.008
 Alan-0.008
 war-0.008
Tokenarre
Token ID9624
Feature activation-1.72e+01

Pos logit contributions
 Skip+0.172
 Alan+0.162
 war+0.162
 MacDonald+0.159
fires+0.154
Neg logit contributions
itten-0.209
el-0.201
une-0.195
umb-0.193
 arm-0.179
Tokenling
Token ID1359
Feature activation-1.87e+00

Pos logit contributions
 Skip+0.722
 MacDonald+0.718
 Alan+0.697
 Bow+0.681
Alan+0.656
Neg logit contributions
el-0.624
 bulb-0.571
 nail-0.552
itten-0.539
 knob-0.520
Token stopped
Token ID5025
Feature activation+8.19e-01

Pos logit contributions
brate+0.077
 MacDonald+0.077
 Skip+0.076
fires+0.076
 Alan+0.073
Neg logit contributions
 arm-0.064
el-0.063
itten-0.062
 nail-0.059
une-0.058
Token and
Token ID290
Feature activation-1.85e-01

Pos logit contributions
itten+0.034
el+0.033
une+0.032
 arm+0.031
 nail+0.031
Neg logit contributions
 Skip-0.030
brate-0.029
 war-0.029
fires-0.028
 MacDonald-0.028
Token they
Token ID484
Feature activation-5.80e+00

Pos logit contributions
 MacDonald+0.007
fires+0.007
brate+0.007
 war+0.006
 Skip+0.006
Neg logit contributions
 bulb-0.007
 arm-0.007
 knob-0.007
 nail-0.007
el-0.007
Token heard
Token ID2982
Feature activation-1.34e+00

Pos logit contributions
 MacDonald+0.201
 war+0.195
fires+0.193
 Skip+0.189
brate+0.183
Neg logit contributions
itten-0.242
 arm-0.235
une-0.231
 nail-0.226
el-0.226
Token walking
Token ID6155
Feature activation-2.90e+00

Pos logit contributions
 Skip+0.016
 war+0.015
 MacDonald+0.015
fires+0.015
 tournament+0.015
Neg logit contributions
itten-0.018
 arm-0.018
une-0.017
 nail-0.017
el-0.017
Token by
Token ID416
Feature activation+2.57e-01

Pos logit contributions
 war+0.116
 Skip+0.114
brate+0.113
fires+0.111
 MacDonald+0.111
Neg logit contributions
itten-0.104
el-0.100
 arm-0.099
une-0.097
 knob-0.092
Token saw
Token ID2497
Feature activation+4.47e-01

Pos logit contributions
 arm+0.009
el+0.009
itten+0.009
 nail+0.008
 knob+0.008
Neg logit contributions
brate-0.010
 Skip-0.010
 MacDonald-0.010
 tournament-0.010
 war-0.010
Token them
Token ID606
Feature activation-2.58e+00

Pos logit contributions
el+0.019
itten+0.019
une+0.018
 nail+0.018
 arm+0.018
Neg logit contributions
 Skip-0.014
fires-0.014
 war-0.014
 MacDonald-0.014
brate-0.013
Token qu
Token ID627
Feature activation-4.88e+00

Pos logit contributions
 Skip+0.105
 MacDonald+0.104
 war+0.103
fires+0.102
 Alan+0.101
Neg logit contributions
itten-0.094
 arm-0.089
el-0.088
une-0.088
 nail-0.082
Tokenarre
Token ID9624
Feature activation-1.72e+01

Pos logit contributions
 war+0.126
 Skip+0.125
 MacDonald+0.117
 Alan+0.116
fires+0.116
Neg logit contributions
itten-0.256
une-0.245
el-0.239
umb-0.231
 arm-0.229
Tokenling
Token ID1359
Feature activation-1.71e+00

Pos logit contributions
 Skip+0.711
 Alan+0.688
 MacDonald+0.683
 war+0.676
 Bow+0.640
Neg logit contributions
el-0.637
itten-0.580
 arm-0.565
 nail-0.553
els-0.549
Token.
Token ID13
Feature activation+3.86e-01

Pos logit contributions
brate+0.076
 Skip+0.075
fires+0.075
 MacDonald+0.075
 tournament+0.074
Neg logit contributions
 arm-0.052
el-0.051
itten-0.049
une-0.046
 knob-0.045
Token She
Token ID1375
Feature activation+1.54e+00

Pos logit contributions
itten+0.013
une+0.012
el+0.011
 nail+0.011
 arm+0.010
Neg logit contributions
 war-0.018
 Skip-0.017
 MacDonald-0.017
 Alan-0.017
fires-0.016
Token was
Token ID373
Feature activation-3.81e-01

Pos logit contributions
itten+0.062
une+0.057
el+0.056
 arm+0.056
 nail+0.055
Neg logit contributions
 war-0.057
 Skip-0.053
fires-0.053
 Alan-0.052
 MacDonald-0.051
Token very
Token ID845
Feature activation-4.64e-02

Pos logit contributions
 war+0.013
 MacDonald+0.013
 Skip+0.013
fires+0.013
brate+0.012
Neg logit contributions
itten-0.016
 arm-0.015
une-0.015
 nail-0.014
el-0.014
Token friends
Token ID2460
Feature activation-6.50e+00

Pos logit contributions
itten+0.056
une+0.053
el+0.052
 nail+0.051
 arm+0.051
Neg logit contributions
fires-0.067
 MacDonald-0.067
 Skip-0.066
brate-0.065
 war-0.064
Token didn
Token ID1422
Feature activation-9.66e-01

Pos logit contributions
 MacDonald+0.234
 war+0.221
 Skip+0.221
fires+0.217
brate+0.205
Neg logit contributions
itten-0.264
 arm-0.260
 nail-0.259
el-0.257
une-0.255
Token't
Token ID470
Feature activation+2.39e+00

Pos logit contributions
 war+0.043
fires+0.042
 MacDonald+0.041
 Skip+0.041
 seals+0.041
Neg logit contributions
itten-0.032
une-0.029
 arm-0.028
el-0.027
 nail-0.027
Token stop
Token ID2245
Feature activation-8.60e-01

Pos logit contributions
itten+0.082
 nail+0.081
une+0.077
 arm+0.076
 brush+0.075
Neg logit contributions
 Skip-0.096
 MacDonald-0.094
 war-0.093
 Alan-0.093
fires-0.091
Token qu
Token ID627
Feature activation-4.78e+00

Pos logit contributions
fires+0.029
brate+0.028
 Skip+0.028
ival+0.027
 war+0.027
Neg logit contributions
el-0.037
 arm-0.036
itten-0.035
 nail-0.034
une-0.033
Tokenarre
Token ID9624
Feature activation-1.72e+01

Pos logit contributions
 Skip+0.116
 war+0.114
 MacDonald+0.110
fires+0.108
 Alan+0.106
Neg logit contributions
itten-0.261
une-0.250
el-0.243
umb-0.237
 nail-0.233
Tokenling
Token ID1359
Feature activation-1.68e+00

Pos logit contributions
 Skip+0.741
 MacDonald+0.726
 Alan+0.724
Alan+0.692
 Bow+0.688
Neg logit contributions
el-0.576
 arm-0.517
 nail-0.517
itten-0.506
umb-0.498
Token and
Token ID290
Feature activation-1.80e-01

Pos logit contributions
brate+0.078
 MacDonald+0.075
 tournament+0.073
 Skip+0.072
Alan+0.072
Neg logit contributions
 arm-0.050
el-0.045
une-0.042
 foot-0.041
 nail-0.041
Token were
Token ID547
Feature activation-2.32e+00

Pos logit contributions
brate+0.006
 tournament+0.006
fires+0.006
 MacDonald+0.006
 war+0.006
Neg logit contributions
 arm-0.007
 nail-0.006
une-0.006
el-0.006
itten-0.006
Token getting
Token ID1972
Feature activation+3.30e-01

Pos logit contributions
 MacDonald+0.095
brate+0.089
fires+0.088
 Skip+0.086
 tournament+0.086
Neg logit contributions
 arm-0.085
itten-0.081
une-0.079
 nail-0.077
 foot-0.074
Token louder
Token ID27089
Feature activation-4.86e+00

Pos logit contributions
itten+0.012
une+0.012
 nail+0.012
 arm+0.012
el+0.011
Neg logit contributions
 MacDonald-0.013
 Skip-0.013
fires-0.012
brate-0.012
 war-0.012
Token on
Token ID319
Feature activation+1.19e-01

Pos logit contributions
 war+0.057
 Skip+0.055
fires+0.053
 MacDonald+0.052
 Alan+0.052
Neg logit contributions
itten-0.084
une-0.079
el-0.075
 arm-0.074
 nail-0.074
Token,
Token ID11
Feature activation-9.01e-01

Pos logit contributions
itten+0.004
el+0.004
 arm+0.004
une+0.004
 nail+0.004
Neg logit contributions
fires-0.005
 MacDonald-0.005
 performers-0.005
 announcements-0.005
 cheered-0.005
Token they
Token ID484
Feature activation-5.71e+00

Pos logit contributions
fires+0.031
 MacDonald+0.031
 Skip+0.027
brate+0.027
Alan+0.027
Neg logit contributions
itten-0.036
el-0.035
 nail-0.035
 arm-0.035
 rag-0.034
Token never
Token ID1239
Feature activation+4.35e+00

Pos logit contributions
 war+0.171
fires+0.170
 MacDonald+0.168
 Skip+0.167
 Alan+0.156
Neg logit contributions
itten-0.265
une-0.257
el-0.249
 nail-0.245
 arm-0.244
Token qu
Token ID627
Feature activation-4.79e+00

Pos logit contributions
une+0.150
 arm+0.149
 nail+0.148
raid+0.146
itten+0.144
Neg logit contributions
fires-0.172
 MacDonald-0.169
 Skip-0.169
 Alan-0.161
Alan-0.155
Tokenarre
Token ID9624
Feature activation-1.72e+01

Pos logit contributions
 war+0.108
 Skip+0.107
 MacDonald+0.103
 Alan+0.099
fires+0.099
Neg logit contributions
itten-0.267
une-0.257
el-0.247
umb-0.242
 arm-0.239
Tokenled
Token ID992
Feature activation-3.70e+00

Pos logit contributions
 Skip+0.579
 MacDonald+0.576
 Alan+0.566
 war+0.516
Alan+0.509
Neg logit contributions
el-0.759
itten-0.694
 nail-0.682
 arm-0.681
umb-0.671
Token again
Token ID757
Feature activation-1.96e+00

Pos logit contributions
 MacDonald+0.167
fires+0.161
brate+0.159
 Skip+0.158
 war+0.149
Neg logit contributions
 arm-0.105
une-0.104
el-0.104
 nail-0.100
itten-0.097
Token and
Token ID290
Feature activation-3.22e-01

Pos logit contributions
 Skip+0.093
 MacDonald+0.090
 Alan+0.088
brate+0.086
Alan+0.085
Neg logit contributions
 arm-0.056
itten-0.053
el-0.051
 nail-0.048
une-0.048
Token played
Token ID2826
Feature activation-4.46e+00

Pos logit contributions
fires+0.011
 MacDonald+0.011
 Skip+0.010
Alan+0.010
 Alan+0.010
Neg logit contributions
 nail-0.013
el-0.013
une-0.013
 arm-0.013
itten-0.012
Token together
Token ID1978
Feature activation-4.88e+00

Pos logit contributions
 MacDonald+0.179
 seals+0.155
 congrat+0.155
 Alan+0.154
Alan+0.152
Neg logit contributions
 arm-0.151
 block-0.144
 nail-0.142
 foot-0.136
 toe-0.134
Token she
Token ID673
Feature activation+5.90e-01

Pos logit contributions
une+0.011
 arm+0.011
 nail+0.010
itten+0.010
 bulb+0.009
Neg logit contributions
 MacDonald-0.011
fires-0.011
rob-0.011
brate-0.011
 war-0.011
Token was
Token ID373
Feature activation-5.90e-01

Pos logit contributions
itten+0.024
une+0.023
 arm+0.022
 nail+0.022
el+0.022
Neg logit contributions
 war-0.022
 Skip-0.021
fires-0.021
 Alan-0.020
 MacDonald-0.020
Token sorry
Token ID7926
Feature activation-6.96e+00

Pos logit contributions
fires+0.020
 MacDonald+0.020
 Skip+0.019
brate+0.019
 war+0.018
Neg logit contributions
une-0.024
itten-0.024
 arm-0.024
 nail-0.023
el-0.022
Token for
Token ID329
Feature activation-1.79e+00

Pos logit contributions
 war+0.261
 Skip+0.254
fires+0.249
 Alan+0.246
 MacDonald+0.243
Neg logit contributions
itten-0.278
une-0.259
 arm-0.253
el-0.248
 nail-0.246
Token qu
Token ID627
Feature activation-4.81e+00

Pos logit contributions
 MacDonald+0.060
 Skip+0.056
fires+0.055
 seals+0.055
 cheered+0.054
Neg logit contributions
 arm-0.073
 nail-0.073
itten-0.070
 knob-0.069
el-0.068
Tokenarre
Token ID9624
Feature activation-1.71e+01

Pos logit contributions
 Skip+0.140
 MacDonald+0.129
 Alan+0.126
 war+0.125
fires+0.122
Neg logit contributions
itten-0.244
une-0.235
el-0.234
umb-0.229
 arm-0.216
Tokenling
Token ID1359
Feature activation-1.72e+00

Pos logit contributions
 Skip+0.770
 Alan+0.735
 MacDonald+0.725
 Bow+0.692
 seals+0.684
Neg logit contributions
el-0.564
 nail-0.517
 arm-0.512
umb-0.496
itten-0.495
Token.
Token ID13
Feature activation-4.00e-03

Pos logit contributions
brate+0.072
 Skip+0.072
fires+0.071
 MacDonald+0.071
 war+0.070
Neg logit contributions
 arm-0.056
itten-0.054
une-0.052
el-0.052
 nail-0.049
Token From
Token ID3574
Feature activation+7.42e-01

Pos logit contributions
 war+0.000
 Skip+0.000
fires+0.000
 Alan+0.000
 MacDonald+0.000
Neg logit contributions
itten-0.000
une-0.000
el-0.000
 nail-0.000
 arm-0.000
Token that
Token ID326
Feature activation-5.45e-01

Pos logit contributions
itten+0.029
el+0.028
 arm+0.026
 nail+0.026
 egg+0.026
Neg logit contributions
fires-0.028
 war-0.027
 MacDonald-0.027
 villains-0.025
 Skip-0.025
Token day
Token ID1110
Feature activation-1.95e+00

Pos logit contributions
fires+0.023
 war+0.023
 Skip+0.023
 MacDonald+0.023
 Alan+0.022
Neg logit contributions
itten-0.019
une-0.017
 arm-0.017
el-0.017
 nail-0.017
Token Lily
Token ID20037
Feature activation-1.03e-01

Pos logit contributions
 MacDonald+0.048
fires+0.046
 announcements+0.043
 Skip+0.042
Alan+0.042
Neg logit contributions
 nail-0.029
el-0.027
 arm-0.026
 bulb-0.026
une-0.026
Token and
Token ID290
Feature activation-4.25e-01

Pos logit contributions
 war+0.004
fires+0.004
 Skip+0.004
 MacDonald+0.004
 Alan+0.004
Neg logit contributions
itten-0.004
une-0.004
 arm-0.004
el-0.004
 nail-0.003
Token Jack
Token ID3619
Feature activation-5.03e+00

Pos logit contributions
fires+0.015
 MacDonald+0.013
lic+0.013
chers+0.013
brate+0.013
Neg logit contributions
el-0.019
 nail-0.018
 arm-0.018
une-0.017
itten-0.016
Token never
Token ID1239
Feature activation+4.22e+00

Pos logit contributions
fires+0.173
 war+0.167
 Skip+0.165
 MacDonald+0.163
 Alan+0.155
Neg logit contributions
itten-0.210
une-0.209
el-0.203
 arm-0.202
 nail-0.194
Token qu
Token ID627
Feature activation-4.71e+00

Pos logit contributions
une+0.157
 nail+0.157
 arm+0.153
raid+0.151
 brush+0.149
Neg logit contributions
fires-0.156
 MacDonald-0.155
 Skip-0.155
 Alan-0.145
Alan-0.138
Tokenarre
Token ID9624
Feature activation-1.70e+01

Pos logit contributions
 war+0.104
 Skip+0.103
 MacDonald+0.097
fires+0.095
 Alan+0.094
Neg logit contributions
itten-0.265
une-0.255
el-0.245
umb-0.239
 nail-0.239
Tokenled
Token ID992
Feature activation-3.58e+00

Pos logit contributions
 MacDonald+0.596
 Skip+0.590
 Alan+0.570
 war+0.515
Alan+0.512
Neg logit contributions
el-0.751
itten-0.685
 nail-0.673
 arm-0.673
umb-0.670
Token again
Token ID757
Feature activation-1.82e+00

Pos logit contributions
 MacDonald+0.159
fires+0.159
brate+0.158
 Skip+0.155
 war+0.147
Neg logit contributions
el-0.101
une-0.100
 arm-0.098
 nail-0.093
itten-0.090
Token.
Token ID13
Feature activation+6.02e-02

Pos logit contributions
 Skip+0.089
 MacDonald+0.086
 Alan+0.082
brate+0.081
fires+0.080
Neg logit contributions
 arm-0.050
el-0.049
itten-0.047
une-0.046
 nail-0.045
Token They
Token ID1119
Feature activation-6.09e+00

Pos logit contributions
itten+0.003
une+0.003
el+0.003
 nail+0.003
 arm+0.003
Neg logit contributions
 war-0.002
 Skip-0.002
fires-0.002
 MacDonald-0.002
 Alan-0.001
Token learned
Token ID4499
Feature activation-2.35e+00

Pos logit contributions
fires+0.195
 war+0.191
 MacDonald+0.188
 Skip+0.183
 Alan+0.173
Neg logit contributions
itten-0.270
une-0.267
el-0.253
 nail-0.252
 arm-0.252
Token the
Token ID262
Feature activation-1.33e+00

Pos logit contributions
 MacDonald+0.094
brate+0.090
 war+0.088
rob+0.083
fires+0.082
Neg logit contributions
 arm-0.095
el-0.093
 finger-0.090
 foot-0.089
 nail-0.088
Token parents
Token ID3397
Feature activation-2.51e+00

Pos logit contributions
 Skip+0.052
 war+0.052
fires+0.051
 Alan+0.051
 cheered+0.049
Neg logit contributions
itten-0.049
 arm-0.047
 knob-0.045
une-0.045
 nail-0.043
Token were
Token ID547
Feature activation-2.26e+00

Pos logit contributions
 war+0.088
 Skip+0.087
 MacDonald+0.086
fires+0.083
brate+0.081
Neg logit contributions
itten-0.103
el-0.100
une-0.098
 arm-0.098
 nail-0.095
Token also
Token ID635
Feature activation+4.83e+00

Pos logit contributions
 MacDonald+0.079
 war+0.077
brate+0.076
 Skip+0.076
fires+0.072
Neg logit contributions
 arm-0.092
itten-0.090
une-0.089
 nail-0.084
el-0.084
Token qu
Token ID627
Feature activation-4.77e+00

Pos logit contributions
 arm+0.198
itten+0.191
une+0.185
 nail+0.181
el+0.180
Neg logit contributions
 Skip-0.171
brate-0.170
 war-0.164
 MacDonald-0.163
 Alan-0.153
Tokenarre
Token ID9624
Feature activation-1.70e+01

Pos logit contributions
 Skip+0.128
 war+0.127
 MacDonald+0.119
 Alan+0.116
fires+0.115
Neg logit contributions
itten-0.251
une-0.238
el-0.235
umb-0.230
 arm-0.220
Tokenling
Token ID1359
Feature activation-1.76e+00

Pos logit contributions
 Skip+0.748
 MacDonald+0.732
 Alan+0.715
 Bow+0.694
Alan+0.675
Neg logit contributions
el-0.606
 bulb-0.547
 nail-0.545
itten-0.535
 ornament-0.514
Token.
Token ID13
Feature activation+2.13e-01

Pos logit contributions
brate+0.078
 MacDonald+0.074
 Skip+0.072
 war+0.072
fires+0.071
Neg logit contributions
 arm-0.056
el-0.054
une-0.050
itten-0.050
 knob-0.048
Token The
Token ID383
Feature activation+6.14e-01

Pos logit contributions
itten+0.008
une+0.008
el+0.008
 arm+0.007
 nail+0.007
Neg logit contributions
 war-0.008
fires-0.007
 Skip-0.007
 MacDonald-0.007
brate-0.007
Token first
Token ID717
Feature activation+6.18e+00

Pos logit contributions
itten+0.023
 arm+0.023
 knob+0.022
une+0.021
 nail+0.021
Neg logit contributions
 Skip-0.024
fires-0.023
 Alan-0.023
 war-0.022
 MacDonald-0.022
Token family
Token ID1641
Feature activation-2.06e+00

Pos logit contributions
itten+0.216
une+0.191
 arm+0.189
el+0.185
 knob+0.185
Neg logit contributions
 war-0.265
 Skip-0.265
fires-0.257
 Alan-0.250
brate-0.249
Token Finally
Token ID9461
Feature activation+2.70e+00

Pos logit contributions
itten+0.017
une+0.017
 arm+0.015
 nail+0.015
el+0.015
Neg logit contributions
 war-0.016
 MacDonald-0.015
fires-0.015
brate-0.015
 Skip-0.015
Token,
Token ID11
Feature activation-8.67e-01

Pos logit contributions
el+0.076
 arm+0.075
 nail+0.073
 knob+0.071
une+0.070
Neg logit contributions
fires-0.126
 MacDonald-0.126
brate-0.120
 seals-0.114
girls-0.113
Token after
Token ID706
Feature activation+1.19e-02

Pos logit contributions
 MacDonald+0.034
brate+0.030
fires+0.029
 Skip+0.026
core+0.026
Neg logit contributions
 nail-0.034
 arm-0.034
 knob-0.033
une-0.032
itten-0.032
Token much
Token ID881
Feature activation-7.87e-01

Pos logit contributions
 arm+0.000
 nail+0.000
el+0.000
itten+0.000
une+0.000
Neg logit contributions
 MacDonald-0.000
fires-0.000
 Skip-0.000
brate-0.000
 appet-0.000
Token qu
Token ID627
Feature activation-4.74e+00

Pos logit contributions
 MacDonald+0.032
fires+0.029
 Skip+0.028
Alan+0.027
 seals+0.027
Neg logit contributions
 nail-0.027
itten-0.026
une-0.026
el-0.025
 brush-0.025
Tokenarre
Token ID9624
Feature activation-1.70e+01

Pos logit contributions
 Skip+0.153
 war+0.150
 MacDonald+0.145
fires+0.144
 Alan+0.142
Neg logit contributions
itten-0.219
une-0.212
el-0.206
umb-0.197
 nail-0.190
Tokenling
Token ID1359
Feature activation-1.56e+00

Pos logit contributions
 Skip+0.799
 MacDonald+0.775
 Bow+0.766
 Alan+0.763
Alan+0.735
Neg logit contributions
el-0.539
els-0.425
 bulb-0.422
 nail-0.409
 knob-0.405
Token,
Token ID11
Feature activation-8.30e-01

Pos logit contributions
brate+0.065
 MacDonald+0.064
fires+0.060
 Skip+0.059
Alan+0.058
Neg logit contributions
 arm-0.051
el-0.050
une-0.049
 nail-0.046
itten-0.045
Token one
Token ID530
Feature activation+5.60e+00

Pos logit contributions
 MacDonald+0.032
brate+0.032
fires+0.029
 appet+0.027
ulating+0.026
Neg logit contributions
 nail-0.031
 arm-0.030
une-0.029
 knob-0.029
el-0.028
Token of
Token ID286
Feature activation+2.33e+00

Pos logit contributions
itten+0.210
une+0.195
 arm+0.188
 nail+0.187
el+0.184
Neg logit contributions
 MacDonald-0.226
 Skip-0.223
fires-0.220
 war-0.220
brate-0.213
Token the
Token ID262
Feature activation-1.34e+00

Pos logit contributions
itten+0.127
une+0.120
el+0.115
 nail+0.115
 arm+0.114
Neg logit contributions
 war-0.056
 Skip-0.053
fires-0.051
 MacDonald-0.050
 Alan-0.049
Token two
Token ID734
Feature activation+2.09e+00

Pos logit contributions
itten+0.071
une+0.065
 arm+0.062
 nail+0.061
el+0.060
Neg logit contributions
 war-0.074
 Skip-0.071
fires-0.071
 Alan-0.070
 MacDonald-0.069
Token squirrel
Token ID33039
Feature activation-5.76e-01

Pos logit contributions
itten+0.081
el+0.072
 arm+0.068
une+0.068
 nail+0.064
Neg logit contributions
fires-0.087
 war-0.084
 Alan-0.083
 Skip-0.082
 MacDonald-0.079
Tokens
Token ID82
Feature activation+4.31e+00

Pos logit contributions
 war+0.022
fires+0.020
 MacDonald+0.019
 Alan+0.019
 Skip+0.019
Neg logit contributions
itten-0.025
el-0.021
une-0.021
 arm-0.020
 nail-0.020
Token kept
Token ID4030
Feature activation+7.70e-01

Pos logit contributions
itten+0.193
une+0.182
 arm+0.173
el+0.169
 knob+0.164
Neg logit contributions
 war-0.151
 Skip-0.142
fires-0.140
 MacDonald-0.137
 Alan-0.136
Token qu
Token ID627
Feature activation-4.76e+00

Pos logit contributions
itten+0.036
 arm+0.033
el+0.033
une+0.032
 nail+0.032
Neg logit contributions
 war-0.024
fires-0.024
 MacDonald-0.023
 Skip-0.023
brate-0.023
Tokenarre
Token ID9624
Feature activation-1.70e+01

Pos logit contributions
 war+0.153
 Skip+0.153
 Alan+0.143
 MacDonald+0.142
fires+0.140
Neg logit contributions
itten-0.229
une-0.213
el-0.210
umb-0.206
 arm-0.196
Tokenling
Token ID1359
Feature activation-1.66e+00

Pos logit contributions
 war+0.709
 Skip+0.709
 Alan+0.702
 Bow+0.680
 MacDonald+0.676
Neg logit contributions
el-0.593
itten-0.586
umb-0.537
 arm-0.531
 nail-0.523
Token until
Token ID1566
Feature activation+2.36e+00

Pos logit contributions
 war+0.065
brate+0.065
fires+0.063
 MacDonald+0.062
 Alan+0.062
Neg logit contributions
 arm-0.058
itten-0.057
el-0.056
une-0.052
 nail-0.052
Token finally
Token ID3443
Feature activation+2.41e+00

Pos logit contributions
itten+0.107
el+0.100
 arm+0.099
une+0.097
 nail+0.095
Neg logit contributions
fires-0.076
 MacDonald-0.072
 war-0.069
brate-0.068
 Skip-0.067
Token Sammy
Token ID44067
Feature activation-1.88e+00

Pos logit contributions
el+0.090
itten+0.089
une+0.087
 arm+0.085
 knob+0.081
Neg logit contributions
fires-0.090
 war-0.080
 films-0.076
 battlefield-0.076
brate-0.076
Token said
Token ID531
Feature activation+3.06e-01

Pos logit contributions
 war+0.076
fires+0.074
 MacDonald+0.069
 Skip+0.069
 films+0.068
Neg logit contributions
itten-0.068
 arm-0.060
une-0.060
el-0.055
 nail-0.055
Token
Token ID198
Feature activation-1.51e-02

Pos logit contributions
 war+0.000
 Skip+0.000
fires+0.000
 Alan+0.000
 MacDonald+0.000
Neg logit contributions
itten-0.000
une-0.000
el-0.000
 nail-0.000
 arm-0.000
TokenThey
Token ID2990
Feature activation-5.96e+00

Pos logit contributions
 war+0.000
 Skip+0.000
 MacDonald+0.000
 Alan+0.000
fires+0.000
Neg logit contributions
itten-0.001
une-0.001
 nail-0.001
 arm-0.001
el-0.001
Token learn
Token ID2193
Feature activation-1.18e+00

Pos logit contributions
 war+0.201
fires+0.198
 Skip+0.197
 MacDonald+0.191
 Alan+0.186
Neg logit contributions
itten-0.253
une-0.248
 nail-0.236
 arm-0.234
el-0.232
Token that
Token ID326
Feature activation-3.09e-01

Pos logit contributions
fires+0.044
 MacDonald+0.042
 Skip+0.042
brate+0.041
 Alan+0.041
Neg logit contributions
 arm-0.046
itten-0.043
 nail-0.043
une-0.043
 bulb-0.042
Token qu
Token ID627
Feature activation-4.63e+00

Pos logit contributions
 war+0.008
 Skip+0.008
fires+0.008
 MacDonald+0.008
 Alan+0.008
Neg logit contributions
itten-0.015
une-0.014
 nail-0.014
 arm-0.014
el-0.014
Tokenarre
Token ID9624
Feature activation-1.70e+01

Pos logit contributions
 Skip+0.138
 war+0.134
 Alan+0.130
 MacDonald+0.129
fires+0.126
Neg logit contributions
itten-0.221
une-0.215
el-0.209
 nail-0.200
umb-0.200
Tokenling
Token ID1359
Feature activation-1.52e+00

Pos logit contributions
 Skip+0.606
 Alan+0.586
 MacDonald+0.570
 war+0.552
Alan+0.529
Neg logit contributions
el-0.711
 nail-0.650
itten-0.644
 bulb-0.638
els-0.633
Token is
Token ID318
Feature activation-4.87e-01

Pos logit contributions
 Skip+0.069
 Alan+0.068
brate+0.067
 MacDonald+0.067
Alan+0.066
Neg logit contributions
el-0.044
 arm-0.044
une-0.042
 nail-0.042
 bulb-0.041
Token bad
Token ID2089
Feature activation-4.06e+00

Pos logit contributions
 MacDonald+0.018
 Skip+0.017
 cheered+0.017
fires+0.017
 Alan+0.017
Neg logit contributions
une-0.018
itten-0.018
 nail-0.018
 arm-0.017
 knob-0.017
Token and
Token ID290
Feature activation-5.83e-02

Pos logit contributions
Alan+0.166
 Alan+0.165
 Skip+0.164
fires+0.162
 war+0.160
Neg logit contributions
itten-0.126
une-0.125
 arm-0.124
el-0.122
 nail-0.121
Token sharing
Token ID7373
Feature activation-6.04e+00

Pos logit contributions
 Skip+0.002
 MacDonald+0.002
 Alan+0.002
fires+0.002
Alan+0.002
Neg logit contributions
 nail-0.002
 bulb-0.002
 arm-0.002
itten-0.002
une-0.002
Token said
Token ID531
Feature activation+3.43e-01

Pos logit contributions
itten+0.062
une+0.058
el+0.056
 nail+0.056
 arm+0.056
Neg logit contributions
 war-0.046
 Skip-0.044
fires-0.043
 MacDonald-0.042
 Alan-0.041
Token,
Token ID11
Feature activation-7.11e-01

Pos logit contributions
une+0.013
itten+0.013
 nail+0.012
 arm+0.012
el+0.011
Neg logit contributions
fires-0.014
 MacDonald-0.013
 Skip-0.013
 seals-0.012
 war-0.012
Token "
Token ID366
Feature activation+1.18e+00

Pos logit contributions
 war+0.025
 Skip+0.024
fires+0.023
 Alan+0.023
 MacDonald+0.023
Neg logit contributions
itten-0.030
une-0.028
 arm-0.027
 nail-0.027
el-0.026
TokenStop
Token ID19485
Feature activation-5.12e+00

Pos logit contributions
itten+0.056
une+0.052
el+0.049
 nail+0.049
 arm+0.049
Neg logit contributions
 war-0.037
 Skip-0.035
fires-0.034
 MacDonald-0.034
 Alan-0.034
Token qu
Token ID627
Feature activation-4.65e+00

Pos logit contributions
fires+0.175
 Skip+0.167
Alan+0.167
 seals+0.160
 Alan+0.158
Neg logit contributions
 nail-0.210
itten-0.208
 arm-0.207
 knob-0.195
el-0.194
Tokenarre
Token ID9624
Feature activation-1.70e+01

Pos logit contributions
 Skip+0.105
 war+0.102
fires+0.097
 MacDonald+0.096
 Alan+0.094
Neg logit contributions
itten-0.260
une-0.247
el-0.242
umb-0.235
 nail-0.235
Tokenling
Token ID1359
Feature activation-1.39e+00

Pos logit contributions
 Skip+0.677
 MacDonald+0.642
 Alan+0.638
 seals+0.623
 Bow+0.611
Neg logit contributions
el-0.656
 nail-0.600
 arm-0.597
itten-0.590
umb-0.579
Token,
Token ID11
Feature activation-7.00e-01

Pos logit contributions
 Skip+0.057
 MacDonald+0.055
 Alan+0.055
fires+0.055
brate+0.054
Neg logit contributions
 arm-0.049
itten-0.047
el-0.046
une-0.045
 nail-0.045
Token boys
Token ID6510
Feature activation-7.02e+00

Pos logit contributions
 Skip+0.023
fires+0.023
 Alan+0.023
 war+0.023
Alan+0.022
Neg logit contributions
itten-0.031
 arm-0.029
 nail-0.029
une-0.028
 knob-0.028
Token.
Token ID13
Feature activation+4.00e-01

Pos logit contributions
 Skip+0.253
 war+0.248
fires+0.245
 Alan+0.242
 seals+0.233
Neg logit contributions
itten-0.294
une-0.274
 nail-0.270
 arm-0.268
el-0.266
Token You
Token ID921
Feature activation-3.61e+00

Pos logit contributions
itten+0.019
une+0.018
el+0.017
 nail+0.017
 arm+0.017
Neg logit contributions
 war-0.012
 Skip-0.012
fires-0.012
 MacDonald-0.011
 Alan-0.011
Token Lily
Token ID20037
Feature activation-2.82e-01

Pos logit contributions
itten+0.005
une+0.005
el+0.004
 nail+0.004
 arm+0.004
Neg logit contributions
 war-0.003
 Skip-0.003
 cheered-0.003
 Alan-0.003
fires-0.003
Token was
Token ID373
Feature activation-6.61e-01

Pos logit contributions
 cheered+0.007
 celebrated+0.006
 congratulated+0.006
 war+0.006
 they+0.006
Neg logit contributions
itten-0.015
une-0.014
umb-0.013
el-0.013
 knob-0.013
Token very
Token ID845
Feature activation-3.64e-01

Pos logit contributions
 war+0.014
 cheered+0.013
 Skip+0.013
 celebrating+0.012
 impressed+0.012
Neg logit contributions
itten-0.038
une-0.036
el-0.035
 nail-0.034
 knob-0.034
Token careful
Token ID8161
Feature activation+4.56e-01

Pos logit contributions
 impressed+0.008
 cheered+0.008
 war+0.007
 they+0.007
 congratulated+0.006
Neg logit contributions
itten-0.021
une-0.020
el-0.019
umb-0.018
 knob-0.018
Token and
Token ID290
Feature activation-2.63e-01

Pos logit contributions
itten+0.022
une+0.021
el+0.020
 nail+0.019
 arm+0.019
Neg logit contributions
 war-0.014
 Skip-0.013
fires-0.013
 Alan-0.012
 MacDonald-0.012
Token cut
Token ID2005
Feature activation+6.08e+00

Pos logit contributions
 war+0.008
 cheered+0.008
 Skip+0.008
 they+0.007
fires+0.007
Neg logit contributions
itten-0.013
une-0.012
el-0.011
umb-0.011
 arm-0.011
Token the
Token ID262
Feature activation-1.76e+00

Pos logit contributions
itten+0.325
une+0.296
umb+0.281
 nail+0.275
 axe+0.274
Neg logit contributions
 cheered-0.128
 they-0.128
 war-0.127
 Skip-0.120
fires-0.119
Token w
Token ID266
Feature activation-3.19e+00

Pos logit contributions
 war+0.044
 games+0.042
 players+0.042
 jokes+0.042
brate+0.040
Neg logit contributions
itten-0.089
une-0.084
el-0.079
 nail-0.078
umb-0.078
Tokenaffle
Token ID30697
Feature activation+1.27e+00

Pos logit contributions
 war+0.095
fires+0.093
brate+0.091
 jokes+0.089
 Skip+0.089
Neg logit contributions
itten-0.143
 nail-0.132
 arm-0.131
 bulb-0.130
une-0.129
Token into
Token ID656
Feature activation-1.85e+00

Pos logit contributions
itten+0.061
une+0.055
el+0.053
 nail+0.052
 arm+0.051
Neg logit contributions
 war-0.038
fires-0.036
 Skip-0.035
 cheered-0.035
 they-0.034
Token tiny
Token ID7009
Feature activation+3.16e+00

Pos logit contributions
 war+0.052
 games+0.049
 cheered+0.049
 they+0.048
ts+0.046
Neg logit contributions
itten-0.094
une-0.090
umb-0.078
 axe-0.075
 injection-0.075
Token paws
Token ID49193
Feature activation+3.17e+00

Pos logit contributions
itten+0.164
une+0.151
umb+0.147
el+0.138
 nail+0.132
Neg logit contributions
 war-0.146
 Skip-0.134
 Alan-0.126
fires-0.125
 games-0.125
Token to
Token ID284
Feature activation-5.09e-01

Pos logit contributions
itten+0.159
une+0.147
el+0.139
 nail+0.138
 knob+0.136
Neg logit contributions
 war-0.087
 cheered-0.081
 Skip-0.080
fires-0.079
 Alan-0.078
Token tear
Token ID11626
Feature activation+2.83e+00

Pos logit contributions
 war+0.020
 Skip+0.019
 cheered+0.019
fires+0.019
 Alan+0.019
Neg logit contributions
itten-0.020
une-0.018
el-0.017
umb-0.016
 arm-0.016
Token the
Token ID262
Feature activation-1.25e+00

Pos logit contributions
itten+0.147
une+0.134
umb+0.125
 nail+0.123
el+0.121
Neg logit contributions
 war-0.078
 Skip-0.073
 cheered-0.070
 Alan-0.070
fires-0.069
Token wrap
Token ID14441
Feature activation+2.69e+00

Pos logit contributions
 war+0.057
 Skip+0.053
fires+0.053
 MacDonald+0.052
 cheered+0.052
Neg logit contributions
itten-0.043
une-0.038
el-0.035
umb-0.034
 nail-0.034
Token open
Token ID1280
Feature activation+6.71e+00

Pos logit contributions
itten+0.121
une+0.112
el+0.106
 nail+0.105
 arm+0.104
Neg logit contributions
 war-0.090
 Skip-0.085
fires-0.082
 Alan-0.082
 cheered-0.081
Token.
Token ID13
Feature activation+2.13e-01

Pos logit contributions
itten+0.337
une+0.306
umb+0.283
 nail+0.280
el+0.276
Neg logit contributions
 war-0.194
 cheered-0.176
fires-0.174
 Skip-0.173
 games-0.173
Token Inside
Token ID14384
Feature activation+5.81e+00

Pos logit contributions
itten+0.009
une+0.008
el+0.008
 nail+0.008
 knob+0.008
Neg logit contributions
 war-0.007
 Skip-0.007
 Alan-0.007
 cheered-0.007
fires-0.007
Token the
Token ID262
Feature activation-1.25e+00

Pos logit contributions
itten+0.307
une+0.289
el+0.274
 nail+0.274
 arm+0.273
Neg logit contributions
 war-0.150
 Skip-0.141
fires-0.134
 Alan-0.133
 MacDonald-0.132
Token wrap
Token ID14441
Feature activation+2.68e+00

Pos logit contributions
 war+0.057
 Skip+0.053
fires+0.052
 MacDonald+0.051
 games+0.051
Neg logit contributions
itten-0.043
une-0.039
umb-0.035
el-0.034
 nail-0.033
Token,
Token ID11
Feature activation-8.05e-01

Pos logit contributions
itten+0.113
une+0.106
el+0.101
 nail+0.101
 arm+0.101
Neg logit contributions
 war-0.096
 Skip-0.093
 MacDonald-0.090
fires-0.090
brate-0.089
Token Sam
Token ID3409
Feature activation-2.53e+00

Pos logit contributions
itten+0.012
une+0.012
umb+0.012
el+0.011
ool+0.011
Neg logit contributions
 war-0.003
 Skip-0.003
 they-0.003
 Alan-0.002
 Bow-0.002
Token say
Token ID910
Feature activation-4.64e-01

Pos logit contributions
 war+0.093
fires+0.090
 Skip+0.089
 MacDonald+0.087
 Alan+0.085
Neg logit contributions
itten-0.102
une-0.096
el-0.092
 arm-0.091
 nail-0.090
Token.
Token ID13
Feature activation+9.81e-01

Pos logit contributions
 war+0.018
 Skip+0.018
 MacDonald+0.017
 Alan+0.017
fires+0.017
Neg logit contributions
itten-0.018
une-0.016
 arm-0.016
el-0.015
 nail-0.015
Token
Token ID198
Feature activation+2.43e-02

Pos logit contributions
itten+0.048
une+0.045
el+0.042
 nail+0.042
 arm+0.041
Neg logit contributions
 war-0.030
 Skip-0.029
 cheered-0.028
 Alan-0.028
 MacDonald-0.027
Token
Token ID198
Feature activation+2.75e-02

Pos logit contributions
itten+0.001
une+0.001
el+0.001
 nail+0.001
 knob+0.001
Neg logit contributions
 war-0.001
 Skip-0.001
 cheered-0.001
 Alan-0.001
 MacDonald-0.001
TokenMom
Token ID29252
Feature activation+9.20e+00

Pos logit contributions
itten+0.001
une+0.001
el+0.001
 nail+0.001
 arm+0.001
Neg logit contributions
 war-0.001
 Skip-0.001
fires-0.001
 MacDonald-0.001
 cheered-0.001
Token nods
Token ID34833
Feature activation-4.23e+00

Pos logit contributions
itten+0.457
une+0.428
el+0.406
 nail+0.405
 arm+0.402
Neg logit contributions
 war-0.267
 Skip-0.252
fires-0.242
 MacDonald-0.240
 Alan-0.240
Token and
Token ID290
Feature activation+2.15e-01

Pos logit contributions
 war+0.144
 Skip+0.137
fires+0.132
 MacDonald+0.132
 Alan+0.132
Neg logit contributions
itten-0.190
une-0.178
 nail-0.167
el-0.165
 arm-0.163
Token smiles
Token ID21845
Feature activation-5.64e+00

Pos logit contributions
itten+0.009
une+0.008
 arm+0.008
 nail+0.008
el+0.008
Neg logit contributions
 war-0.008
fires-0.007
 Skip-0.007
 Alan-0.007
 MacDonald-0.007
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
 war+0.250
 Skip+0.248
fires+0.243
brate+0.242
 Alan+0.238
Neg logit contributions
itten-0.177
 arm-0.172
el-0.165
une-0.165
 knob-0.156
Token She
Token ID1375
Feature activation+1.79e+00

Pos logit contributions
itten+0.041
une+0.038
el+0.036
 nail+0.035
 arm+0.035
Neg logit contributions
 war-0.038
 Skip-0.038
 MacDonald-0.036
 cheered-0.036
 Alan-0.036
Token wonderful
Token ID7932
Feature activation-6.26e+00

Pos logit contributions
 Skip+0.066
fires+0.065
 MacDonald+0.065
 war+0.065
 Alan+0.063
Neg logit contributions
itten-0.065
 nail-0.060
une-0.060
 arm-0.059
 knob-0.059
Token surprise
Token ID5975
Feature activation-4.78e-01

Pos logit contributions
 Skip+0.261
fires+0.260
 war+0.255
 MacDonald+0.255
 Alan+0.250
Neg logit contributions
itten-0.217
une-0.198
 nail-0.198
 knob-0.197
 arm-0.197
Token!
Token ID0
Feature activation-9.58e-01

Pos logit contributions
 war+0.017
 Skip+0.016
fires+0.016
 Alan+0.015
brate+0.015
Neg logit contributions
itten-0.021
une-0.019
 knob-0.019
el-0.019
 arm-0.019
Token
Token ID220
Feature activation+2.09e+00

Pos logit contributions
 war+0.034
 Skip+0.032
fires+0.031
 MacDonald+0.031
 Alan+0.031
Neg logit contributions
itten-0.041
une-0.039
el-0.036
 nail-0.036
 arm-0.036
Token
Token ID198
Feature activation-2.55e-01

Pos logit contributions
itten+0.092
une+0.086
el+0.081
 nail+0.081
 arm+0.080
Neg logit contributions
 war-0.072
 Skip-0.069
fires-0.067
 Alan-0.066
 MacDonald-0.066
TokenM
Token ID44
Feature activation+6.63e+00

Pos logit contributions
 war+0.009
 Skip+0.009
fires+0.008
 MacDonald+0.008
 Alan+0.008
Neg logit contributions
itten-0.011
une-0.010
el-0.010
 nail-0.010
 arm-0.010
Tokenama
Token ID1689
Feature activation+6.59e+00

Pos logit contributions
itten+0.237
une+0.216
 nail+0.206
 arm+0.206
 knob+0.201
Neg logit contributions
 war-0.275
 Skip-0.259
fires-0.256
 MacDonald-0.256
 Alan-0.255
Token and
Token ID290
Feature activation-1.73e-01

Pos logit contributions
itten+0.274
une+0.254
el+0.249
 arm+0.245
 knob+0.235
Neg logit contributions
 war-0.252
fires-0.233
 Skip-0.231
 MacDonald-0.224
brate-0.223
Token Papa
Token ID42328
Feature activation-1.48e+00

Pos logit contributions
 war+0.007
fires+0.007
brate+0.007
 MacDonald+0.007
 Skip+0.007
Neg logit contributions
itten-0.006
une-0.006
 arm-0.005
el-0.005
 nail-0.005
Token opened
Token ID4721
Feature activation+4.01e+00

Pos logit contributions
 war+0.052
 Skip+0.047
 MacDonald+0.047
fires+0.046
brate+0.045
Neg logit contributions
itten-0.066
une-0.062
el-0.062
 arm-0.061
 knob-0.060
Token the
Token ID262
Feature activation-1.38e+00

Pos logit contributions
itten+0.192
el+0.185
une+0.184
 arm+0.180
 knob+0.178
Neg logit contributions
 war-0.115
fires-0.110
 MacDonald-0.107
 Skip-0.107
brate-0.104
Tokenoll
Token ID692
Feature activation+5.69e+00

Pos logit contributions
 players+0.043
 Skip+0.043
 Alan+0.042
brate+0.042
 war+0.042
Neg logit contributions
el-0.041
 bulb-0.039
 knob-0.038
itten-0.037
 rag-0.036
Tokenipop
Token ID42800
Feature activation+5.36e+00

Pos logit contributions
umb+0.219
el+0.214
 nail+0.213
une+0.213
ipt+0.208
Neg logit contributions
 they-0.159
 Skip-0.152
brate-0.150
 players-0.141
 war-0.139
Token hiding
Token ID11816
Feature activation-1.96e+00

Pos logit contributions
itten+0.255
une+0.240
el+0.228
 nail+0.224
 arm+0.222
Neg logit contributions
 war-0.162
 Skip-0.152
fires-0.148
 Alan-0.145
 cheered-0.144
Token behind
Token ID2157
Feature activation+4.30e-01

Pos logit contributions
 war+0.062
 Skip+0.058
fires+0.057
 Alan+0.057
 cheered+0.055
Neg logit contributions
itten-0.094
une-0.087
el-0.081
 nail-0.081
 arm-0.080
Token a
Token ID257
Feature activation-1.80e+00

Pos logit contributions
itten+0.020
une+0.019
el+0.019
 arm+0.019
 nail+0.018
Neg logit contributions
 war-0.013
fires-0.012
 Skip-0.012
 MacDonald-0.012
 Alan-0.012
Token rock
Token ID3881
Feature activation+6.42e+00

Pos logit contributions
 war+0.086
 Skip+0.081
 cheered+0.078
fires+0.077
 Alan+0.077
Neg logit contributions
itten-0.056
une-0.051
el-0.049
umb-0.045
 arm-0.043
Token.
Token ID13
Feature activation+3.63e-01

Pos logit contributions
itten+0.294
une+0.276
el+0.257
 nail+0.256
 arm+0.253
Neg logit contributions
 war-0.210
 Skip-0.195
fires-0.191
 cheered-0.188
 Alan-0.188
Token John
Token ID1757
Feature activation-2.68e+00

Pos logit contributions
itten+0.016
une+0.014
 arm+0.014
el+0.014
 nail+0.014
Neg logit contributions
 war-0.013
fires-0.012
 Skip-0.012
 MacDonald-0.012
 Alan-0.011
Token was
Token ID373
Feature activation-3.26e-01

Pos logit contributions
 cheered+0.077
 war+0.073
 Skip+0.073
 Alan+0.070
 congratulated+0.069
Neg logit contributions
itten-0.134
une-0.126
umb-0.117
 knob-0.116
 nail-0.116
Token very
Token ID845
Feature activation-1.23e-01

Pos logit contributions
 war+0.009
 Skip+0.008
fires+0.008
 MacDonald+0.008
 Alan+0.008
Neg logit contributions
itten-0.017
une-0.016
el-0.015
 nail-0.015
 arm-0.015
Token excited
Token ID6568
Feature activation-1.88e+00

Pos logit contributions
 war+0.003
 Skip+0.003
fires+0.003
 MacDonald+0.003
 Alan+0.003
Neg logit contributions
itten-0.006
une-0.006
el-0.006
 nail-0.006
 arm-0.006
Token proud
Token ID6613
Feature activation-6.35e+00

Pos logit contributions
 Skip+0.012
 war+0.012
 MacDonald+0.012
 Alan+0.011
fires+0.011
Neg logit contributions
itten-0.018
 arm-0.017
une-0.017
 nail-0.016
el-0.016
Token of
Token ID286
Feature activation+2.24e+00

Pos logit contributions
 war+0.253
 Skip+0.244
fires+0.238
 Alan+0.235
 MacDonald+0.235
Neg logit contributions
itten-0.247
une-0.227
el-0.214
 nail-0.212
 arm-0.211
Token Lily
Token ID20037
Feature activation-2.15e-01

Pos logit contributions
itten+0.083
une+0.077
el+0.075
 nail+0.072
 arm+0.072
Neg logit contributions
 war-0.091
fires-0.087
 Skip-0.087
 MacDonald-0.086
 cheered-0.085
Token.
Token ID13
Feature activation+2.39e-01

Pos logit contributions
 war+0.009
fires+0.009
 Skip+0.009
 MacDonald+0.009
 Alan+0.009
Neg logit contributions
itten-0.007
 arm-0.007
une-0.007
el-0.007
 nail-0.006
Token She
Token ID1375
Feature activation+1.25e+00

Pos logit contributions
itten+0.010
une+0.009
el+0.009
umb+0.008
 nail+0.008
Neg logit contributions
 war-0.009
 cheered-0.009
 they-0.008
 Skip-0.008
 MacDonald-0.008
Token said
Token ID531
Feature activation+1.74e-01

Pos logit contributions
itten+0.050
une+0.047
 arm+0.046
 knob+0.045
 nail+0.045
Neg logit contributions
 war-0.046
fires-0.044
 Skip-0.044
 Alan-0.042
 MacDonald-0.041
Token she
Token ID673
Feature activation+8.70e-01

Pos logit contributions
itten+0.005
une+0.005
 nail+0.005
 arm+0.005
 ornament+0.005
Neg logit contributions
fires-0.008
 Skip-0.007
 MacDonald-0.007
Alan-0.007
 unison-0.007
Token forg
Token ID5784
Feature activation-4.59e+00

Pos logit contributions
itten+0.039
une+0.036
 arm+0.034
el+0.034
 nail+0.034
Neg logit contributions
 war-0.030
 Skip-0.028
 Alan-0.027
fires-0.027
 MacDonald-0.027
Tokenave
Token ID1015
Feature activation+1.83e+00

Pos logit contributions
 war+0.196
 Skip+0.192
 Alan+0.186
 MacDonald+0.181
fires+0.180
Neg logit contributions
itten-0.164
une-0.154
 arm-0.142
umb-0.140
el-0.137
Token her
Token ID607
Feature activation+3.62e+00

Pos logit contributions
itten+0.068
une+0.062
 nail+0.057
umb+0.055
 arm+0.055
Neg logit contributions
 war-0.077
 Skip-0.074
 Alan-0.071
 MacDonald-0.071
 cheered-0.071
Token.
Token ID13
Feature activation+1.81e-01

Pos logit contributions
itten+0.135
une+0.131
 arm+0.129
 knob+0.121
 nail+0.118
Neg logit contributions
 Skip-0.146
 war-0.145
 Alan-0.140
Alan-0.137
brate-0.136
Token toys
Token ID14958
Feature activation+8.44e-02

Pos logit contributions
itten+0.000
une+0.000
 arm+0.000
 nail+0.000
el+0.000
Neg logit contributions
 war-0.000
 Skip-0.000
 MacDonald-0.000
fires-0.000
 Alan-0.000
Token from
Token ID422
Feature activation-2.49e+00

Pos logit contributions
itten+0.003
une+0.003
 arm+0.003
el+0.003
 nail+0.003
Neg logit contributions
 war-0.003
 Skip-0.003
 MacDonald-0.003
 Alan-0.003
fires-0.003
Token his
Token ID465
Feature activation+2.19e+00

Pos logit contributions
 war+0.074
 Skip+0.070
fires+0.068
 Alan+0.067
 MacDonald+0.067
Neg logit contributions
itten-0.122
une-0.114
el-0.109
 nail-0.108
 arm-0.107
Token luggage
Token ID31488
Feature activation-3.85e-01

Pos logit contributions
itten+0.083
une+0.072
umb+0.072
el+0.066
 nail+0.062
Neg logit contributions
 war-0.098
 Skip-0.089
 games-0.088
 seals-0.084
fires-0.083
Token and
Token ID290
Feature activation+1.89e-02

Pos logit contributions
 war+0.015
 Skip+0.015
 MacDonald+0.014
 Alan+0.014
brate+0.014
Neg logit contributions
itten-0.015
une-0.014
 arm-0.013
el-0.013
 nail-0.013
Token put
Token ID1234
Feature activation+2.57e+00

Pos logit contributions
itten+0.001
une+0.001
 arm+0.001
 nail+0.001
el+0.001
Neg logit contributions
 war-0.001
 Skip-0.001
 MacDonald-0.001
fires-0.001
 Alan-0.001
Token them
Token ID606
Feature activation-2.65e+00

Pos logit contributions
itten+0.143
une+0.133
 nail+0.127
el+0.126
 arm+0.125
Neg logit contributions
 war-0.062
 Skip-0.058
fires-0.054
 Alan-0.054
 cheered-0.053
Token in
Token ID287
Feature activation-2.78e-01

Pos logit contributions
 war+0.099
 Skip+0.096
 MacDonald+0.096
 Alan+0.094
fires+0.093
Neg logit contributions
itten-0.105
une-0.099
 arm-0.096
el-0.095
 nail-0.093
Token his
Token ID465
Feature activation+2.33e+00

Pos logit contributions
 war+0.007
 Skip+0.007
 Alan+0.006
fires+0.006
 cheered+0.006
Neg logit contributions
itten-0.015
une-0.014
 nail-0.013
el-0.013
umb-0.013
Token backpack
Token ID22526
Feature activation+6.59e-01

Pos logit contributions
itten+0.084
une+0.075
umb+0.072
el+0.069
 nail+0.067
Neg logit contributions
 war-0.104
 Skip-0.095
 MacDonald-0.094
fires-0.093
 games-0.093
Token.
Token ID13
Feature activation+4.64e-01

Pos logit contributions
itten+0.030
une+0.028
el+0.026
 nail+0.026
 arm+0.026
Neg logit contributions
 war-0.022
 Skip-0.021
fires-0.020
 cheered-0.020
 Alan-0.020
Token best
Token ID1266
Feature activation-1.07e+00

Pos logit contributions
 war+0.060
 Skip+0.055
 Alan+0.053
 MacDonald+0.053
fires+0.052
Neg logit contributions
itten-0.075
une-0.069
el-0.066
 nail-0.063
 arm-0.063
Token picture
Token ID4286
Feature activation+3.44e+00

Pos logit contributions
 war+0.041
 games+0.037
 celebrating+0.036
 they+0.035
 parade+0.035
Neg logit contributions
itten-0.045
une-0.042
el-0.038
umb-0.038
 injection-0.037
Token she
Token ID673
Feature activation+7.30e-01

Pos logit contributions
itten+0.142
une+0.131
 arm+0.126
 nail+0.126
el+0.124
Neg logit contributions
 war-0.126
 Skip-0.121
fires-0.120
 MacDonald-0.120
 Alan-0.118
Token had
Token ID550
Feature activation-8.06e-01

Pos logit contributions
itten+0.029
une+0.027
 nail+0.026
 arm+0.026
el+0.025
Neg logit contributions
 war-0.027
 Skip-0.026
 Alan-0.025
fires-0.025
 MacDonald-0.025
Token ever
Token ID1683
Feature activation+8.75e-01

Pos logit contributions
 Skip+0.029
 war+0.029
 MacDonald+0.027
 Alan+0.027
fires+0.027
Neg logit contributions
itten-0.033
une-0.031
el-0.030
 arm-0.030
 nail-0.030
Token drawn
Token ID7428
Feature activation-3.90e-01

Pos logit contributions
itten+0.029
une+0.027
el+0.027
 nail+0.027
 arm+0.026
Neg logit contributions
 Skip-0.039
 war-0.036
 Alan-0.036
 MacDonald-0.035
fires-0.035
Token.
Token ID13
Feature activation+1.04e-01

Pos logit contributions
 war+0.012
 Skip+0.011
fires+0.011
 Alan+0.011
 MacDonald+0.011
Neg logit contributions
itten-0.019
une-0.017
 nail-0.016
el-0.016
 arm-0.016
Token She
Token ID1375
Feature activation+1.19e+00

Pos logit contributions
itten+0.004
une+0.004
el+0.004
 nail+0.003
 arm+0.003
Neg logit contributions
 war-0.004
 Skip-0.004
 Alan-0.004
 MacDonald-0.004
fires-0.004
Token wanted
Token ID2227
Feature activation+2.30e+00

Pos logit contributions
itten+0.058
une+0.054
el+0.051
 nail+0.050
 arm+0.050
Neg logit contributions
 war-0.036
 Skip-0.034
 cheered-0.034
 Alan-0.033
 MacDonald-0.032
Token to
Token ID284
Feature activation-4.80e-01

Pos logit contributions
itten+0.105
une+0.098
el+0.093
 nail+0.092
 arm+0.091
Neg logit contributions
 war-0.076
 Skip-0.073
fires-0.070
 Alan-0.070
 MacDonald-0.069
Token draw
Token ID3197
Feature activation+1.34e+00

Pos logit contributions
 war+0.013
 cheered+0.012
 jokes+0.012
 congratulated+0.012
 games+0.011
Neg logit contributions
itten-0.026
une-0.023
umb-0.022
el-0.021
 injection-0.021
Token us
Token ID514
Feature activation-2.64e+00

Pos logit contributions
itten+0.050
une+0.047
el+0.045
 nail+0.045
 arm+0.044
Neg logit contributions
 war-0.029
 Skip-0.028
fires-0.027
 MacDonald-0.026
 Alan-0.026
Token and
Token ID290
Feature activation+1.57e-01

Pos logit contributions
 war+0.103
 Skip+0.103
 MacDonald+0.101
 Alan+0.100
fires+0.097
Neg logit contributions
itten-0.099
une-0.094
 arm-0.091
el-0.089
 nail-0.086
Token hit
Token ID2277
Feature activation+3.46e-01

Pos logit contributions
itten+0.006
 arm+0.006
 nail+0.006
une+0.006
 knob+0.006
Neg logit contributions
 MacDonald-0.005
 Alan-0.005
Alan-0.005
 Skip-0.005
fires-0.005
Token us
Token ID514
Feature activation-2.64e+00

Pos logit contributions
itten+0.018
une+0.017
el+0.016
 nail+0.016
 arm+0.016
Neg logit contributions
 war-0.009
 Skip-0.009
fires-0.009
 Alan-0.009
 MacDonald-0.009
Token."
Token ID526
Feature activation-1.92e+00

Pos logit contributions
 war+0.089
 Skip+0.085
fires+0.083
 Alan+0.081
 cheered+0.081
Neg logit contributions
itten-0.118
une-0.110
el-0.103
 nail-0.103
 arm-0.101
Token
Token ID198
Feature activation-1.49e-01

Pos logit contributions
 war+0.052
 Skip+0.051
 cheered+0.050
 they+0.049
 MacDonald+0.048
Neg logit contributions
itten-0.097
une-0.092
umb-0.086
 nail-0.086
el-0.085
Token
Token ID198
Feature activation-1.44e-01

Pos logit contributions
 war+0.004
 Skip+0.004
 cheered+0.004
fires+0.004
 they+0.004
Neg logit contributions
itten-0.007
une-0.007
el-0.007
 nail-0.007
 knob-0.007
TokenBut
Token ID1537
Feature activation+4.44e+00

Pos logit contributions
 war+0.005
 Skip+0.005
fires+0.004
 cheered+0.004
 MacDonald+0.004
Neg logit contributions
itten-0.006
une-0.006
el-0.006
umb-0.006
 nail-0.006
Token Tim
Token ID5045
Feature activation+1.88e+00

Pos logit contributions
itten+0.209
une+0.194
el+0.187
 arm+0.187
 nail+0.185
Neg logit contributions
 war-0.139
 Skip-0.133
fires-0.130
 MacDonald-0.129
 Alan-0.128
Token did
Token ID750
Feature activation-9.45e-01

Pos logit contributions
itten+0.080
une+0.076
 nail+0.072
el+0.071
 bulb+0.070
Neg logit contributions
 war-0.061
 cheered-0.060
 Skip-0.059
 Alan-0.058
 MacDonald-0.056
Token not
Token ID407
Feature activation+5.36e-01

Pos logit contributions
 tournament+0.039
 war+0.039
 cheered+0.038
 MacDonald+0.038
 seals+0.038
Neg logit contributions
 arm-0.031
itten-0.030
une-0.027
 nail-0.027
 knob-0.027
Token.
Token ID13
Feature activation+1.10e+00

Pos logit contributions
 Skip+0.279
 Alan+0.275
Alan+0.271
fires+0.268
 war+0.265
Neg logit contributions
 arm-0.190
itten-0.188
 nail-0.177
 knob-0.173
el-0.173
Token He
Token ID679
Feature activation-3.18e-01

Pos logit contributions
itten+0.059
une+0.055
el+0.053
 egg+0.052
 nail+0.052
Neg logit contributions
 war-0.028
 Skip-0.028
 they-0.027
 MacDonald-0.026
 Alan-0.026
Token goes
Token ID2925
Feature activation-9.34e-01

Pos logit contributions
 war+0.011
 Skip+0.011
fires+0.010
 MacDonald+0.010
 Alan+0.010
Neg logit contributions
itten-0.014
une-0.013
el-0.012
 nail-0.012
 arm-0.012
Token back
Token ID736
Feature activation+1.69e+00

Pos logit contributions
 war+0.036
 Skip+0.035
 MacDonald+0.034
 Alan+0.034
fires+0.033
Neg logit contributions
itten-0.037
une-0.034
 arm-0.033
 nail-0.032
el-0.032
Token to
Token ID284
Feature activation-3.96e-01

Pos logit contributions
itten+0.083
une+0.077
el+0.072
 nail+0.071
umb+0.070
Neg logit contributions
 war-0.053
 Skip-0.050
fires-0.048
 cheered-0.047
 Alan-0.047
Token the
Token ID262
Feature activation-1.10e+00

Pos logit contributions
 war+0.010
 Skip+0.009
 Alan+0.009
 they+0.008
 celebrating+0.008
Neg logit contributions
itten-0.023
une-0.020
umb-0.019
el-0.019
 nail-0.019
Token living
Token ID2877
Feature activation-4.47e+00

Pos logit contributions
 war+0.048
 games+0.043
 Skip+0.043
fires+0.043
 cheered+0.042
Neg logit contributions
itten-0.042
une-0.038
el-0.036
umb-0.035
 nail-0.032
Token room
Token ID2119
Feature activation-1.88e-01

Pos logit contributions
 war+0.209
 Skip+0.203
fires+0.197
 Alan+0.197
 MacDonald+0.196
Neg logit contributions
itten-0.141
une-0.128
el-0.119
 arm-0.118
 nail-0.118
Token and
Token ID290
Feature activation+3.54e-01

Pos logit contributions
 war+0.007
 Skip+0.007
 Alan+0.007
 MacDonald+0.007
fires+0.006
Neg logit contributions
itten-0.008
une-0.007
 arm-0.007
 nail-0.007
el-0.007
Token lays
Token ID26614
Feature activation+4.84e-01

Pos logit contributions
itten+0.013
une+0.012
 arm+0.012
el+0.012
 nail+0.012
Neg logit contributions
 war-0.014
fires-0.014
 Skip-0.014
 Alan-0.013
 MacDonald-0.013
Token on
Token ID319
Feature activation+1.09e-01

Pos logit contributions
itten+0.024
une+0.022
umb+0.021
 nail+0.020
el+0.020
Neg logit contributions
 war-0.014
 they-0.013
 Skip-0.013
fires-0.013
 cheered-0.013
Token told
Token ID1297
Feature activation+1.12e+00

Pos logit contributions
itten+0.092
el+0.087
une+0.084
 arm+0.082
 knob+0.080
Neg logit contributions
 MacDonald-0.084
 war-0.083
fires-0.082
 Skip-0.079
brate-0.077
Token it
Token ID340
Feature activation+3.36e+00

Pos logit contributions
itten+0.041
el+0.039
une+0.039
 arm+0.039
 nail+0.037
Neg logit contributions
fires-0.045
 MacDonald-0.042
 war-0.042
brate-0.042
 cheered-0.041
Token to
Token ID284
Feature activation+9.83e-01

Pos logit contributions
itten+0.111
 arm+0.109
une+0.107
 nail+0.103
el+0.098
Neg logit contributions
fires-0.138
 MacDonald-0.137
 Skip-0.137
 war-0.136
Alan-0.135
Token keep
Token ID1394
Feature activation+5.39e+00

Pos logit contributions
itten+0.039
une+0.037
el+0.035
 nail+0.035
 arm+0.035
Neg logit contributions
 war-0.037
 Skip-0.036
fires-0.036
 MacDonald-0.035
 Alan-0.034
Token the
Token ID262
Feature activation-4.59e-01

Pos logit contributions
itten+0.259
une+0.243
el+0.232
 nail+0.230
 arm+0.230
Neg logit contributions
 war-0.163
 Skip-0.155
fires-0.151
 MacDonald-0.149
 Alan-0.148
Token message
Token ID3275
Feature activation-3.25e+00

Pos logit contributions
 war+0.020
 Skip+0.019
fires+0.018
 MacDonald+0.018
 Alan+0.018
Neg logit contributions
itten-0.016
une-0.015
el-0.014
 nail-0.014
 arm-0.013
Token safe
Token ID3338
Feature activation-1.82e+00

Pos logit contributions
 war+0.112
 Skip+0.109
 MacDonald+0.109
 Alan+0.105
fires+0.104
Neg logit contributions
itten-0.140
une-0.131
 arm-0.125
 nail-0.125
el-0.124
Token.
Token ID13
Feature activation+7.79e-01

Pos logit contributions
 war+0.070
 Skip+0.070
 MacDonald+0.068
brate+0.067
 Alan+0.067
Neg logit contributions
itten-0.069
une-0.064
 arm-0.064
el-0.063
 nail-0.062
Token
Token ID198
Feature activation+2.42e-01

Pos logit contributions
itten+0.034
une+0.032
el+0.030
 nail+0.030
 arm+0.029
Neg logit contributions
 war-0.027
 Skip-0.026
fires-0.025
 MacDonald-0.025
 Alan-0.025
Token
Token ID198
Feature activation+2.31e-01

Pos logit contributions
itten+0.011
une+0.011
el+0.010
 nail+0.010
 arm+0.010
Neg logit contributions
 war-0.008
 Skip-0.007
 Alan-0.007
 cheered-0.007
fires-0.007
TokenFrom
Token ID4863
Feature activation+5.64e-01

Pos logit contributions
itten+0.010
une+0.009
 nail+0.009
el+0.009
 arm+0.009
Neg logit contributions
 war-0.008
 Skip-0.007
fires-0.007
 MacDonald-0.007
 Alan-0.007
Token!
Token ID0
Feature activation-1.22e+00

Pos logit contributions
 MacDonald+0.200
fires+0.193
 Skip+0.192
brate+0.192
 war+0.187
Neg logit contributions
itten-0.148
une-0.145
 nail-0.145
 arm-0.141
el-0.138
Token Tim
Token ID5045
Feature activation+1.10e+00

Pos logit contributions
 war+0.033
 Skip+0.031
 Alan+0.029
 cheered+0.029
fires+0.028
Neg logit contributions
itten-0.064
une-0.059
el-0.057
 nail-0.056
 arm-0.056
Tokenmy
Token ID1820
Feature activation+3.97e+00

Pos logit contributions
itten+0.017
une+0.014
el+0.012
 arm+0.011
 nail+0.011
Neg logit contributions
 war-0.069
 Skip-0.068
fires-0.067
 Alan-0.066
 MacDonald-0.066
Token felt
Token ID2936
Feature activation-3.32e+00

Pos logit contributions
 arm+0.112
 nail+0.104
itten+0.101
 block+0.097
el+0.096
Neg logit contributions
fires-0.190
 war-0.177
 MacDonald-0.176
 Skip-0.169
brate-0.167
Token so
Token ID523
Feature activation-9.66e-01

Pos logit contributions
fires+0.152
 MacDonald+0.151
works+0.139
brate+0.138
girls+0.138
Neg logit contributions
 nail-0.091
 arm-0.088
 foot-0.086
 toe-0.084
 polish-0.079
Token happy
Token ID3772
Feature activation-3.12e+00

Pos logit contributions
 MacDonald+0.038
 Skip+0.037
fires+0.036
 seals+0.036
girls+0.036
Neg logit contributions
 nail-0.033
 arm-0.033
itten-0.032
 foot-0.031
une-0.031
Token and
Token ID290
Feature activation-8.08e-02

Pos logit contributions
 announcements+0.162
Alan+0.160
fires+0.160
 Skip+0.159
 war+0.159
Neg logit contributions
itten-0.057
 arm-0.054
 nail-0.049
el-0.049
 knob-0.043
Token successful
Token ID4388
Feature activation-4.32e+00

Pos logit contributions
fires+0.003
brate+0.003
 war+0.003
 films+0.003
 MacDonald+0.003
Neg logit contributions
 arm-0.003
 nail-0.002
 handle-0.002
 foot-0.002
 brush-0.002
Token.
Token ID13
Feature activation+3.95e-01

Pos logit contributions
 announcements+0.213
Alan+0.209
brate+0.206
 MacDonald+0.205
 war+0.200
Neg logit contributions
el-0.079
 arm-0.070
 er-0.062
 nail-0.059
 foot-0.058
Token
Token ID198
Feature activation-2.85e-01

Pos logit contributions
itten+0.020
une+0.019
el+0.018
 nail+0.018
 knob+0.018
Neg logit contributions
 war-0.011
 Skip-0.011
 Alan-0.010
 cheered-0.010
 they-0.010
Token
Token ID198
Feature activation-2.73e-01

Pos logit contributions
 war+0.008
 Skip+0.008
 cheered+0.008
 Alan+0.007
fires+0.007
Neg logit contributions
itten-0.014
une-0.014
el-0.013
 knob-0.013
 nail-0.013
Token fall
Token ID2121
Feature activation+1.65e+00

Pos logit contributions
 war+0.078
 Skip+0.074
fires+0.072
 Alan+0.071
 cheered+0.071
Neg logit contributions
itten-0.085
une-0.078
el-0.073
 nail-0.073
 arm-0.072
Token in
Token ID287
Feature activation-3.03e-01

Pos logit contributions
itten+0.073
une+0.067
el+0.063
 nail+0.063
 arm+0.061
Neg logit contributions
 war-0.057
 Skip-0.054
fires-0.052
 cheered-0.051
 Alan-0.051
Token."
Token ID526
Feature activation-2.02e+00

Pos logit contributions
 war+0.008
 Skip+0.008
fires+0.007
 MacDonald+0.007
 cheered+0.007
Neg logit contributions
itten-0.016
une-0.015
el-0.014
 nail-0.014
umb-0.013
Token Ben
Token ID3932
Feature activation-3.83e+00

Pos logit contributions
 war+0.083
fires+0.082
 Skip+0.079
 MacDonald+0.078
brate+0.077
Neg logit contributions
itten-0.070
une-0.068
el-0.065
 arm-0.064
 nail-0.064
Token was
Token ID373
Feature activation-2.47e-01

Pos logit contributions
 war+0.140
fires+0.131
 Skip+0.127
 celebrating+0.125
brate+0.122
Neg logit contributions
itten-0.165
 arm-0.154
une-0.152
el-0.149
 nail-0.144
Token curious
Token ID11040
Feature activation-2.44e+00

Pos logit contributions
 war+0.008
 Skip+0.008
 MacDonald+0.008
fires+0.008
brate+0.008
Neg logit contributions
itten-0.011
une-0.010
 arm-0.010
 nail-0.009
el-0.009
Token.
Token ID13
Feature activation+4.38e-01

Pos logit contributions
 Skip+0.100
 war+0.100
fires+0.098
 Alan+0.097
Alan+0.095
Neg logit contributions
itten-0.088
 arm-0.083
une-0.079
el-0.079
 knob-0.076
Token He
Token ID679
Feature activation-5.18e-01

Pos logit contributions
itten+0.021
une+0.019
el+0.018
 nail+0.018
 arm+0.018
Neg logit contributions
 war-0.014
 Skip-0.013
 Alan-0.013
 cheered-0.013
fires-0.013
Token said
Token ID531
Feature activation+5.60e-01

Pos logit contributions
 war+0.017
 Skip+0.016
fires+0.016
 MacDonald+0.015
 Alan+0.015
Neg logit contributions
itten-0.024
une-0.022
el-0.021
 nail-0.021
 arm-0.021
Token,
Token ID11
Feature activation-5.86e-01

Pos logit contributions
itten+0.022
une+0.021
 arm+0.021
 nail+0.020
el+0.020
Neg logit contributions
fires-0.021
 war-0.020
brate-0.020
 MacDonald-0.020
 tournament-0.020
Token "
Token ID366
Feature activation+1.33e+00

Pos logit contributions
 war+0.022
 Skip+0.021
 MacDonald+0.020
fires+0.020
 Alan+0.020
Neg logit contributions
itten-0.024
une-0.022
 arm-0.021
 nail-0.021
 knob-0.021
Token much
Token ID881
Feature activation-4.86e-02

Pos logit contributions
 MacDonald+0.005
 Skip+0.005
fires+0.005
 war+0.005
brate+0.005
Neg logit contributions
itten-0.007
une-0.006
 arm-0.006
 knob-0.006
 nail-0.006
Token better
Token ID1365
Feature activation-5.32e-01

Pos logit contributions
 Skip+0.002
 Alan+0.002
 MacDonald+0.002
fires+0.002
Alan+0.002
Neg logit contributions
itten-0.002
 knob-0.002
 nail-0.002
une-0.002
 arm-0.002
Token without
Token ID1231
Feature activation+8.71e-01

Pos logit contributions
 war+0.021
 Skip+0.021
brate+0.020
 Alan+0.020
 MacDonald+0.020
Neg logit contributions
itten-0.020
 arm-0.018
une-0.018
 nail-0.018
 knob-0.018
Token all
Token ID477
Feature activation+1.39e+00

Pos logit contributions
itten+0.039
une+0.037
el+0.036
 arm+0.036
 nail+0.035
Neg logit contributions
 war-0.028
 Skip-0.027
fires-0.027
 MacDonald-0.026
 Alan-0.026
Token the
Token ID262
Feature activation-1.14e+00

Pos logit contributions
itten+0.065
une+0.060
el+0.058
 arm+0.058
 nail+0.058
Neg logit contributions
 war-0.043
 Skip-0.042
fires-0.041
 MacDonald-0.041
 Alan-0.040
Token noise
Token ID7838
Feature activation-5.55e+00

Pos logit contributions
 Skip+0.044
 Alan+0.043
 MacDonald+0.043
 war+0.042
fires+0.042
Neg logit contributions
itten-0.043
 arm-0.040
une-0.040
 knob-0.039
 nail-0.039
Token!
Token ID0
Feature activation-6.54e-01

Pos logit contributions
 war+0.211
 Skip+0.211
 MacDonald+0.205
 Alan+0.202
fires+0.199
Neg logit contributions
itten-0.220
une-0.203
el-0.198
 arm-0.197
 nail-0.195
Token<|endoftext|>
Token ID50256
Feature activation-3.23e+00

Pos logit contributions
 war+0.022
 Skip+0.021
 Alan+0.020
fires+0.020
 MacDonald+0.020
Neg logit contributions
itten-0.030
une-0.028
el-0.026
 nail-0.026
 arm-0.026
TokenOnce
Token ID7454
Feature activation+2.32e+00

Pos logit contributions
 war+0.126
fires+0.118
 Skip+0.118
 MacDonald+0.116
brate+0.115
Neg logit contributions
itten-0.126
une-0.117
el-0.112
 arm-0.109
umb-0.107
Token upon
Token ID2402
Feature activation-2.64e+00

Pos logit contributions
itten+0.097
une+0.090
 nail+0.083
 arm+0.082
el+0.082
Neg logit contributions
 war-0.085
 Skip-0.081
 Alan-0.080
 they-0.078
 cheered-0.078
Token a
Token ID257
Feature activation-1.68e+00

Pos logit contributions
 war+0.091
fires+0.088
 MacDonald+0.087
 Skip+0.087
 Alan+0.085
Neg logit contributions
itten-0.111
 arm-0.102
une-0.100
 nail-0.100
el-0.097
Token
Token ID198
Feature activation+7.61e-01

Pos logit contributions
itten+0.059
une+0.055
el+0.052
 nail+0.051
 arm+0.051
Neg logit contributions
 war-0.051
 Skip-0.048
fires-0.047
 MacDonald-0.047
 Alan-0.046
Token
Token ID198
Feature activation+6.51e-01

Pos logit contributions
itten+0.038
une+0.037
 nail+0.035
 knob+0.035
el+0.035
Neg logit contributions
 Skip-0.021
 war-0.020
 cheered-0.020
 Alan-0.020
fires-0.018
TokenThey
Token ID2990
Feature activation-5.93e+00

Pos logit contributions
itten+0.028
une+0.027
el+0.025
 nail+0.025
 arm+0.024
Neg logit contributions
 war-0.023
 Skip-0.022
 Alan-0.021
fires-0.021
 cheered-0.021
Token played
Token ID2826
Feature activation-4.31e+00

Pos logit contributions
 war+0.200
 Skip+0.191
 MacDonald+0.190
fires+0.190
 Alan+0.180
Neg logit contributions
itten-0.260
une-0.245
el-0.237
 arm-0.236
 nail-0.233
Token a
Token ID257
Feature activation-1.28e+00

Pos logit contributions
 MacDonald+0.183
brate+0.173
fires+0.166
 tournament+0.163
Alan+0.162
Neg logit contributions
 arm-0.134
 block-0.129
 nail-0.121
 foot-0.120
 leaf-0.114
Token fun
Token ID1257
Feature activation-6.93e+00

Pos logit contributions
 MacDonald+0.041
 Alan+0.040
fires+0.040
 Skip+0.040
 war+0.039
Neg logit contributions
itten-0.056
 nail-0.053
 arm-0.051
 knob-0.050
 bulb-0.049
Token game
Token ID983
Feature activation-4.74e+00

Pos logit contributions
fires+0.255
 MacDonald+0.253
 Skip+0.252
 war+0.249
 Alan+0.248
Neg logit contributions
itten-0.284
 arm-0.252
 nail-0.251
une-0.248
 knob-0.241
Token.
Token ID13
Feature activation+2.57e-01

Pos logit contributions
 war+0.179
 MacDonald+0.177
 Skip+0.174
brate+0.174
fires+0.172
Neg logit contributions
itten-0.182
une-0.168
 arm-0.165
 nail-0.163
el-0.155
Token Tim
Token ID5045
Feature activation+8.84e-01

Pos logit contributions
itten+0.012
une+0.011
 arm+0.011
el+0.011
 nail+0.011
Neg logit contributions
 war-0.008
fires-0.007
 MacDonald-0.007
brate-0.007
 Skip-0.007
Token won
Token ID1839
Feature activation-1.42e+00

Pos logit contributions
itten+0.035
 arm+0.032
une+0.031
el+0.031
 nail+0.030
Neg logit contributions
 war-0.035
fires-0.034
 Skip-0.033
 MacDonald-0.032
 Alan-0.032
Token the
Token ID262
Feature activation-1.74e+00

Pos logit contributions
fires+0.052
 seals+0.050
brate+0.050
Alan+0.050
 Alan+0.049
Neg logit contributions
 arm-0.053
 nail-0.051
itten-0.049
el-0.048
une-0.047
Token the
Token ID262
Feature activation-8.42e-01

Pos logit contributions
itten+0.006
une+0.006
 nail+0.006
 arm+0.006
el+0.006
Neg logit contributions
 war-0.005
fires-0.005
 Skip-0.005
 MacDonald-0.005
 Alan-0.004
Token birds
Token ID10087
Feature activation-2.72e+00

Pos logit contributions
 war+0.032
 Skip+0.032
fires+0.031
 Alan+0.031
 cheered+0.030
Neg logit contributions
itten-0.034
une-0.031
 arm-0.029
 nail-0.029
el-0.029
Token were
Token ID547
Feature activation-1.92e+00

Pos logit contributions
 MacDonald+0.090
 Skip+0.090
 war+0.087
 Alan+0.087
fires+0.085
Neg logit contributions
itten-0.114
el-0.113
une-0.110
 bulb-0.108
 nail-0.108
Token only
Token ID691
Feature activation+6.52e+00

Pos logit contributions
 MacDonald+0.073
brate+0.070
 Skip+0.070
fires+0.069
 tournament+0.067
Neg logit contributions
 arm-0.070
itten-0.070
une-0.070
 nail-0.069
 bulb-0.068
Token qu
Token ID627
Feature activation-3.86e+00

Pos logit contributions
 arm+0.253
itten+0.252
une+0.247
el+0.242
 nail+0.240
Neg logit contributions
 MacDonald-0.231
brate-0.225
 Skip-0.223
fires-0.223
 war-0.216
Tokenarre
Token ID9624
Feature activation-1.59e+01

Pos logit contributions
 war+0.089
 Skip+0.084
fires+0.079
 MacDonald+0.079
 Alan+0.078
Neg logit contributions
itten-0.216
une-0.204
el-0.197
 nail-0.194
 arm-0.193
Tokenling
Token ID1359
Feature activation-6.53e-01

Pos logit contributions
 Skip+0.707
 MacDonald+0.691
 Alan+0.691
Alan+0.657
 Bow+0.649
Neg logit contributions
el-0.573
 bulb-0.521
 nail-0.514
itten-0.497
 arm-0.475
Token like
Token ID588
Feature activation-6.56e-01

Pos logit contributions
brate+0.027
 MacDonald+0.027
 Skip+0.027
 tournament+0.026
 war+0.026
Neg logit contributions
el-0.021
 arm-0.021
itten-0.020
une-0.020
 bulb-0.019
Token little
Token ID1310
Feature activation+3.72e+00

Pos logit contributions
 MacDonald+0.023
fires+0.023
brate+0.023
 cheered+0.022
 Skip+0.022
Neg logit contributions
 nail-0.024
itten-0.023
une-0.023
 arm-0.023
 bulb-0.023
Token children
Token ID1751
Feature activation-4.93e+00

Pos logit contributions
el+0.118
itten+0.116
 egg+0.111
 arm+0.111
une+0.110
Neg logit contributions
fires-0.156
brate-0.155
 Skip-0.154
 Alan-0.147
 war-0.147
Token do
Token ID466
Feature activation-1.42e+00

Pos logit contributions
 Skip+0.200
 war+0.195
 Alan+0.194
 MacDonald+0.192
Alan+0.190
Neg logit contributions
itten-0.174
une-0.164
 arm-0.161
el-0.159
 nail-0.156
Token The
Token ID383
Feature activation+6.61e-01

Pos logit contributions
itten+0.017
une+0.016
el+0.015
 nail+0.015
 arm+0.015
Neg logit contributions
 war-0.016
fires-0.016
 MacDonald-0.015
brate-0.015
 Skip-0.015
Token bird
Token ID6512
Feature activation+1.86e+00

Pos logit contributions
itten+0.019
une+0.018
 arm+0.017
 nail+0.017
el+0.016
Neg logit contributions
fires-0.032
 Skip-0.031
 war-0.031
 MacDonald-0.031
brate-0.030
Token explained
Token ID4893
Feature activation-3.84e-01

Pos logit contributions
itten+0.093
une+0.087
el+0.083
 nail+0.082
 arm+0.082
Neg logit contributions
 war-0.053
 Skip-0.050
fires-0.048
 Alan-0.048
 cheered-0.047
Token about
Token ID546
Feature activation-3.83e+00

Pos logit contributions
fires+0.014
 MacDonald+0.013
 Skip+0.013
 war+0.013
brate+0.013
Neg logit contributions
itten-0.015
une-0.015
 nail-0.015
 arm-0.014
el-0.014
Token the
Token ID262
Feature activation-1.51e+00

Pos logit contributions
fires+0.127
 MacDonald+0.124
 cheered+0.124
 Skip+0.117
brate+0.116
Neg logit contributions
itten-0.158
 nail-0.155
une-0.154
 arm-0.152
el-0.151
Token war
Token ID1175
Feature activation-1.09e+01

Pos logit contributions
 Skip+0.058
 MacDonald+0.058
fires+0.057
 cheered+0.056
 Alan+0.055
Neg logit contributions
itten-0.057
une-0.055
 nail-0.054
 arm-0.053
 knob-0.052
Token and
Token ID290
Feature activation-2.48e-01

Pos logit contributions
 MacDonald+0.427
 Skip+0.425
 war+0.423
brate+0.415
 Alan+0.412
Neg logit contributions
itten-0.371
 arm-0.352
 nail-0.352
une-0.348
el-0.343
Token how
Token ID703
Feature activation+8.22e-01

Pos logit contributions
 MacDonald+0.008
brate+0.008
fires+0.008
 Skip+0.008
 war+0.008
Neg logit contributions
 nail-0.010
el-0.009
 arm-0.009
itten-0.009
une-0.009
Token it
Token ID340
Feature activation+2.43e+00

Pos logit contributions
 nail+0.031
itten+0.030
une+0.029
 bulb+0.029
el+0.028
Neg logit contributions
 MacDonald-0.031
 Skip-0.030
 Alan-0.029
 seals-0.029
brate-0.028
Token was
Token ID373
Feature activation-4.56e-01

Pos logit contributions
itten+0.093
une+0.091
 nail+0.088
el+0.087
 bulb+0.085
Neg logit contributions
 MacDonald-0.087
 war-0.086
 Skip-0.084
fires-0.083
 Alan-0.083
Token making
Token ID1642
Feature activation-2.60e+00

Pos logit contributions
 MacDonald+0.017
 Skip+0.016
 Alan+0.015
brate+0.015
Alan+0.015
Neg logit contributions
itten-0.017
une-0.017
 nail-0.017
 arm-0.017
 bulb-0.016
TokenFinally
Token ID11158
Feature activation+4.11e+00

Pos logit contributions
itten+0.002
une+0.002
el+0.002
 nail+0.002
 arm+0.002
Neg logit contributions
 war-0.001
 Skip-0.001
fires-0.001
 MacDonald-0.001
 Alan-0.001
Token,
Token ID11
Feature activation-5.71e-01

Pos logit contributions
itten+0.137
el+0.134
 arm+0.131
une+0.127
 nail+0.126
Neg logit contributions
fires-0.175
 MacDonald-0.161
brate-0.158
 impressed-0.155
 war-0.155
Token Tim
Token ID5045
Feature activation+1.23e+00

Pos logit contributions
fires+0.018
 MacDonald+0.018
brate+0.017
 war+0.017
 cheered+0.015
Neg logit contributions
itten-0.025
 nail-0.024
une-0.024
 arm-0.024
 knob-0.023
Tokenmy
Token ID1820
Feature activation+4.53e+00

Pos logit contributions
itten+0.037
une+0.033
el+0.031
 arm+0.031
 nail+0.030
Neg logit contributions
 war-0.061
 Skip-0.059
fires-0.058
 MacDonald-0.057
 Alan-0.057
Token fell
Token ID3214
Feature activation+2.34e+00

Pos logit contributions
itten+0.164
une+0.157
 arm+0.153
el+0.147
 nail+0.144
Neg logit contributions
fires-0.185
 war-0.184
 Skip-0.177
brate-0.175
 MacDonald-0.174
Token asleep
Token ID16039
Feature activation-1.05e+01

Pos logit contributions
itten+0.114
une+0.107
el+0.101
 nail+0.100
umb+0.097
Neg logit contributions
 war-0.070
 Skip-0.066
 cheered-0.062
 Alan-0.062
fires-0.061
Token and
Token ID290
Feature activation+1.99e-01

Pos logit contributions
 war+0.429
brate+0.413
 MacDonald+0.410
 Skip+0.402
 seals+0.400
Neg logit contributions
 arm-0.375
itten-0.368
une-0.333
 knob-0.323
 nail-0.319
Token had
Token ID550
Feature activation-9.45e-01

Pos logit contributions
itten+0.007
 arm+0.007
une+0.007
 nail+0.007
 knob+0.007
Neg logit contributions
 war-0.007
 MacDonald-0.007
fires-0.007
 Skip-0.007
 Alan-0.007
Token a
Token ID257
Feature activation-1.75e+00

Pos logit contributions
fires+0.038
 MacDonald+0.036
 Skip+0.035
 Alan+0.034
 war+0.034
Neg logit contributions
 arm-0.034
itten-0.033
une-0.032
el-0.031
 nail-0.031
Token good
Token ID922
Feature activation-2.06e+00

Pos logit contributions
fires+0.056
 war+0.055
 Skip+0.055
 MacDonald+0.054
 Alan+0.053
Neg logit contributions
itten-0.079
une-0.073
 arm-0.071
 nail-0.071
 knob-0.068
Token dream
Token ID4320
Feature activation+1.69e-01

Pos logit contributions
 war+0.077
 Skip+0.076
fires+0.076
 MacDonald+0.075
 Alan+0.074
Neg logit contributions
itten-0.083
une-0.076
 arm-0.073
 nail-0.071
el-0.070
Token and
Token ID290
Feature activation+3.10e-01

Pos logit contributions
 war+0.002
 Skip+0.002
 MacDonald+0.002
fires+0.002
 Alan+0.002
Neg logit contributions
itten-0.003
 arm-0.003
une-0.003
el-0.003
 nail-0.003
Token pretend
Token ID16614
Feature activation+9.93e-01

Pos logit contributions
itten+0.011
 arm+0.010
 knob+0.010
une+0.010
 nail+0.010
Neg logit contributions
 war-0.013
 Skip-0.012
 MacDonald-0.012
fires-0.012
 Alan-0.012
Token to
Token ID284
Feature activation-1.68e-01

Pos logit contributions
 arm+0.043
 knob+0.042
itten+0.042
 egg+0.041
 nail+0.041
Neg logit contributions
 Skip-0.030
Alan-0.030
 Alan-0.030
brate-0.029
 tournament-0.029
Token be
Token ID307
Feature activation+2.26e-01

Pos logit contributions
 war+0.006
 Skip+0.005
fires+0.005
 MacDonald+0.005
 cheered+0.005
Neg logit contributions
itten-0.008
une-0.007
umb-0.007
el-0.007
 nail-0.006
Token opera
Token ID27296
Feature activation-5.13e+00

Pos logit contributions
 arm+0.009
 nail+0.008
une+0.008
 knob+0.008
 egg+0.008
Neg logit contributions
brate-0.008
 Skip-0.008
 MacDonald-0.007
 congratulated-0.007
 Alan-0.007
Token singers
Token ID39113
Feature activation-1.15e+01

Pos logit contributions
 Skip+0.237
 Alan+0.230
Alan+0.228
 war+0.224
brate+0.217
Neg logit contributions
 knob-0.147
 arm-0.140
une-0.136
itten-0.135
 bulb-0.131
Token.
Token ID13
Feature activation+8.79e-01

Pos logit contributions
 Skip+0.511
 war+0.510
brate+0.496
 Alan+0.494
Alan+0.489
Neg logit contributions
itten-0.335
 arm-0.327
el-0.316
une-0.311
 knob-0.305
Token
Token ID198
Feature activation+2.93e-01

Pos logit contributions
itten+0.046
une+0.043
el+0.041
 nail+0.041
 arm+0.040
Neg logit contributions
 war-0.024
 Skip-0.023
 Alan-0.022
fires-0.022
 MacDonald-0.021
Token
Token ID198
Feature activation+3.03e-01

Pos logit contributions
itten+0.016
une+0.015
el+0.014
 nail+0.014
 knob+0.014
Neg logit contributions
 Skip-0.008
 war-0.008
 cheered-0.007
 they-0.007
 Alan-0.007
Token"
Token ID1
Feature activation+3.74e+00

Pos logit contributions
itten+0.013
une+0.012
el+0.011
 arm+0.011
 nail+0.011
Neg logit contributions
 war-0.011
 Skip-0.011
fires-0.010
 Alan-0.010
 cheered-0.010
TokenHello
Token ID15496
Feature activation-1.90e+00

Pos logit contributions
itten+0.159
une+0.147
el+0.139
 nail+0.139
 arm+0.138
Neg logit contributions
 war-0.135
 Skip-0.129
fires-0.125
 Alan-0.125
 MacDonald-0.123
Token Ben
Token ID3932
Feature activation-4.16e+00

Pos logit contributions
 war+0.014
brate+0.013
 MacDonald+0.013
 Skip+0.013
fires+0.013
Neg logit contributions
itten-0.017
 arm-0.017
une-0.016
el-0.016
 nail-0.016
Token!
Token ID0
Feature activation-1.10e+00

Pos logit contributions
 war+0.193
brate+0.189
fires+0.185
 Skip+0.181
 Alan+0.177
Neg logit contributions
itten-0.130
 arm-0.129
el-0.122
une-0.119
 nail-0.108
Token
Token ID198
Feature activation-4.31e-02

Pos logit contributions
 war+0.037
 Skip+0.036
fires+0.035
 Alan+0.034
 MacDonald+0.034
Neg logit contributions
itten-0.049
une-0.046
el-0.043
 nail-0.043
 arm-0.043
Token
Token ID198
Feature activation-4.59e-02

Pos logit contributions
 war+0.001
 Skip+0.001
 cheered+0.001
 Alan+0.001
fires+0.001
Neg logit contributions
itten-0.002
une-0.002
el-0.002
 nail-0.002
 arm-0.002
TokenThe
Token ID464
Feature activation+1.61e+00

Pos logit contributions
 war+0.002
 Skip+0.002
fires+0.002
 MacDonald+0.002
 Alan+0.002
Neg logit contributions
itten-0.002
une-0.002
el-0.002
 nail-0.002
 arm-0.002
Token audience
Token ID5386
Feature activation-1.12e+01

Pos logit contributions
itten+0.065
une+0.060
 arm+0.058
 nail+0.058
 knob+0.057
Neg logit contributions
 war-0.059
 Skip-0.059
fires-0.057
 MacDonald-0.057
 Alan-0.056
Token cheers
Token ID34550
Feature activation-7.84e+00

Pos logit contributions
 Skip+0.380
fires+0.371
 war+0.371
 MacDonald+0.348
 Alan+0.346
Neg logit contributions
el-0.441
une-0.430
 knob-0.428
 arm-0.422
 bulb-0.419
Token and
Token ID290
Feature activation-1.23e-01

Pos logit contributions
brate+0.373
fires+0.369
 tournament+0.363
 war+0.359
 MacDonald+0.356
Neg logit contributions
el-0.212
 arm-0.204
 knob-0.194
itten-0.181
une-0.179
Token cl
Token ID537
Feature activation-4.25e+00

Pos logit contributions
fires+0.005
brate+0.004
 war+0.004
ggies+0.004
Roger+0.004
Neg logit contributions
 brush-0.004
 arm-0.004
 knob-0.004
 clip-0.004
 comb-0.004
Tokenaps
Token ID1686
Feature activation-6.08e+00

Pos logit contributions
 war+0.170
 Skip+0.163
brate+0.160
fires+0.158
 games+0.153
Neg logit contributions
el-0.162
une-0.160
itten-0.157
umb-0.142
 arm-0.141
Token.
Token ID13
Feature activation+8.27e-01

Pos logit contributions
brate+0.263
fires+0.254
 MacDonald+0.251
 tournament+0.239
 war+0.239
Neg logit contributions
el-0.201
 arm-0.197
itten-0.183
 knob-0.181
une-0.177