TOP ACTIVATIONS
MAX = 0.202

you ". The chip m unk and Sam were
. They all agreed to chip in some money so that
at these places that the chip m unk revealed something truly
said Sammy . " This sausage is so big !"
, and even mint chocolate chip . But her favorite was
after that . Whenever the chip m unk needed help ,
place ! The chip mun ks didn 't know
floor . The chip mun ks were very curious
bird . Luckily , the chip m unk said they should
her favorite -- ch ocolate chip ! She was very happy
frog agreed , and the chip m unk agreed too .
. The chip m unk told the boy
they decided to make chocolate chip cookies . Lily 's mom
cookies . They are chocolate chip . My favorite . Maybe
so she gave the spicy chip to the raven . The
loved cookies , especially chocolate chip cookies . One day ,
chip m unk . The chip m unk wanted the boy
very excited to bake chocolate chip cookies . Lily helped her
in her paws . The chip m unk got closer and
too . The chip m unk helped the frog

MIN ACTIVATIONS
MIN = -0.208

around , she saw a grace fully cur ving snake near
to cry and threw a tant rum . She didn 't
bag . Lily was over joy ed and hugged her blue
kept crying and throwing a tant rum . Finally
She cried and threw a tant rum . Her mom tried
Jack was over joy ed , and quickly said
John was over joy ed and asked the woman
all ." Lucy was over joy ed and quickly grabbed the
listen . She threw a tant rum in the store .
Cl aire was over joy ed - her mug had
. Tim my was over joy ed and said , "
The rabbit was over joy ed ! He hopped up
and so she threw a tant rum when her parents said
sad . She threw a tant rum and cried loudly .
The little girl was over joy ed and she thanked her
R uf us was over joy ed and as he left
Jack was over joy ed . He and Jill
The oct opus was over joy ed , and he thanked
her feet and threw a tant rum . She grabbed the
S ally was so over joy ed with her present that

INTERVAL 0.099 - 0.202
CONTAINS 0.930%

The bird was surprised but also scared because all igators are
be seen . He was so scared he couldn 't move
with pride , � � € � � We made this
s like this , â € she said . Mike tried
P olly was so excited , she pract ised

INTERVAL -0.003 - 0.099
CONTAINS 54.146%

, it 's mine , I saw it first !" Sam
," her mom replied . L ily didn 't
Lily smiled and said , " I know , my grandma
kept on playing . The little girl and the
her butterfly , but at least she had a fun story

INTERVAL -0.106 - -0.003
CONTAINS 44.412%

all your dinner , I will give you a special reward
have him with her on their trip . <|endoftext|> Once upon
together they all worked together to turn it back into a
ready . As P ia spread her wings
. <|endoftext|> Once upon a time , in a small house

INTERVAL -0.208 - -0.106
CONTAINS 0.511%

mistake ." God heard his prayer and felt sorry
just couldn â € ™ t reach it . Then a
soft sweater . And he never opened the zipper coat 's
again tomorrow . <|endoftext|> Once upon a time , there was
cried . Ben heard Lily . He ran to
Token you
Token ID345
Feature activation-5.98e-02

Pos logit contributions
arl+0.001
lessness+0.001
ily+0.001
anger+0.001
der+0.001
Neg logit contributions
 bank-0.001
load-0.001
ior-0.001
 rely-0.001
 roasted-0.001
Token".
Token ID1911
Feature activation+1.53e-03

Pos logit contributions
arl+0.088
ily+0.085
lessness+0.083
anger+0.083
anish+0.079
Neg logit contributions
 bank-0.085
 afloat-0.083
 roasted-0.082
 rely-0.081
load-0.081
Token
Token ID198
Feature activation+1.07e-02

Pos logit contributions
 bank+0.002
 roasted+0.002
 afloat+0.002
load+0.002
 rely+0.002
Neg logit contributions
ily-0.002
lessness-0.002
arl-0.002
anish-0.002
ed-0.002
Token
Token ID198
Feature activation+9.09e-03

Pos logit contributions
 bank+0.017
 forth+0.016
 afloat+0.016
 discuss+0.016
 roasted+0.016
Neg logit contributions
ily-0.016
arl-0.014
lessness-0.014
anger-0.013
ed-0.013
TokenThe
Token ID464
Feature activation-3.82e-03

Pos logit contributions
 bank+0.014
 roasted+0.014
 afloat+0.014
load+0.014
ior+0.014
Neg logit contributions
ily-0.012
arl-0.011
lessness-0.011
anish-0.011
der-0.010
Token chip
Token ID11594
Feature activation+2.02e-01

Pos logit contributions
ily+0.005
 words+0.004
arl+0.004
der+0.004
less+0.004
Neg logit contributions
 afloat-0.006
ior-0.006
bowl-0.006
load-0.006
 Junior-0.006
Tokenm
Token ID76
Feature activation+7.08e-02

Pos logit contributions
 afloat+0.337
 roasted+0.323
 rely+0.322
load+0.319
 bank+0.317
Neg logit contributions
ily-0.260
lessness-0.248
iness-0.246
ed-0.235
anish-0.233
Tokenunk
Token ID2954
Feature activation+7.11e-02

Pos logit contributions
 bank+0.115
 roasted+0.115
bowl+0.114
load+0.113
 sausage+0.112
Neg logit contributions
arl-0.083
lessness-0.079
ily-0.078
anish-0.075
anger-0.075
Token and
Token ID290
Feature activation+1.37e-02

Pos logit contributions
 bank+0.075
 roasted+0.072
 cub+0.072
 rely+0.070
load+0.069
Neg logit contributions
arl-0.137
lessness-0.124
anger-0.124
ily-0.124
anish-0.120
Token Sam
Token ID3409
Feature activation-2.69e-02

Pos logit contributions
 bank+0.023
load+0.023
 afloat+0.023
 roasted+0.023
 rely+0.023
Neg logit contributions
ily-0.015
arl-0.015
lessness-0.015
der-0.014
anish-0.014
Token were
Token ID547
Feature activation+3.30e-03

Pos logit contributions
arl+0.050
ily+0.048
lessness+0.048
anger+0.047
der+0.046
Neg logit contributions
 bank-0.028
 roasted-0.027
load-0.026
 rely-0.026
 afloat-0.026
Token.
Token ID13
Feature activation-1.93e-03

Pos logit contributions
arl+0.044
ily+0.037
anish+0.037
lessness+0.037
anger+0.035
Neg logit contributions
 bank-0.055
 rely-0.052
 cub-0.051
load-0.051
bowl-0.050
Token They
Token ID1119
Feature activation+2.78e-02

Pos logit contributions
arl+0.003
ily+0.003
lessness+0.003
iness+0.002
anger+0.002
Neg logit contributions
 bank-0.003
 roasted-0.003
load-0.003
ior-0.003
 rely-0.003
Token all
Token ID477
Feature activation+2.49e-02

Pos logit contributions
ior+0.039
 afloat+0.039
 rely+0.038
load+0.037
 pasture+0.037
Neg logit contributions
ily-0.041
ed-0.039
lessness-0.038
der-0.036
iness-0.035
Token agreed
Token ID4987
Feature activation+3.91e-03

Pos logit contributions
 afloat+0.031
load+0.030
 bank+0.030
 pasture+0.030
 rely+0.030
Neg logit contributions
ily-0.041
lessness-0.041
ed-0.039
iness-0.038
less-0.036
Token to
Token ID284
Feature activation-1.10e-02

Pos logit contributions
 bank+0.006
 asked+0.006
 sausage+0.006
 roasted+0.006
 discuss+0.006
Neg logit contributions
arl-0.006
aces-0.005
anish-0.005
anger-0.005
ily-0.005
Token chip
Token ID11594
Feature activation+2.01e-01

Pos logit contributions
arl+0.020
ily+0.019
lessness+0.019
anish+0.018
der+0.018
Neg logit contributions
 afloat-0.011
 bank-0.011
 roasted-0.011
bowl-0.011
ior-0.011
Token in
Token ID287
Feature activation+5.09e-02

Pos logit contributions
 roasted+0.195
 afloat+0.191
load+0.187
 bank+0.185
 rely+0.184
Neg logit contributions
ily-0.376
lessness-0.367
iness-0.362
arl-0.359
anish-0.356
Token some
Token ID617
Feature activation-1.19e-02

Pos logit contributions
 bank+0.070
 rely+0.069
 discuss+0.068
 feed+0.066
 cub+0.066
Neg logit contributions
arl-0.079
anger-0.077
der-0.075
aces-0.074
ily-0.073
Token money
Token ID1637
Feature activation+1.46e-02

Pos logit contributions
arl+0.017
ily+0.017
lessness+0.016
der+0.016
anger+0.016
Neg logit contributions
 bank-0.017
 roasted-0.017
load-0.017
 afloat-0.016
 rely-0.016
Token so
Token ID523
Feature activation+1.12e-01

Pos logit contributions
 bank+0.023
 afloat+0.021
 rely+0.021
 forth+0.021
 roasted+0.020
Neg logit contributions
arl-0.021
ily-0.019
anish-0.019
anger-0.018
lessness-0.018
Token that
Token ID326
Feature activation+3.57e-02

Pos logit contributions
 roasted+0.136
 bank+0.136
 rely+0.131
 forth+0.129
 Junior+0.129
Neg logit contributions
arl-0.185
anish-0.174
anger-0.171
aces-0.171
ily-0.169
Token at
Token ID379
Feature activation-3.62e-02

Pos logit contributions
 roasted+0.016
 bank+0.016
 afloat+0.015
 rely+0.015
load+0.015
Neg logit contributions
arl-0.012
ily-0.012
lessness-0.012
anger-0.012
anish-0.011
Token these
Token ID777
Feature activation-3.74e-02

Pos logit contributions
arl+0.043
ily+0.042
lessness+0.041
anger+0.039
der+0.039
Neg logit contributions
 bank-0.061
 roasted-0.060
load-0.059
 afloat-0.059
 rely-0.059
Token places
Token ID4113
Feature activation-6.92e-02

Pos logit contributions
arl+0.058
ily+0.056
lessness+0.055
anish+0.053
iness+0.052
Neg logit contributions
 bank-0.052
 rely-0.049
load-0.048
 roasted-0.048
 pasture-0.048
Token that
Token ID326
Feature activation+5.65e-02

Pos logit contributions
arl+0.102
ily+0.093
anish+0.092
anger+0.089
der+0.088
Neg logit contributions
 bank-0.105
 afloat-0.101
 rely-0.100
 forth-0.100
 roasted-0.099
Token the
Token ID262
Feature activation+3.58e-02

Pos logit contributions
load+0.075
ior+0.075
 bank+0.075
 pasture+0.074
 afloat+0.073
Neg logit contributions
ily-0.083
lessness-0.082
iness-0.079
arl-0.078
ed-0.076
Token chip
Token ID11594
Feature activation+2.01e-01

Pos logit contributions
bowl+0.052
ior+0.051
 afloat+0.051
load+0.051
 rely+0.051
Neg logit contributions
 words-0.047
less-0.046
ily-0.045
der-0.045
joy-0.043
Tokenm
Token ID76
Feature activation+8.06e-02

Pos logit contributions
 afloat+0.341
 roasted+0.332
 rely+0.332
ior+0.327
 pasture+0.325
Neg logit contributions
ily-0.233
lessness-0.232
iness-0.231
ed-0.230
anish-0.216
Tokenunk
Token ID2954
Feature activation+7.26e-02

Pos logit contributions
 bank+0.135
 roasted+0.134
load+0.132
bowl+0.130
ior+0.130
Neg logit contributions
arl-0.093
ily-0.090
lessness-0.089
anish-0.084
anger-0.084
Token revealed
Token ID4602
Feature activation+3.28e-02

Pos logit contributions
 bank+0.075
 roasted+0.073
 rely+0.071
bowl+0.071
load+0.070
Neg logit contributions
arl-0.136
ily-0.129
anger-0.126
lessness-0.126
anish-0.125
Token something
Token ID1223
Feature activation-3.87e-02

Pos logit contributions
 bank+0.052
 cub+0.050
 roasted+0.049
 rely+0.048
load+0.048
Neg logit contributions
arl-0.046
anger-0.041
ily-0.040
lessness-0.040
anish-0.039
Token truly
Token ID4988
Feature activation+6.11e-02

Pos logit contributions
arl+0.051
ily+0.050
lessness+0.049
anish+0.047
anger+0.047
Neg logit contributions
 bank-0.059
 roasted-0.058
load-0.057
 rely-0.057
 afloat-0.057
Token said
Token ID531
Feature activation+4.34e-02

Pos logit contributions
ily+0.003
arl+0.003
lessness+0.003
ed+0.003
iness+0.003
Neg logit contributions
 bank-0.001
load-0.001
 rely-0.001
 pasture-0.001
ior-0.001
Token Sammy
Token ID44067
Feature activation-9.96e-03

Pos logit contributions
 bank+0.054
load+0.052
 rely+0.051
 roasted+0.051
ior+0.051
Neg logit contributions
ily-0.070
arl-0.069
lessness-0.068
anger-0.065
iness-0.065
Token.
Token ID13
Feature activation-9.55e-03

Pos logit contributions
ily+0.009
lessness+0.008
arl+0.008
der+0.008
aces+0.008
Neg logit contributions
 roasted-0.019
 bank-0.019
load-0.019
ior-0.019
 afloat-0.019
Token "
Token ID366
Feature activation+5.28e-03

Pos logit contributions
arl+0.009
ily+0.009
lessness+0.008
der+0.008
anger+0.008
Neg logit contributions
 bank-0.018
 rely-0.018
 afloat-0.018
load-0.018
ior-0.018
TokenThis
Token ID1212
Feature activation+3.46e-02

Pos logit contributions
 roasted+0.007
load+0.007
 bank+0.007
bowl+0.007
 discuss+0.007
Neg logit contributions
arl-0.008
ily-0.008
anger-0.008
lessness-0.008
iness-0.007
Token sausage
Token ID31889
Feature activation+2.00e-01

Pos logit contributions
 afloat+0.039
 roasted+0.039
 forth+0.039
ior+0.037
load+0.037
Neg logit contributions
 words-0.056
der-0.056
anish-0.055
ed-0.055
ily-0.055
Token is
Token ID318
Feature activation+1.79e-02

Pos logit contributions
 afloat+0.317
 pasture+0.314
 roasted+0.312
ior+0.311
load+0.310
Neg logit contributions
ily-0.247
lessness-0.235
ed-0.232
arl-0.229
aces-0.229
Token so
Token ID523
Feature activation+1.30e-01

Pos logit contributions
mun+0.033
 pasture+0.033
ior+0.032
oc+0.032
load+0.032
Neg logit contributions
ily-0.018
 words-0.017
less-0.016
arl-0.015
 to-0.015
Token big
Token ID1263
Feature activation+5.81e-02

Pos logit contributions
 pasture+0.222
 afloat+0.215
 bank+0.214
 forth+0.213
 rely+0.209
Neg logit contributions
arl-0.170
ily-0.161
lessness-0.153
less-0.152
t-0.140
Token!"
Token ID2474
Feature activation-2.85e-03

Pos logit contributions
 bank+0.081
 sausage+0.079
 roasted+0.079
ior+0.079
 afloat+0.077
Neg logit contributions
arl-0.086
lessness-0.080
ily-0.080
anish-0.078
anger-0.078
Token
Token ID198
Feature activation-1.20e-02

Pos logit contributions
ily+0.005
lessness+0.005
arl+0.005
ed+0.005
der+0.005
Neg logit contributions
 bank-0.003
 rely-0.003
load-0.003
 afloat-0.003
ior-0.003
Token,
Token ID11
Feature activation-1.82e-02

Pos logit contributions
 roasted+0.198
 afloat+0.196
 bank+0.194
 rely+0.194
load+0.193
Neg logit contributions
ily-0.099
arl-0.098
der-0.093
lessness-0.092
anger-0.091
Token and
Token ID290
Feature activation+8.12e-03

Pos logit contributions
arl+0.027
lessness+0.026
ily+0.026
anger+0.026
iness+0.025
Neg logit contributions
 bank-0.025
 roasted-0.025
load-0.024
ior-0.024
 sausage-0.024
Token even
Token ID772
Feature activation+3.39e-02

Pos logit contributions
 afloat+0.012
 rely+0.011
 bank+0.011
load+0.011
bowl+0.011
Neg logit contributions
ily-0.011
der-0.011
ed-0.010
arl-0.010
aces-0.010
Token mint
Token ID21043
Feature activation+1.06e-01

Pos logit contributions
 afloat+0.051
 bank+0.049
 pasture+0.048
bowl+0.047
ior+0.047
Neg logit contributions
ily-0.048
ed-0.045
der-0.043
aces-0.043
arl-0.042
Token chocolate
Token ID11311
Feature activation+6.86e-02

Pos logit contributions
 bank+0.144
 roasted+0.143
load+0.141
 afloat+0.141
 rely+0.140
Neg logit contributions
arl-0.154
ily-0.152
lessness-0.149
der-0.144
anger-0.143
Token chip
Token ID11594
Feature activation+1.99e-01

Pos logit contributions
 bank+0.116
 roasted+0.115
load+0.114
 afloat+0.114
 rely+0.113
Neg logit contributions
arl-0.077
ily-0.076
lessness-0.074
der-0.071
anger-0.070
Token.
Token ID13
Feature activation+5.88e-03

Pos logit contributions
 afloat+0.281
 roasted+0.275
load+0.273
 discuss+0.272
 rely+0.267
Neg logit contributions
ily-0.290
lessness-0.280
iness-0.277
ed-0.275
aces-0.274
Token But
Token ID887
Feature activation-8.85e-03

Pos logit contributions
 afloat+0.009
 roasted+0.009
 bank+0.009
 rely+0.008
load+0.008
Neg logit contributions
ily-0.008
arl-0.008
lessness-0.008
der-0.008
anger-0.008
Token her
Token ID607
Feature activation-2.48e-02

Pos logit contributions
arl+0.013
ily+0.012
lessness+0.012
anger+0.012
der+0.012
Neg logit contributions
 bank-0.013
 roasted-0.012
load-0.012
 rely-0.012
 afloat-0.012
Token favorite
Token ID4004
Feature activation-1.37e-02

Pos logit contributions
ily+0.031
der+0.031
 words+0.030
less+0.030
joy+0.030
Neg logit contributions
 afloat-0.038
load-0.038
bowl-0.037
 roasted-0.037
ior-0.036
Token was
Token ID373
Feature activation+1.35e-02

Pos logit contributions
ily+0.021
less+0.020
 words+0.020
anish+0.020
der+0.020
Neg logit contributions
 afloat-0.019
 roasted-0.017
load-0.017
ior-0.017
bowl-0.016
Token after
Token ID706
Feature activation-6.97e-02

Pos logit contributions
arl+0.016
anger+0.014
anish+0.013
ily+0.013
aces+0.012
Neg logit contributions
 cub-0.016
 bank-0.016
 rely-0.016
bowl-0.015
 afloat-0.015
Token that
Token ID326
Feature activation+3.71e-02

Pos logit contributions
arl+0.106
anger+0.097
ily+0.097
lessness+0.097
anish+0.096
Neg logit contributions
 roasted-0.098
 bank-0.097
 rely-0.094
 afloat-0.094
 cub-0.093
Token.
Token ID13
Feature activation-2.05e-03

Pos logit contributions
load+0.066
 roasted+0.064
ior+0.063
 bank+0.063
 discuss+0.062
Neg logit contributions
lessness-0.040
ily-0.039
iness-0.038
arl-0.037
der-0.037
Token Whenever
Token ID21326
Feature activation+1.39e-02

Pos logit contributions
arl+0.003
ily+0.003
lessness+0.003
anger+0.003
der+0.003
Neg logit contributions
 bank-0.003
 roasted-0.003
load-0.003
 rely-0.003
ior-0.002
Token the
Token ID262
Feature activation+3.13e-02

Pos logit contributions
 bank+0.021
 roasted+0.021
 rely+0.020
 discuss+0.020
 afloat+0.020
Neg logit contributions
arl-0.019
ily-0.018
lessness-0.018
anger-0.017
der-0.017
Token chip
Token ID11594
Feature activation+1.99e-01

Pos logit contributions
 afloat+0.041
ior+0.040
load+0.040
 roasted+0.039
bowl+0.038
Neg logit contributions
ily-0.048
 words-0.046
arl-0.045
der-0.045
less-0.045
Tokenm
Token ID76
Feature activation+7.40e-02

Pos logit contributions
 afloat+0.328
 roasted+0.314
 rely+0.313
load+0.311
itionally+0.307
Neg logit contributions
ily-0.254
iness-0.245
lessness-0.240
ed-0.238
anish-0.232
Tokenunk
Token ID2954
Feature activation+7.31e-02

Pos logit contributions
 bank+0.129
 roasted+0.128
load+0.126
bowl+0.125
 afloat+0.125
Neg logit contributions
arl-0.080
ily-0.078
lessness-0.077
anger-0.072
der-0.072
Token needed
Token ID2622
Feature activation+5.54e-02

Pos logit contributions
 bank+0.078
load+0.077
 roasted+0.077
 afloat+0.076
ior+0.075
Neg logit contributions
ily-0.126
arl-0.125
lessness-0.125
der-0.120
iness-0.120
Token help
Token ID1037
Feature activation-1.32e-02

Pos logit contributions
 bank+0.090
 rely+0.089
 roasted+0.088
 cub+0.088
 sausage+0.087
Neg logit contributions
arl-0.076
lessness-0.068
der-0.066
anger-0.066
iness-0.065
Token,
Token ID11
Feature activation-1.11e-02

Pos logit contributions
arl+0.017
ily+0.016
lessness+0.015
anger+0.015
der+0.015
Neg logit contributions
 bank-0.022
 rely-0.021
 afloat-0.021
 roasted-0.021
bowl-0.021
Token place
Token ID1295
Feature activation-2.91e-02

Pos logit contributions
 afloat+0.047
 roasted+0.046
 bank+0.045
 discuss+0.044
 cub+0.043
Neg logit contributions
arl-0.062
aces-0.061
anger-0.060
ily-0.059
iness-0.056
Token!
Token ID0
Feature activation-1.95e-03

Pos logit contributions
arl+0.054
ily+0.048
aces+0.047
anish+0.046
anger+0.045
Neg logit contributions
 bank-0.037
 roasted-0.036
 afloat-0.035
 barbecue-0.033
 called-0.033
Token
Token ID198
Feature activation+1.27e-02

Pos logit contributions
ily+0.003
arl+0.003
lessness+0.003
der+0.002
anger+0.002
Neg logit contributions
 forth-0.003
 bank-0.003
 rely-0.003
 afloat-0.003
 roasted-0.003
Token
Token ID198
Feature activation+1.12e-02

Pos logit contributions
 forth+0.023
 bank+0.022
ior+0.022
 afloat+0.021
 rely+0.021
Neg logit contributions
ily-0.016
arl-0.014
lessness-0.014
t-0.013
J-0.013
TokenThe
Token ID464
Feature activation+2.53e-03

Pos logit contributions
 bank+0.018
ior+0.017
 rely+0.017
 roasted+0.017
 afloat+0.017
Neg logit contributions
ily-0.015
arl-0.014
lessness-0.014
anish-0.013
der-0.013
Token chip
Token ID11594
Feature activation+1.97e-01

Pos logit contributions
ior+0.004
bowl+0.004
 afloat+0.004
load+0.004
 roasted+0.004
Neg logit contributions
ily-0.003
arl-0.003
less-0.003
lessness-0.003
 words-0.003
Tokenmun
Token ID6199
Feature activation+7.92e-02

Pos logit contributions
 afloat+0.337
 rely+0.320
load+0.316
 roasted+0.314
itionally+0.312
Neg logit contributions
ily-0.250
lessness-0.236
iness-0.232
ed-0.226
anish-0.217
Tokenks
Token ID591
Feature activation-4.33e-02

Pos logit contributions
 bank+0.154
 roasted+0.154
bowl+0.152
load+0.151
 rely+0.150
Neg logit contributions
arl-0.072
anger-0.063
lessness-0.063
ily-0.062
less-0.061
Token didn
Token ID1422
Feature activation-9.46e-02

Pos logit contributions
arl+0.079
anger+0.069
anish+0.068
lessness+0.067
joy+0.066
Neg logit contributions
 roasted-0.053
 bank-0.050
 cub-0.050
 asked-0.050
load-0.046
Token't
Token ID470
Feature activation-7.71e-02

Pos logit contributions
lessness+0.108
arl+0.105
joy+0.104
aces+0.102
iness+0.102
Neg logit contributions
 roasted-0.161
 rely-0.161
 bank-0.160
 discuss-0.160
load-0.159
Token know
Token ID760
Feature activation-6.41e-03

Pos logit contributions
arl+0.144
anger+0.143
anish+0.140
overed+0.140
aces+0.137
Neg logit contributions
 discuss-0.081
 rely-0.079
 roasted-0.079
 feed-0.078
 bank-0.075
Token floor
Token ID4314
Feature activation+6.00e-04

Pos logit contributions
ily+0.015
arl+0.014
lessness+0.014
anger+0.014
der+0.014
Neg logit contributions
load-0.015
 rely-0.015
ior-0.014
 roasted-0.014
bowl-0.014
Token.
Token ID13
Feature activation+7.76e-03

Pos logit contributions
 bank+0.001
 asked+0.001
bowl+0.001
 called+0.001
load+0.001
Neg logit contributions
arl-0.001
anish-0.001
anger-0.001
ily-0.001
lessness-0.001
Token
Token ID198
Feature activation+1.69e-02

Pos logit contributions
 forth+0.013
 rely+0.013
 afloat+0.013
 bank+0.012
load+0.012
Neg logit contributions
ily-0.010
arl-0.009
lessness-0.009
anger-0.009
der-0.009
Token
Token ID198
Feature activation+1.60e-02

Pos logit contributions
 forth+0.028
 bank+0.028
 afloat+0.027
ior+0.027
 rely+0.026
Neg logit contributions
ily-0.023
arl-0.020
lessness-0.020
anger-0.019
t-0.019
TokenThe
Token ID464
Feature activation+3.52e-03

Pos logit contributions
 bank+0.025
 roasted+0.025
 afloat+0.025
 rely+0.025
ior+0.024
Neg logit contributions
ily-0.020
arl-0.020
lessness-0.020
anish-0.018
der-0.018
Token chip
Token ID11594
Feature activation+1.97e-01

Pos logit contributions
 bank+0.005
 roasted+0.005
load+0.005
 afloat+0.005
 rely+0.005
Neg logit contributions
arl-0.005
ily-0.005
lessness-0.005
der-0.005
anger-0.005
Tokenmun
Token ID6199
Feature activation+8.11e-02

Pos logit contributions
 afloat+0.330
 rely+0.310
load+0.308
itionally+0.304
 roasted+0.303
Neg logit contributions
ily-0.259
lessness-0.245
iness-0.245
ed-0.239
anish-0.227
Tokenks
Token ID591
Feature activation-4.31e-02

Pos logit contributions
 bank+0.164
 roasted+0.163
load+0.161
bowl+0.161
 rely+0.160
Neg logit contributions
arl-0.067
lessness-0.061
ily-0.061
anger-0.058
der-0.057
Token were
Token ID547
Feature activation-2.52e-03

Pos logit contributions
arl+0.070
anger+0.060
anish+0.060
lessness+0.060
aces+0.058
Neg logit contributions
 roasted-0.059
 asked-0.059
 bank-0.058
 cub-0.058
 sausage-0.055
Token very
Token ID845
Feature activation+6.88e-02

Pos logit contributions
ily+0.003
lessness+0.003
arl+0.003
less+0.003
der+0.003
Neg logit contributions
 bank-0.004
ior-0.004
load-0.004
bowl-0.004
oc-0.004
Token curious
Token ID11040
Feature activation-8.92e-04

Pos logit contributions
 bank+0.097
ior+0.097
bowl+0.096
 roasted+0.095
 pasture+0.095
Neg logit contributions
ily-0.099
arl-0.098
lessness-0.096
less-0.093
der-0.091
Token bird
Token ID6512
Feature activation+1.62e-02

Pos logit contributions
 bank+0.039
 roasted+0.038
load+0.038
 afloat+0.037
 rely+0.037
Neg logit contributions
arl-0.041
ily-0.040
lessness-0.040
der-0.038
anger-0.038
Token.
Token ID13
Feature activation-3.60e-03

Pos logit contributions
load+0.032
 roasted+0.032
ior+0.032
 afloat+0.032
 bank+0.032
Neg logit contributions
ily-0.013
lessness-0.012
arl-0.012
der-0.012
iness-0.012
Token Luckily
Token ID24262
Feature activation+5.77e-02

Pos logit contributions
arl+0.005
ily+0.005
lessness+0.005
der+0.005
anger+0.005
Neg logit contributions
 bank-0.005
 roasted-0.005
load-0.005
 rely-0.005
ior-0.005
Token,
Token ID11
Feature activation-9.23e-03

Pos logit contributions
 bank+0.089
 roasted+0.087
 cub+0.087
 afloat+0.085
 Junior+0.085
Neg logit contributions
arl-0.083
lessness-0.073
ily-0.071
der-0.071
anish-0.068
Token the
Token ID262
Feature activation+1.73e-02

Pos logit contributions
arl+0.014
ily+0.013
lessness+0.012
anger+0.012
aces+0.012
Neg logit contributions
 roasted-0.014
 bank-0.014
 discuss-0.013
 cub-0.013
 rely-0.013
Token chip
Token ID11594
Feature activation+1.97e-01

Pos logit contributions
 roasted+0.023
 bank+0.023
load+0.023
 afloat+0.023
ior+0.023
Neg logit contributions
ily-0.025
arl-0.025
lessness-0.025
der-0.024
anish-0.024
Tokenm
Token ID76
Feature activation+7.52e-02

Pos logit contributions
 afloat+0.298
load+0.285
 roasted+0.284
 rely+0.276
ior+0.274
Neg logit contributions
ily-0.285
iness-0.273
lessness-0.267
anish-0.260
ed-0.258
Tokenunk
Token ID2954
Feature activation+7.46e-02

Pos logit contributions
 cub+0.107
 bank+0.106
bowl+0.103
 rely+0.103
 roasted+0.103
Neg logit contributions
arl-0.106
lessness-0.100
ily-0.098
anish-0.097
joy-0.093
Token said
Token ID531
Feature activation+7.16e-02

Pos logit contributions
 bank+0.072
 roasted+0.069
 rely+0.067
 cub+0.067
 discuss+0.067
Neg logit contributions
arl-0.146
ily-0.138
lessness-0.138
anger-0.135
anish-0.132
Token they
Token ID484
Feature activation+2.22e-02

Pos logit contributions
 cub+0.094
 sausage+0.088
 asked+0.088
 Junior+0.086
 Nem+0.084
Neg logit contributions
arl-0.128
anger-0.113
ips-0.106
lessness-0.104
itted-0.103
Token should
Token ID815
Feature activation+9.10e-02

Pos logit contributions
 bank+0.022
 roasted+0.021
 rely+0.021
 discuss+0.021
load+0.020
Neg logit contributions
arl-0.042
ily-0.040
lessness-0.040
anger-0.039
anish-0.039
Token her
Token ID607
Feature activation-5.14e-02

Pos logit contributions
 bank+0.017
load+0.017
ior+0.017
 afloat+0.017
bowl+0.017
Neg logit contributions
ily-0.014
arl-0.013
lessness-0.013
der-0.012
less-0.012
Token favorite
Token ID4004
Feature activation-2.00e-02

Pos logit contributions
arl+0.074
ily+0.073
lessness+0.072
der+0.070
anger+0.069
Neg logit contributions
 bank-0.070
 roasted-0.070
load-0.070
 afloat-0.069
ior-0.068
Token--
Token ID438
Feature activation+6.90e-03

Pos logit contributions
ily+0.029
less+0.028
anish+0.028
 words+0.028
der+0.028
Neg logit contributions
 afloat-0.028
 roasted-0.027
load-0.026
ior-0.026
 rely-0.025
Tokench
Token ID354
Feature activation+6.40e-02

Pos logit contributions
load+0.010
 sausage+0.010
 rely+0.010
 weighed+0.010
 bank+0.009
Neg logit contributions
arl-0.010
lessness-0.010
der-0.010
anish-0.009
iness-0.009
Tokenocolate
Token ID9140
Feature activation+1.42e-02

Pos logit contributions
 sausage+0.086
bowl+0.085
 bank+0.085
 roasted+0.084
load+0.081
Neg logit contributions
der-0.094
arl-0.092
joy-0.089
lessness-0.086
ative-0.085
Token chip
Token ID11594
Feature activation+1.97e-01

Pos logit contributions
 afloat+0.026
 roasted+0.026
ior+0.025
 discuss+0.025
load+0.025
Neg logit contributions
ily-0.014
der-0.014
less-0.013
anger-0.013
arl-0.013
Token!
Token ID0
Feature activation-3.91e-03

Pos logit contributions
 roasted+0.308
 afloat+0.307
load+0.306
 bank+0.299
 rely+0.299
Neg logit contributions
ily-0.255
lessness-0.245
iness-0.242
aces-0.232
arl-0.230
Token She
Token ID1375
Feature activation+2.55e-03

Pos logit contributions
arl+0.005
ily+0.005
lessness+0.005
der+0.005
anger+0.005
Neg logit contributions
 bank-0.006
 roasted-0.006
load-0.006
 afloat-0.006
 rely-0.006
Token was
Token ID373
Feature activation+1.43e-02

Pos logit contributions
 afloat+0.004
itionally+0.004
ior+0.003
 rely+0.003
 forth+0.003
Neg logit contributions
ily-0.004
ed-0.004
der-0.004
aces-0.003
te-0.003
Token very
Token ID845
Feature activation+7.88e-02

Pos logit contributions
ior+0.025
 bank+0.025
 afloat+0.025
oc+0.024
load+0.024
Neg logit contributions
ily-0.016
lessness-0.014
less-0.014
aces-0.014
ed-0.014
Token happy
Token ID3772
Feature activation-2.73e-02

Pos logit contributions
 bank+0.134
ior+0.134
 afloat+0.131
 pasture+0.130
bowl+0.129
Neg logit contributions
ily-0.100
arl-0.094
less-0.093
lessness-0.090
ed-0.083
Token frog
Token ID21264
Feature activation+5.11e-02

Pos logit contributions
 afloat+0.027
ior+0.027
load+0.027
bowl+0.026
 roasted+0.026
Neg logit contributions
ily-0.023
 words-0.023
der-0.020
anish-0.019
arl-0.019
Token agreed
Token ID4987
Feature activation-7.82e-03

Pos logit contributions
 afloat+0.057
load+0.057
 roasted+0.056
ior+0.056
 bank+0.056
Neg logit contributions
ily-0.086
lessness-0.082
der-0.082
arl-0.081
ed-0.081
Token,
Token ID11
Feature activation-3.81e-02

Pos logit contributions
arl+0.014
aces+0.013
anish+0.013
anger+0.013
adies+0.012
Neg logit contributions
 bank-0.010
 asked-0.010
 cub-0.009
 sausage-0.009
 nib-0.009
Token and
Token ID290
Feature activation-1.35e-04

Pos logit contributions
arl+0.048
ily+0.046
anger+0.045
anish+0.044
lessness+0.044
Neg logit contributions
 bank-0.062
 roasted-0.062
 cub-0.060
load-0.059
ior-0.059
Token the
Token ID262
Feature activation+2.48e-02

Pos logit contributions
ily+0.000
lessness+0.000
arl+0.000
der+0.000
ed+0.000
Neg logit contributions
 bank-0.000
 afloat-0.000
load-0.000
 rely-0.000
ior-0.000
Token chip
Token ID11594
Feature activation+1.96e-01

Pos logit contributions
ior+0.042
load+0.041
 afloat+0.041
 roasted+0.041
 Junior+0.040
Neg logit contributions
ily-0.029
 words-0.029
arl-0.027
anish-0.026
der-0.026
Tokenm
Token ID76
Feature activation+7.36e-02

Pos logit contributions
 afloat+0.321
 roasted+0.307
load+0.304
 rely+0.304
 pasture+0.298
Neg logit contributions
ily-0.256
iness-0.247
lessness-0.246
ed-0.239
anish-0.230
Tokenunk
Token ID2954
Feature activation+7.42e-02

Pos logit contributions
 bank+0.114
 cub+0.112
 roasted+0.111
bowl+0.111
 rely+0.111
Neg logit contributions
arl-0.095
lessness-0.089
ily-0.088
anish-0.086
less-0.083
Token agreed
Token ID4987
Feature activation-2.69e-03

Pos logit contributions
 bank+0.073
 roasted+0.069
 rely+0.068
 cub+0.067
load+0.066
Neg logit contributions
arl-0.147
ily-0.137
lessness-0.136
anger-0.135
anish-0.132
Token too
Token ID1165
Feature activation+3.05e-02

Pos logit contributions
arl+0.005
anger+0.004
anish+0.004
aces+0.004
adies+0.004
Neg logit contributions
 bank-0.004
 asked-0.003
 rely-0.003
 cub-0.003
 nib-0.003
Token.
Token ID13
Feature activation-2.23e-03

Pos logit contributions
 bank+0.038
 cub+0.038
 afloat+0.036
 rely+0.035
 Junior+0.034
Neg logit contributions
arl-0.054
anish-0.050
anger-0.050
iness-0.047
ily-0.047
Token.
Token ID13
Feature activation+4.84e-03

Pos logit contributions
 bank+0.179
 roasted+0.172
 cub+0.171
 rely+0.169
ior+0.168
Neg logit contributions
arl-0.166
anger-0.154
ily-0.151
lessness-0.150
anish-0.150
Token
Token ID220
Feature activation+1.16e-02

Pos logit contributions
 forth+0.007
 rely+0.007
 afloat+0.007
 roasted+0.007
 discuss+0.006
Neg logit contributions
arl-0.007
ily-0.007
der-0.007
lessness-0.007
joy-0.006
Token
Token ID198
Feature activation+1.13e-02

Pos logit contributions
 forth+0.018
 roasted+0.018
 bank+0.018
 afloat+0.017
 discuss+0.017
Neg logit contributions
ily-0.016
arl-0.016
lessness-0.014
der-0.014
anger-0.014
Token
Token ID198
Feature activation+7.73e-03

Pos logit contributions
 forth+0.020
 roasted+0.018
 bank+0.018
 afloat+0.018
ior+0.018
Neg logit contributions
ily-0.014
arl-0.014
t-0.012
lessness-0.012
anish-0.012
TokenThe
Token ID464
Feature activation-2.01e-03

Pos logit contributions
 forth+0.014
 roasted+0.014
 afloat+0.013
ior+0.013
 bank+0.013
Neg logit contributions
ily-0.008
arl-0.008
lessness-0.008
anish-0.007
less-0.007
Token chip
Token ID11594
Feature activation+1.96e-01

Pos logit contributions
 words+0.003
ily+0.003
less+0.003
der+0.003
arl+0.003
Neg logit contributions
 afloat-0.003
bowl-0.003
 roasted-0.003
 Junior-0.003
ior-0.003
Tokenm
Token ID76
Feature activation+7.10e-02

Pos logit contributions
 afloat+0.359
 rely+0.340
 roasted+0.340
 pasture+0.328
load+0.326
Neg logit contributions
ily-0.224
lessness-0.215
iness-0.214
ed-0.208
anish-0.206
Tokenunk
Token ID2954
Feature activation+6.29e-02

Pos logit contributions
 bank+0.120
 roasted+0.118
load+0.117
bowl+0.116
ior+0.115
Neg logit contributions
arl-0.080
ily-0.077
lessness-0.077
anger-0.072
anish-0.071
Token told
Token ID1297
Feature activation+3.10e-02

Pos logit contributions
 bank+0.063
 roasted+0.062
load+0.060
 rely+0.060
 discuss+0.059
Neg logit contributions
arl-0.117
ily-0.113
lessness-0.112
anger-0.109
der-0.108
Token the
Token ID262
Feature activation+4.03e-02

Pos logit contributions
 bank+0.046
 Junior+0.044
 sausage+0.044
ior+0.044
 roasted+0.044
Neg logit contributions
arl-0.044
lessness-0.043
ily-0.042
aces-0.042
anger-0.041
Token boy
Token ID2933
Feature activation+8.27e-02

Pos logit contributions
 afloat+0.046
 forth+0.044
 roasted+0.044
load+0.043
ior+0.043
Neg logit contributions
 words-0.070
ily-0.069
der-0.067
less-0.067
arl-0.066
Token they
Token ID484
Feature activation+1.12e-02

Pos logit contributions
arl+0.029
aces+0.029
lessness+0.028
iness+0.028
der+0.028
Neg logit contributions
 roasted-0.025
 discuss-0.025
 feed-0.024
 asked-0.024
 bank-0.024
Token decided
Token ID3066
Feature activation+4.55e-03

Pos logit contributions
 afloat+0.015
 rely+0.015
ior+0.014
 pasture+0.014
load+0.013
Neg logit contributions
ily-0.019
ed-0.017
lessness-0.017
anish-0.016
less-0.016
Token to
Token ID284
Feature activation-1.23e-02

Pos logit contributions
 bank+0.008
 discuss+0.008
 asked+0.008
 barbecue+0.008
 roasted+0.008
Neg logit contributions
arl-0.006
lessness-0.006
iness-0.005
aces-0.005
ily-0.005
Token make
Token ID787
Feature activation+1.19e-02

Pos logit contributions
ily+0.020
anish+0.019
arl+0.019
 words+0.018
anger+0.017
Neg logit contributions
 afloat-0.017
ior-0.016
 cub-0.014
 forth-0.014
bowl-0.014
Token chocolate
Token ID11311
Feature activation+6.79e-02

Pos logit contributions
 afloat+0.025
ior+0.025
 rely+0.025
 bank+0.025
 forth+0.024
Neg logit contributions
ily-0.009
 words-0.008
der-0.007
arl-0.007
anger-0.007
Token chip
Token ID11594
Feature activation+1.95e-01

Pos logit contributions
 afloat+0.108
ior+0.103
 rely+0.102
bowl+0.102
 roasted+0.101
Neg logit contributions
ily-0.085
anger-0.082
der-0.081
arl-0.080
ed-0.080
Token cookies
Token ID14746
Feature activation+3.06e-02

Pos logit contributions
 afloat+0.339
 roasted+0.321
 rely+0.318
 bank+0.315
field+0.314
Neg logit contributions
ily-0.240
lessness-0.220
ed-0.219
iness-0.217
aces-0.216
Token.
Token ID13
Feature activation+5.29e-03

Pos logit contributions
 bank+0.056
 roasted+0.056
ior+0.056
 afloat+0.055
load+0.055
Neg logit contributions
ily-0.030
arl-0.030
lessness-0.028
der-0.027
anger-0.027
Token Lily
Token ID20037
Feature activation-2.16e-02

Pos logit contributions
 rely+0.011
 afloat+0.011
 forth+0.011
 cub+0.010
cker+0.010
Neg logit contributions
ily-0.005
arl-0.005
anger-0.004
ed-0.004
 She-0.004
Token's
Token ID338
Feature activation+6.05e-02

Pos logit contributions
ily+0.032
ed+0.031
t+0.027
aces+0.026
anish+0.026
Neg logit contributions
 afloat-0.037
 rely-0.031
 paddle-0.030
 sle-0.029
ior-0.029
Token mom
Token ID1995
Feature activation-9.27e-03

Pos logit contributions
 bank+0.089
 afloat+0.089
 roasted+0.088
load+0.088
 rely+0.087
Neg logit contributions
ily-0.082
arl-0.082
lessness-0.079
der-0.076
anger-0.076
Token cookies
Token ID14746
Feature activation+2.91e-02

Pos logit contributions
arl+0.012
ily+0.012
lessness+0.011
anger+0.011
der+0.011
Neg logit contributions
 bank-0.012
 roasted-0.012
load-0.012
 rely-0.012
 afloat-0.012
Token.
Token ID13
Feature activation+2.13e-02

Pos logit contributions
 bank+0.048
 roasted+0.047
load+0.047
 rely+0.047
 afloat+0.047
Neg logit contributions
arl-0.034
ily-0.033
lessness-0.033
anger-0.031
der-0.031
Token They
Token ID1119
Feature activation+4.30e-02

Pos logit contributions
 bank+0.032
 roasted+0.032
 afloat+0.032
load+0.032
 rely+0.031
Neg logit contributions
arl-0.028
ily-0.028
lessness-0.027
der-0.026
anish-0.025
Token are
Token ID389
Feature activation+5.01e-04

Pos logit contributions
 afloat+0.073
ior+0.072
load+0.071
 bank+0.071
 pasture+0.071
Neg logit contributions
ily-0.048
arl-0.047
lessness-0.046
aces-0.043
der-0.043
Token chocolate
Token ID11311
Feature activation+7.34e-02

Pos logit contributions
 bank+0.001
 afloat+0.001
bowl+0.001
oc+0.001
load+0.001
Neg logit contributions
ily-0.001
arl-0.001
 words-0.000
 herself-0.000
aces-0.000
Token chip
Token ID11594
Feature activation+1.95e-01

Pos logit contributions
 roasted+0.115
 bank+0.114
 afloat+0.114
load+0.114
 rely+0.113
Neg logit contributions
arl-0.091
ily-0.090
lessness-0.087
der-0.086
anger-0.084
Token.
Token ID13
Feature activation+2.23e-02

Pos logit contributions
 roasted+0.286
 bank+0.284
load+0.282
 afloat+0.280
 rely+0.277
Neg logit contributions
ily-0.268
arl-0.263
lessness-0.262
iness-0.252
aces-0.250
Token My
Token ID2011
Feature activation+5.42e-03

Pos logit contributions
 bank+0.035
 afloat+0.035
 forth+0.035
load+0.034
 roasted+0.034
Neg logit contributions
arl-0.029
ily-0.029
lessness-0.027
der-0.026
anish-0.026
Token favorite
Token ID4004
Feature activation+6.84e-03

Pos logit contributions
 afloat+0.007
 bank+0.007
 roasted+0.007
load+0.007
bowl+0.007
Neg logit contributions
arl-0.008
ily-0.008
lessness-0.008
der-0.007
anger-0.007
Token.
Token ID13
Feature activation+5.62e-03

Pos logit contributions
 afloat+0.011
 roasted+0.010
load+0.010
ior+0.010
 Junior+0.010
Neg logit contributions
ily-0.009
anish-0.009
arl-0.008
 words-0.008
der-0.008
Token Maybe
Token ID6674
Feature activation-2.75e-02

Pos logit contributions
 forth+0.010
 afloat+0.010
 bank+0.010
load+0.009
 rely+0.009
Neg logit contributions
arl-0.007
ily-0.007
der-0.006
lessness-0.006
anish-0.006
Token so
Token ID523
Feature activation+9.58e-02

Pos logit contributions
arl+0.067
anger+0.063
ily+0.062
anish+0.061
lessness+0.061
Neg logit contributions
 bank-0.052
 roasted-0.052
 discuss-0.050
 feed-0.049
 forth-0.049
Token she
Token ID673
Feature activation-3.33e-02

Pos logit contributions
 roasted+0.185
 bank+0.183
 rely+0.182
 forth+0.181
 discuss+0.179
Neg logit contributions
arl-0.089
lessness-0.081
ily-0.079
anger-0.079
anish-0.078
Token gave
Token ID2921
Feature activation+2.95e-02

Pos logit contributions
ily+0.054
ed+0.049
der+0.046
aces+0.046
ps+0.042
Neg logit contributions
 afloat-0.051
 pasture-0.045
ior-0.045
 rely-0.044
load-0.044
Token the
Token ID262
Feature activation+3.74e-02

Pos logit contributions
 bank+0.054
 roasted+0.054
load+0.054
 afloat+0.053
 rely+0.053
Neg logit contributions
ily-0.029
arl-0.029
lessness-0.028
der-0.026
anger-0.026
Token spicy
Token ID26880
Feature activation+7.41e-02

Pos logit contributions
 roasted+0.052
 afloat+0.052
load+0.052
ior+0.052
 bank+0.051
Neg logit contributions
ily-0.053
arl-0.052
lessness-0.050
anish-0.049
 words-0.049
Token chip
Token ID11594
Feature activation+1.95e-01

Pos logit contributions
 bank+0.080
 sausage+0.076
 roasted+0.076
 rely+0.075
load+0.075
Neg logit contributions
arl-0.132
lessness-0.131
ily-0.130
der-0.123
anger-0.123
Token to
Token ID284
Feature activation+3.29e-03

Pos logit contributions
 afloat+0.277
 roasted+0.275
load+0.268
 rely+0.265
 bank+0.264
Neg logit contributions
ily-0.295
iness-0.277
lessness-0.277
ed-0.275
anish-0.267
Token the
Token ID262
Feature activation+3.50e-02

Pos logit contributions
 bank+0.006
 roasted+0.006
load+0.006
 rely+0.006
 afloat+0.006
Neg logit contributions
arl-0.003
ily-0.003
lessness-0.003
anger-0.003
der-0.003
Token raven
Token ID37735
Feature activation+6.35e-02

Pos logit contributions
 afloat+0.055
 roasted+0.055
load+0.055
ior+0.054
bowl+0.053
Neg logit contributions
ily-0.045
arl-0.044
 words-0.043
der-0.041
anish-0.040
Token.
Token ID13
Feature activation-9.58e-03

Pos logit contributions
 bank+0.123
 roasted+0.123
load+0.123
 afloat+0.123
ior+0.122
Neg logit contributions
ily-0.055
arl-0.054
lessness-0.052
der-0.049
aces-0.048
Token The
Token ID383
Feature activation-2.72e-03

Pos logit contributions
arl+0.013
lessness+0.013
iness+0.013
less+0.012
ily+0.012
Neg logit contributions
 bank-0.014
ior-0.014
 roasted-0.014
 discuss-0.014
load-0.013
Token loved
Token ID6151
Feature activation-5.75e-02

Pos logit contributions
 afloat+0.002
load+0.002
 bank+0.001
ior+0.001
 pasture+0.001
Neg logit contributions
ily-0.002
ed-0.001
lessness-0.001
aces-0.001
t-0.001
Token cookies
Token ID14746
Feature activation+9.54e-03

Pos logit contributions
arl+0.033
ily+0.032
lessness+0.030
der+0.027
anger+0.027
Neg logit contributions
 afloat-0.129
 bank-0.129
load-0.128
 roasted-0.127
 rely-0.127
Token,
Token ID11
Feature activation-1.65e-02

Pos logit contributions
 roasted+0.019
load+0.019
 bank+0.019
 afloat+0.019
ior+0.019
Neg logit contributions
ily-0.008
arl-0.007
lessness-0.007
aces-0.007
der-0.006
Token especially
Token ID2592
Feature activation+5.17e-02

Pos logit contributions
ily+0.028
lessness+0.026
aces+0.026
der+0.025
 words+0.025
Neg logit contributions
 afloat-0.020
load-0.020
 rely-0.019
 bank-0.019
ior-0.018
Token chocolate
Token ID11311
Feature activation+6.29e-02

Pos logit contributions
 afloat+0.089
 bank+0.088
 rely+0.086
load+0.084
bowl+0.084
Neg logit contributions
ily-0.063
arl-0.061
less-0.056
lessness-0.055
ed-0.055
Token chip
Token ID11594
Feature activation+1.94e-01

Pos logit contributions
 afloat+0.101
 roasted+0.099
load+0.099
 rely+0.099
 discuss+0.098
Neg logit contributions
arl-0.076
ily-0.076
der-0.074
lessness-0.072
anger-0.071
Token cookies
Token ID14746
Feature activation+2.67e-02

Pos logit contributions
 afloat+0.309
 roasted+0.301
load+0.299
 rely+0.297
 bank+0.291
Neg logit contributions
ily-0.259
lessness-0.244
aces-0.244
iness-0.242
arl-0.232
Token.
Token ID13
Feature activation+6.38e-04

Pos logit contributions
 bank+0.049
 roasted+0.049
load+0.048
 rely+0.048
 afloat+0.048
Neg logit contributions
arl-0.026
ily-0.025
lessness-0.025
der-0.023
anger-0.023
Token One
Token ID1881
Feature activation+2.72e-03

Pos logit contributions
 afloat+0.001
load+0.001
 roasted+0.001
 bank+0.001
 forth+0.001
Neg logit contributions
ily-0.001
arl-0.001
der-0.001
aces-0.001
anger-0.001
Token day
Token ID1110
Feature activation+1.00e-02

Pos logit contributions
 afloat+0.004
 bank+0.004
load+0.004
 rely+0.004
 negotiate+0.004
Neg logit contributions
ily-0.004
lessness-0.004
less-0.004
arl-0.004
iness-0.004
Token,
Token ID11
Feature activation-1.70e-02

Pos logit contributions
 roasted+0.015
 bank+0.014
 discuss+0.014
 sausage+0.014
bowl+0.014
Neg logit contributions
arl-0.014
lessness-0.013
der-0.013
ily-0.013
aces-0.013
Token chip
Token ID11594
Feature activation+1.57e-01

Pos logit contributions
 bank+0.046
 roasted+0.045
load+0.045
 afloat+0.045
 rely+0.044
Neg logit contributions
arl-0.059
ily-0.058
lessness-0.057
der-0.055
anger-0.055
Tokenm
Token ID76
Feature activation+5.26e-02

Pos logit contributions
 roasted+0.268
 afloat+0.265
 rely+0.264
load+0.262
 discuss+0.256
Neg logit contributions
iness-0.183
ily-0.182
lessness-0.180
ed-0.166
less-0.160
Tokenunk
Token ID2954
Feature activation+4.09e-02

Pos logit contributions
 bank+0.081
bowl+0.080
 roasted+0.079
 afloat+0.079
load+0.079
Neg logit contributions
ily-0.065
arl-0.065
anish-0.063
lessness-0.062
anger-0.060
Token.
Token ID13
Feature activation+6.96e-03

Pos logit contributions
 bank+0.070
 roasted+0.069
load+0.068
bowl+0.068
 afloat+0.067
Neg logit contributions
arl-0.047
ily-0.045
lessness-0.044
anish-0.042
anger-0.042
Token The
Token ID383
Feature activation+1.70e-03

Pos logit contributions
 forth+0.013
 rely+0.012
 afloat+0.012
 roasted+0.012
load+0.012
Neg logit contributions
arl-0.007
ily-0.007
der-0.007
lessness-0.007
joy-0.006
Token chip
Token ID11594
Feature activation+1.94e-01

Pos logit contributions
 afloat+0.002
bowl+0.002
 Junior+0.002
 forth+0.002
 roasted+0.002
Neg logit contributions
 words-0.003
less-0.002
arl-0.002
ily-0.002
der-0.002
Tokenm
Token ID76
Feature activation+7.55e-02

Pos logit contributions
 afloat+0.348
 rely+0.339
 roasted+0.336
 pasture+0.326
load+0.325
Neg logit contributions
ily-0.217
iness-0.216
lessness-0.216
ed-0.211
anish-0.200
Tokenunk
Token ID2954
Feature activation+6.53e-02

Pos logit contributions
 bank+0.127
 roasted+0.125
load+0.124
bowl+0.124
ior+0.122
Neg logit contributions
arl-0.085
ily-0.083
lessness-0.082
anish-0.078
der-0.077
Token wanted
Token ID2227
Feature activation-9.00e-03

Pos logit contributions
 afloat+0.070
load+0.069
 roasted+0.069
 bank+0.069
 rely+0.068
Neg logit contributions
ily-0.113
lessness-0.111
arl-0.110
der-0.108
iness-0.106
Token the
Token ID262
Feature activation+1.53e-02

Pos logit contributions
arl+0.006
ily+0.006
lessness+0.006
der+0.005
anger+0.005
Neg logit contributions
 bank-0.019
 roasted-0.019
load-0.019
 afloat-0.019
 rely-0.019
Token boy
Token ID2933
Feature activation+5.65e-02

Pos logit contributions
ior+0.017
 forth+0.017
load+0.017
 afloat+0.017
 rely+0.016
Neg logit contributions
less-0.026
 words-0.024
anger-0.023
t-0.023
ily-0.023
Token very
Token ID845
Feature activation+7.75e-02

Pos logit contributions
oc+0.020
ior+0.018
load+0.018
 bank+0.018
 negotiate+0.017
Neg logit contributions
ily-0.014
arl-0.012
ed-0.012
aces-0.012
ps-0.012
Token excited
Token ID6568
Feature activation-2.29e-02

Pos logit contributions
ior+0.120
oc+0.118
 bank+0.117
bowl+0.114
 rely+0.114
Neg logit contributions
ily-0.104
arl-0.104
less-0.098
lessness-0.096
ed-0.091
Token to
Token ID284
Feature activation-2.80e-02

Pos logit contributions
arl+0.025
ily+0.023
lessness+0.022
anish+0.022
aces+0.022
Neg logit contributions
 bank-0.042
 roasted-0.042
 barbecue-0.041
 forth-0.041
 rely-0.041
Token bake
Token ID28450
Feature activation+3.21e-02

Pos logit contributions
ily+0.044
arl+0.042
anger+0.040
 words+0.040
anish+0.040
Neg logit contributions
ior-0.036
 afloat-0.034
 bank-0.032
oc-0.032
 forth-0.032
Token chocolate
Token ID11311
Feature activation+5.73e-02

Pos logit contributions
 bank+0.062
ior+0.061
 roasted+0.061
 rely+0.061
 afloat+0.060
Neg logit contributions
ily-0.029
arl-0.027
lessness-0.027
der-0.025
anger-0.025
Token chip
Token ID11594
Feature activation+1.94e-01

Pos logit contributions
 afloat+0.106
 rely+0.105
 roasted+0.104
ior+0.104
bowl+0.103
Neg logit contributions
ily-0.053
der-0.052
anger-0.051
arl-0.050
ed-0.050
Token cookies
Token ID14746
Feature activation+2.65e-02

Pos logit contributions
 afloat+0.313
 roasted+0.294
 rely+0.293
 discuss+0.289
load+0.288
Neg logit contributions
ily-0.253
ed-0.241
iness-0.239
lessness-0.238
aces-0.230
Token.
Token ID13
Feature activation+1.79e-02

Pos logit contributions
 bank+0.049
 roasted+0.049
load+0.048
 afloat+0.048
 rely+0.048
Neg logit contributions
arl-0.026
ily-0.025
lessness-0.025
der-0.023
anger-0.023
Token Lily
Token ID20037
Feature activation-2.45e-02

Pos logit contributions
 afloat+0.030
 rely+0.030
 forth+0.029
 bank+0.027
 roasted+0.027
Neg logit contributions
ily-0.023
arl-0.020
lessness-0.020
der-0.019
anger-0.019
Token helped
Token ID4193
Feature activation+9.30e-03

Pos logit contributions
ily+0.038
ed+0.036
der+0.033
aces+0.033
lessness+0.032
Neg logit contributions
 afloat-0.038
 rely-0.032
load-0.030
ior-0.030
 paddle-0.030
Token her
Token ID607
Feature activation-4.10e-02

Pos logit contributions
 afloat+0.020
 rely+0.020
 bank+0.020
bowl+0.019
 roasted+0.019
Neg logit contributions
ily-0.007
arl-0.006
anger-0.005
ed-0.005
less-0.005
Token in
Token ID287
Feature activation+4.13e-02

Pos logit contributions
arl+0.131
anish+0.125
ily+0.118
lessness+0.117
ment+0.116
Neg logit contributions
 bank-0.117
 afloat-0.115
 asked-0.113
 forth-0.112
 called-0.111
Token her
Token ID607
Feature activation-4.89e-02

Pos logit contributions
 cub+0.062
 feed+0.060
 asked+0.060
 bank+0.059
 roasted+0.059
Neg logit contributions
anger-0.060
arl-0.059
der-0.059
lessness-0.056
aces-0.056
Token paws
Token ID49193
Feature activation+1.68e-02

Pos logit contributions
arl+0.069
ily+0.069
lessness+0.067
aces+0.065
der+0.065
Neg logit contributions
 roasted-0.069
 bank-0.068
load-0.068
 afloat-0.067
ior-0.066
Token.
Token ID13
Feature activation-2.68e-03

Pos logit contributions
 bank+0.028
bowl+0.027
 afloat+0.027
 cub+0.026
 roasted+0.026
Neg logit contributions
arl-0.022
ily-0.020
anish-0.020
lessness-0.019
anger-0.019
Token The
Token ID383
Feature activation+6.90e-04

Pos logit contributions
arl+0.003
iness+0.003
lessness+0.003
ily+0.003
anish+0.003
Neg logit contributions
 bank-0.004
ior-0.004
 roasted-0.004
load-0.004
 cub-0.004
Token chip
Token ID11594
Feature activation+1.94e-01

Pos logit contributions
 roasted+0.001
 afloat+0.001
ior+0.001
load+0.001
bowl+0.001
Neg logit contributions
 words-0.001
ily-0.001
arl-0.001
less-0.001
lessness-0.001
Tokenm
Token ID76
Feature activation+7.17e-02

Pos logit contributions
 afloat+0.351
 rely+0.342
 roasted+0.339
load+0.338
 discuss+0.327
Neg logit contributions
ily-0.223
lessness-0.215
iness-0.209
ed-0.205
anish-0.194
Tokenunk
Token ID2954
Feature activation+7.44e-02

Pos logit contributions
 cub+0.104
bowl+0.098
 bank+0.097
 sausage+0.095
dy+0.095
Neg logit contributions
arl-0.098
lessness-0.095
anish-0.094
ily-0.091
ative-0.089
Token got
Token ID1392
Feature activation-2.28e-03

Pos logit contributions
 bank+0.079
 roasted+0.078
load+0.078
 afloat+0.077
 rely+0.077
Neg logit contributions
ily-0.130
arl-0.129
lessness-0.127
der-0.124
anish-0.122
Token closer
Token ID5699
Feature activation+2.36e-02

Pos logit contributions
ily+0.003
arl+0.003
lessness+0.003
less+0.003
der+0.003
Neg logit contributions
 bank-0.003
 roasted-0.003
ior-0.003
load-0.003
 rely-0.003
Token and
Token ID290
Feature activation-1.40e-02

Pos logit contributions
 nib+0.031
 bank+0.031
 cub+0.031
 asked+0.030
 forth+0.029
Neg logit contributions
arl-0.041
ily-0.038
anish-0.038
anger-0.037
lessness-0.036
Token too
Token ID1165
Feature activation+3.05e-02

Pos logit contributions
arl+0.005
anger+0.004
anish+0.004
aces+0.004
adies+0.004
Neg logit contributions
 bank-0.004
 asked-0.003
 rely-0.003
 cub-0.003
 nib-0.003
Token.
Token ID13
Feature activation-2.23e-03

Pos logit contributions
 bank+0.038
 cub+0.038
 afloat+0.036
 rely+0.035
 Junior+0.034
Neg logit contributions
arl-0.054
anish-0.050
anger-0.050
iness-0.047
ily-0.047
Token
Token ID198
Feature activation+1.08e-02

Pos logit contributions
ily+0.003
arl+0.003
lessness+0.003
der+0.003
ed+0.003
Neg logit contributions
 bank-0.003
 roasted-0.003
 rely-0.003
 afloat-0.003
 forth-0.003
Token
Token ID198
Feature activation+7.88e-03

Pos logit contributions
 forth+0.019
 bank+0.019
ior+0.018
 discuss+0.018
 afloat+0.018
Neg logit contributions
ily-0.013
arl-0.012
lessness-0.012
t-0.011
anish-0.011
TokenThe
Token ID464
Feature activation-2.46e-03

Pos logit contributions
 bank+0.011
 roasted+0.011
load+0.011
 afloat+0.011
 rely+0.011
Neg logit contributions
arl-0.011
ily-0.011
lessness-0.011
der-0.011
anger-0.011
Token chip
Token ID11594
Feature activation+1.94e-01

Pos logit contributions
ily+0.003
 words+0.003
anish+0.003
arl+0.003
der+0.003
Neg logit contributions
ior-0.004
load-0.004
 afloat-0.004
 Junior-0.004
bowl-0.004
Tokenm
Token ID76
Feature activation+6.72e-02

Pos logit contributions
 afloat+0.341
 roasted+0.323
 rely+0.322
load+0.318
itionally+0.313
Neg logit contributions
ily-0.233
iness-0.221
lessness-0.219
anish-0.213
ed-0.211
Tokenunk
Token ID2954
Feature activation+6.75e-02

Pos logit contributions
 bank+0.108
 roasted+0.107
bowl+0.106
 cub+0.106
 rely+0.105
Neg logit contributions
arl-0.081
lessness-0.078
ily-0.077
anish-0.072
der-0.072
Token helped
Token ID4193
Feature activation+9.41e-03

Pos logit contributions
 bank+0.072
 roasted+0.070
load+0.068
 rely+0.067
bowl+0.066
Neg logit contributions
arl-0.123
ily-0.118
lessness-0.117
anger-0.114
der-0.113
Token the
Token ID262
Feature activation+2.90e-02

Pos logit contributions
 roasted+0.016
 afloat+0.016
 bank+0.016
 rely+0.016
load+0.016
Neg logit contributions
ily-0.010
arl-0.010
lessness-0.009
anish-0.009
anger-0.009
Token frog
Token ID21264
Feature activation+6.01e-02

Pos logit contributions
ior+0.047
 afloat+0.045
 Junior+0.045
load+0.045
 roasted+0.045
Neg logit contributions
 words-0.036
ily-0.035
der-0.033
arl-0.032
anish-0.032
Token around
Token ID1088
Feature activation-1.44e-02

Pos logit contributions
 forth+0.002
 bank+0.001
 asked+0.001
 afloat+0.001
 cub+0.001
Neg logit contributions
arl-0.002
der-0.002
anish-0.002
lessness-0.002
ives-0.002
Token,
Token ID11
Feature activation-4.65e-02

Pos logit contributions
arl+0.033
der+0.029
aces+0.029
iness+0.028
itted+0.027
Neg logit contributions
 bank-0.014
 asked-0.014
 farm-0.014
 forth-0.014
 nib-0.014
Token she
Token ID673
Feature activation-3.39e-02

Pos logit contributions
arl+0.079
iness+0.061
lessness+0.061
anish+0.060
aces+0.059
Neg logit contributions
 roasted-0.074
 bank-0.073
 asked-0.070
 nib-0.069
 discuss-0.068
Token saw
Token ID2497
Feature activation-7.12e-02

Pos logit contributions
ily+0.055
ed+0.054
lessness+0.053
der+0.051
anger+0.051
Neg logit contributions
 rely-0.040
ior-0.040
load-0.039
 afloat-0.038
 sausage-0.038
Token a
Token ID257
Feature activation-1.71e-02

Pos logit contributions
arl+0.126
anish+0.109
iness+0.109
ider+0.108
anger+0.106
Neg logit contributions
 roasted-0.098
 bank-0.096
 asked-0.096
 cub-0.096
 discuss-0.095
Token grace
Token ID11542
Feature activation-1.98e-01

Pos logit contributions
arl+0.013
less+0.013
joy+0.012
 words+0.011
lessness+0.011
Neg logit contributions
ior-0.036
 rely-0.033
load-0.033
bowl-0.033
seed-0.032
Tokenfully
Token ID2759
Feature activation-3.58e-02

Pos logit contributions
joy+0.240
anish+0.213
ips+0.188
 yourselves+0.188
arl+0.188
Neg logit contributions
 roasted-0.334
cker-0.330
 cub-0.315
 nib-0.312
orse-0.310
Token cur
Token ID1090
Feature activation-7.18e-02

Pos logit contributions
arl+0.061
ily+0.060
lessness+0.059
anish+0.057
iness+0.056
Neg logit contributions
 bank-0.044
 roasted-0.042
 afloat-0.042
load-0.041
 forth-0.041
Tokenving
Token ID1075
Feature activation-5.11e-04

Pos logit contributions
arl+0.122
ily+0.120
lessness+0.120
iness+0.114
anger+0.113
Neg logit contributions
ior-0.081
 discuss-0.081
 rely-0.080
 bank-0.080
 roasted-0.079
Token snake
Token ID17522
Feature activation-1.79e-02

Pos logit contributions
arl+0.001
ily+0.001
lessness+0.001
anish+0.001
iness+0.001
Neg logit contributions
 bank-0.001
 afloat-0.001
 roasted-0.001
 cub-0.001
load-0.001
Token near
Token ID1474
Feature activation+2.89e-02

Pos logit contributions
arl+0.021
ily+0.020
lessness+0.020
iness+0.019
anish+0.019
Neg logit contributions
 bank-0.031
 roasted-0.030
load-0.029
 rely-0.029
 afloat-0.029
Token to
Token ID284
Feature activation-3.48e-02

Pos logit contributions
 bank+0.039
 roasted+0.039
 discuss+0.038
load+0.038
 rely+0.038
Neg logit contributions
arl-0.016
lessness-0.015
ily-0.015
iness-0.014
anger-0.014
Token cry
Token ID3960
Feature activation-5.48e-03

Pos logit contributions
ily+0.046
 herself+0.046
anish+0.046
 words+0.046
arl+0.045
Neg logit contributions
ior-0.046
oc-0.046
 roasted-0.046
load-0.046
 afloat-0.045
Token and
Token ID290
Feature activation-2.02e-02

Pos logit contributions
arl+0.007
ily+0.007
anish+0.007
anger+0.007
aces+0.007
Neg logit contributions
 forth-0.008
 bank-0.008
 roasted-0.008
 afloat-0.008
 discuss-0.008
Token threw
Token ID9617
Feature activation+4.95e-02

Pos logit contributions
ily+0.028
lessness+0.026
ed+0.025
 herself+0.025
der+0.025
Neg logit contributions
 afloat-0.030
load-0.030
oc-0.029
ior-0.029
 roasted-0.028
Token a
Token ID257
Feature activation-1.59e-02

Pos logit contributions
 bank+0.089
 forth+0.089
 roasted+0.086
ior+0.085
 discuss+0.085
Neg logit contributions
arl-0.055
lessness-0.051
der-0.049
anger-0.049
anish-0.048
Token tant
Token ID24246
Feature activation-1.98e-01

Pos logit contributions
arl+0.021
ily+0.021
lessness+0.020
der+0.020
aces+0.020
Neg logit contributions
 bank-0.024
 roasted-0.024
load-0.023
 afloat-0.023
bowl-0.023
Tokenrum
Token ID6582
Feature activation-3.96e-02

Pos logit contributions
arl+0.250
ily+0.233
lessness+0.232
der+0.227
anger+0.225
Neg logit contributions
load-0.301
bowl-0.299
oc-0.299
 rely-0.298
ior-0.297
Token.
Token ID13
Feature activation-2.05e-02

Pos logit contributions
arl+0.071
anish+0.063
ives+0.061
anger+0.059
igsaw+0.059
Neg logit contributions
 forth-0.050
 cub-0.045
 asked-0.045
 bank-0.043
 called-0.042
Token She
Token ID1375
Feature activation-6.56e-03

Pos logit contributions
iness+0.029
lessness+0.029
arl+0.028
ier+0.026
less+0.026
Neg logit contributions
 bank-0.031
 discuss-0.031
 asked-0.030
ior-0.029
 pasture-0.029
Token didn
Token ID1422
Feature activation-1.00e-01

Pos logit contributions
ily+0.008
ed+0.008
der+0.008
 words+0.007
aces+0.007
Neg logit contributions
 afloat-0.012
 pasture-0.011
load-0.011
 rely-0.011
 gra-0.010
Token't
Token ID470
Feature activation-8.36e-02

Pos logit contributions
lessness+0.099
arl+0.099
joy+0.094
iness+0.093
ment+0.092
Neg logit contributions
 bank-0.179
 roasted-0.178
load-0.178
 rely-0.178
 discuss-0.176
Token bag
Token ID6131
Feature activation-2.13e-02

Pos logit contributions
arl+0.123
ily+0.120
lessness+0.119
anger+0.114
der+0.113
Neg logit contributions
 bank-0.109
 roasted-0.105
 rely-0.104
 afloat-0.103
load-0.103
Token.
Token ID13
Feature activation-9.90e-03

Pos logit contributions
arl+0.030
anish+0.028
joy+0.027
anger+0.026
der+0.026
Neg logit contributions
 bank-0.033
bowl-0.029
load-0.029
 roasted-0.029
 asked-0.029
Token Lily
Token ID20037
Feature activation-3.67e-02

Pos logit contributions
arl+0.013
ily+0.012
lessness+0.012
der+0.012
anger+0.012
Neg logit contributions
 bank-0.015
 roasted-0.015
load-0.015
 afloat-0.015
 rely-0.015
Token was
Token ID373
Feature activation-2.13e-02

Pos logit contributions
ily+0.055
ed+0.052
aces+0.049
der+0.049
lessness+0.047
Neg logit contributions
 afloat-0.053
load-0.047
 rely-0.047
bowl-0.046
 barbecue-0.046
Token over
Token ID625
Feature activation+3.79e-02

Pos logit contributions
ily+0.031
lessness+0.028
arl+0.028
aces+0.028
less+0.027
Neg logit contributions
ior-0.031
 bank-0.031
oc-0.030
load-0.030
bowl-0.029
Tokenjoy
Token ID2633
Feature activation-1.95e-01

Pos logit contributions
 asked+0.074
 pasture+0.071
 nib+0.070
 feed+0.069
 sausage+0.069
Neg logit contributions
arl-0.043
aces-0.043
anger-0.040
anish-0.040
lessness-0.040
Tokened
Token ID276
Feature activation-8.52e-03

Pos logit contributions
arl+0.164
anger+0.130
der+0.124
lessness+0.121
ily+0.114
Neg logit contributions
ior-0.412
 asked-0.403
oc-0.401
 forth-0.392
 rely-0.392
Token and
Token ID290
Feature activation-9.39e-03

Pos logit contributions
arl+0.012
anish+0.012
aces+0.012
ily+0.012
anger+0.012
Neg logit contributions
 forth-0.012
 bank-0.012
 asked-0.012
 pasture-0.012
 rely-0.012
Token hugged
Token ID41130
Feature activation-1.33e-02

Pos logit contributions
ily+0.015
ed+0.015
lessness+0.014
 herself+0.014
overed+0.014
Neg logit contributions
ior-0.012
 afloat-0.012
bowl-0.011
oc-0.011
 pasture-0.011
Token her
Token ID607
Feature activation-4.52e-02

Pos logit contributions
arl+0.011
lessness+0.010
ily+0.010
anger+0.009
anish+0.009
Neg logit contributions
 bank-0.027
 roasted-0.027
ior-0.027
 rely-0.027
load-0.026
Token blue
Token ID4171
Feature activation+1.53e-02

Pos logit contributions
arl+0.067
ily+0.066
lessness+0.065
anish+0.063
der+0.062
Neg logit contributions
 bank-0.062
 roasted-0.061
 afloat-0.060
 rely-0.060
load-0.060
Token kept
Token ID4030
Feature activation+2.28e-02

Pos logit contributions
ily+0.002
ed+0.002
der+0.002
t+0.002
 words+0.002
Neg logit contributions
 afloat-0.002
load-0.002
 rely-0.002
 gra-0.002
oc-0.002
Token crying
Token ID13774
Feature activation+7.53e-03

Pos logit contributions
 bank+0.033
load+0.032
oc+0.032
 roasted+0.032
ior+0.032
Neg logit contributions
arl-0.031
ily-0.031
joy-0.030
lessness-0.029
der-0.029
Token and
Token ID290
Feature activation+2.49e-03

Pos logit contributions
 forth+0.010
 afloat+0.010
 cub+0.009
ior+0.009
 bank+0.009
Neg logit contributions
anish-0.011
arl-0.011
anger-0.011
overed-0.011
adies-0.011
Token throwing
Token ID9644
Feature activation+6.74e-02

Pos logit contributions
 bank+0.003
 roasted+0.003
load+0.003
 rely+0.003
 afloat+0.003
Neg logit contributions
arl-0.004
ily-0.004
lessness-0.004
anger-0.004
der-0.004
Token a
Token ID257
Feature activation-3.08e-03

Pos logit contributions
 bank+0.122
 roasted+0.116
 sausage+0.116
load+0.115
 forth+0.115
Neg logit contributions
arl-0.074
lessness-0.070
ily-0.068
anger-0.068
anish-0.066
Token tant
Token ID24246
Feature activation-1.94e-01

Pos logit contributions
arl+0.003
lessness+0.003
ily+0.003
less+0.003
anger+0.003
Neg logit contributions
 rely-0.006
ior-0.006
 roasted-0.006
 discuss-0.006
 afloat-0.005
Tokenrum
Token ID6582
Feature activation-3.15e-02

Pos logit contributions
arl+0.241
lessness+0.224
ily+0.224
der+0.221
anger+0.217
Neg logit contributions
load-0.299
bowl-0.297
 rely-0.295
ior-0.294
oc-0.293
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
arl+0.058
anish+0.049
ives+0.047
igsaw+0.047
ir+0.047
Neg logit contributions
 forth-0.039
 asked-0.035
 cub-0.034
 called-0.034
 bank-0.034
Token
Token ID198
Feature activation+3.29e-04

Pos logit contributions
arl+0.017
lessness+0.017
ily+0.017
iness+0.016
der+0.016
Neg logit contributions
 bank-0.013
 roasted-0.012
load-0.012
ior-0.012
 discuss-0.012
Token
Token ID198
Feature activation-2.64e-03

Pos logit contributions
 bank+0.001
 afloat+0.000
 roasted+0.000
 forth+0.000
ior+0.000
Neg logit contributions
ily-0.000
arl-0.000
lessness-0.000
anger-0.000
t-0.000
TokenFinally
Token ID11158
Feature activation-2.14e-02

Pos logit contributions
arl+0.004
lessness+0.004
ily+0.004
anger+0.004
der+0.004
Neg logit contributions
 bank-0.003
 roasted-0.003
load-0.003
 rely-0.003
 discuss-0.003
Token She
Token ID1375
Feature activation-2.73e-03

Pos logit contributions
arl+0.015
lessness+0.015
iness+0.015
ily+0.014
anish+0.013
Neg logit contributions
 bank-0.027
ior-0.027
 discuss-0.026
 roasted-0.026
 pasture-0.026
Token cried
Token ID16896
Feature activation+6.09e-03

Pos logit contributions
ily+0.004
ed+0.004
der+0.004
 words+0.004
aces+0.003
Neg logit contributions
 afloat-0.004
load-0.004
 gra-0.004
 rely-0.004
bowl-0.004
Token and
Token ID290
Feature activation-1.48e-02

Pos logit contributions
 roasted+0.008
 cub+0.008
 bank+0.008
 forth+0.008
ior+0.008
Neg logit contributions
arl-0.009
anger-0.009
anish-0.009
overed-0.009
ily-0.008
Token threw
Token ID9617
Feature activation+5.40e-02

Pos logit contributions
ily+0.028
arl+0.027
lessness+0.027
der+0.027
ed+0.026
Neg logit contributions
load-0.014
 afloat-0.014
 roasted-0.014
 bank-0.014
 rely-0.014
Token a
Token ID257
Feature activation-1.04e-02

Pos logit contributions
 bank+0.099
 forth+0.096
 discuss+0.093
ior+0.093
 sausage+0.093
Neg logit contributions
arl-0.061
lessness-0.057
anger-0.056
der-0.055
ider-0.053
Token tant
Token ID24246
Feature activation-1.93e-01

Pos logit contributions
arl+0.012
ily+0.012
lessness+0.012
der+0.011
aces+0.011
Neg logit contributions
 bank-0.017
 roasted-0.017
load-0.017
 afloat-0.017
bowl-0.017
Tokenrum
Token ID6582
Feature activation-2.37e-02

Pos logit contributions
arl+0.242
ily+0.229
lessness+0.226
anger+0.221
der+0.221
Neg logit contributions
load-0.297
oc-0.295
bowl-0.293
ior-0.293
 rely-0.289
Token.
Token ID13
Feature activation-8.92e-03

Pos logit contributions
arl+0.046
igsaw+0.041
anish+0.039
ir+0.039
anger+0.039
Neg logit contributions
 forth-0.025
 cub-0.024
 asked-0.024
 bank-0.023
 called-0.023
Token Her
Token ID2332
Feature activation+8.28e-03

Pos logit contributions
arl+0.011
lessness+0.011
iness+0.011
ily+0.011
anger+0.010
Neg logit contributions
 bank-0.014
 roasted-0.014
ior-0.014
 discuss-0.014
load-0.014
Token mom
Token ID1995
Feature activation-1.09e-02

Pos logit contributions
 bank+0.009
 cub+0.008
 sausage+0.008
 forth+0.008
 discuss+0.008
Neg logit contributions
arl-0.015
lessness-0.015
ily-0.015
der-0.015
anish-0.014
Token tried
Token ID3088
Feature activation+3.07e-02

Pos logit contributions
ily+0.017
ed+0.017
lessness+0.016
iness+0.016
der+0.015
Neg logit contributions
 afloat-0.015
 pasture-0.014
 rely-0.014
 bank-0.014
ior-0.014
Token
Token ID198
Feature activation+1.38e-03

Pos logit contributions
ily+0.018
arl+0.018
lessness+0.017
der+0.017
anger+0.017
Neg logit contributions
 bank-0.016
 roasted-0.016
load-0.015
 forth-0.015
ior-0.015
Token
Token ID198
Feature activation+3.72e-03

Pos logit contributions
 bank+0.002
 roasted+0.002
 afloat+0.002
 rely+0.002
load+0.002
Neg logit contributions
ily-0.002
arl-0.002
lessness-0.002
anish-0.002
der-0.002
TokenJack
Token ID14295
Feature activation-1.06e-02

Pos logit contributions
load+0.005
 bank+0.005
 roasted+0.005
bowl+0.005
ior+0.005
Neg logit contributions
arl-0.006
lessness-0.005
ily-0.005
anger-0.005
der-0.005
Token was
Token ID373
Feature activation-6.15e-03

Pos logit contributions
ily+0.016
arl+0.016
lessness+0.015
der+0.015
anish+0.015
Neg logit contributions
 bank-0.014
 roasted-0.014
 afloat-0.014
load-0.014
 rely-0.013
Token over
Token ID625
Feature activation+4.77e-02

Pos logit contributions
ily+0.008
lessness+0.008
arl+0.008
der+0.008
aces+0.008
Neg logit contributions
 bank-0.009
ior-0.009
load-0.009
 roasted-0.009
bowl-0.009
Tokenjoy
Token ID2633
Feature activation-1.92e-01

Pos logit contributions
 nib+0.090
 asked+0.089
 cub+0.088
 bank+0.086
 discuss+0.086
Neg logit contributions
arl-0.061
anger-0.055
aces-0.054
iness-0.051
lessness-0.049
Tokened
Token ID276
Feature activation-1.78e-02

Pos logit contributions
arl+0.160
anger+0.127
ily+0.121
lessness+0.118
der+0.115
Neg logit contributions
ior-0.408
 asked-0.408
 rely-0.406
oc-0.400
 cub-0.395
Token,
Token ID11
Feature activation-4.49e-02

Pos logit contributions
arl+0.028
anger+0.026
anish+0.026
ily+0.025
aces+0.025
Neg logit contributions
 forth-0.026
 afloat-0.025
 asked-0.025
 bank-0.025
 rely-0.025
Token and
Token ID290
Feature activation-2.01e-02

Pos logit contributions
arl+0.060
ily+0.059
lessness+0.057
der+0.055
anger+0.055
Neg logit contributions
 bank-0.068
 roasted-0.067
load-0.066
 afloat-0.066
 rely-0.066
Token quickly
Token ID2952
Feature activation+1.76e-02

Pos logit contributions
ily+0.028
lessness+0.027
ed+0.027
der+0.027
ment+0.026
Neg logit contributions
ior-0.028
 bank-0.028
 afloat-0.028
 roasted-0.028
 pasture-0.028
Token said
Token ID531
Feature activation+6.25e-02

Pos logit contributions
 bank+0.016
 roasted+0.014
load+0.014
 rely+0.014
 afloat+0.014
Neg logit contributions
arl-0.036
lessness-0.035
anish-0.034
ily-0.034
anger-0.034
Token
Token ID198
Feature activation+2.91e-03

Pos logit contributions
arl+0.021
ily+0.020
lessness+0.020
der+0.019
anger+0.019
Neg logit contributions
 bank-0.024
 roasted-0.024
 afloat-0.024
 rely-0.024
load-0.024
Token
Token ID198
Feature activation+9.59e-04

Pos logit contributions
 bank+0.004
 roasted+0.004
 forth+0.004
 afloat+0.004
 rely+0.004
Neg logit contributions
ily-0.004
arl-0.004
lessness-0.004
anger-0.004
anish-0.004
TokenJohn
Token ID7554
Feature activation+4.79e-03

Pos logit contributions
load+0.001
 bank+0.001
 roasted+0.001
ior+0.001
 discuss+0.001
Neg logit contributions
arl-0.001
ily-0.001
lessness-0.001
anger-0.001
der-0.001
Token was
Token ID373
Feature activation-5.37e-03

Pos logit contributions
 afloat+0.007
 barbecue+0.006
 rely+0.006
 pasture+0.006
ior+0.006
Neg logit contributions
ed-0.007
ily-0.007
der-0.007
lessness-0.006
aces-0.006
Token over
Token ID625
Feature activation+5.02e-02

Pos logit contributions
ily+0.007
lessness+0.006
ed+0.006
aces+0.006
 herself+0.006
Neg logit contributions
ior-0.009
 bank-0.009
load-0.009
oc-0.009
 barbecue-0.008
Tokenjoy
Token ID2633
Feature activation-1.91e-01

Pos logit contributions
 asked+0.090
 nib+0.086
 cub+0.082
 kay+0.080
 sausage+0.079
Neg logit contributions
arl-0.075
aces-0.073
anger-0.068
iness-0.066
ily-0.064
Tokened
Token ID276
Feature activation-1.69e-02

Pos logit contributions
arl+0.160
ily+0.123
der+0.121
anger+0.118
lessness+0.109
Neg logit contributions
oc-0.416
ior-0.405
 rely-0.394
 asked-0.392
bowl-0.392
Token and
Token ID290
Feature activation-2.07e-02

Pos logit contributions
arl+0.029
anish+0.027
ily+0.027
anger+0.026
aces+0.025
Neg logit contributions
 forth-0.023
 asked-0.021
 afloat-0.021
 bank-0.021
 cub-0.021
Token asked
Token ID1965
Feature activation+1.12e-01

Pos logit contributions
ily+0.035
ed+0.035
lessness+0.035
der+0.033
ment+0.033
Neg logit contributions
ior-0.023
 afloat-0.023
 pasture-0.023
 roasted-0.022
 rely-0.022
Token the
Token ID262
Feature activation+4.07e-02

Pos logit contributions
 bank+0.161
 rely+0.161
 cub+0.160
 discuss+0.160
 asked+0.158
Neg logit contributions
arl-0.165
anger-0.152
lessness-0.150
aces-0.148
der-0.147
Token woman
Token ID2415
Feature activation+1.83e-02

Pos logit contributions
 asked+0.046
 farm+0.046
 bank+0.046
 cub+0.045
 discuss+0.045
Neg logit contributions
arl-0.072
aces-0.071
anish-0.070
lessness-0.068
anger-0.068
Token all
Token ID477
Feature activation+1.53e-02

Pos logit contributions
arl+0.065
ily+0.063
lessness+0.063
anger+0.060
anish+0.059
Neg logit contributions
 bank-0.074
 roasted-0.072
load-0.072
 afloat-0.071
 rely-0.071
Token."
Token ID526
Feature activation-8.29e-03

Pos logit contributions
 bank+0.025
 roasted+0.025
load+0.024
 afloat+0.024
 rely+0.024
Neg logit contributions
arl-0.019
ily-0.018
lessness-0.018
der-0.017
anger-0.017
Token Lucy
Token ID22162
Feature activation+3.01e-02

Pos logit contributions
ily+0.011
lessness+0.010
ed+0.010
der+0.010
ment+0.010
Neg logit contributions
 afloat-0.014
 forth-0.013
 rely-0.013
 bank-0.013
 roasted-0.013
Token was
Token ID373
Feature activation-3.72e-03

Pos logit contributions
 afloat+0.041
 roasted+0.039
load+0.039
 rely+0.039
 bank+0.038
Neg logit contributions
ily-0.046
ed-0.044
der-0.043
anish-0.043
lessness-0.042
Token over
Token ID625
Feature activation+4.89e-02

Pos logit contributions
ily+0.005
lessness+0.005
der+0.004
aces+0.004
ed+0.004
Neg logit contributions
ior-0.006
 bank-0.006
load-0.006
oc-0.006
 roasted-0.006
Tokenjoy
Token ID2633
Feature activation-1.91e-01

Pos logit contributions
 asked+0.085
 nib+0.082
 sausage+0.081
 bank+0.079
 discuss+0.078
Neg logit contributions
arl-0.069
aces-0.067
anger-0.062
hips-0.061
iness-0.059
Tokened
Token ID276
Feature activation-2.38e-02

Pos logit contributions
arl+0.166
der+0.129
anger+0.127
ps+0.122
ily+0.121
Neg logit contributions
ior-0.396
oc-0.391
 asked-0.384
 rely-0.381
 forth-0.378
Token and
Token ID290
Feature activation-2.67e-02

Pos logit contributions
arl+0.040
anger+0.038
anish+0.038
adies+0.037
ily+0.036
Neg logit contributions
 forth-0.032
 asked-0.029
 bank-0.029
 sausage-0.029
 rely-0.028
Token quickly
Token ID2952
Feature activation+9.22e-03

Pos logit contributions
ily+0.042
ed+0.041
lessness+0.041
der+0.040
ment+0.038
Neg logit contributions
 afloat-0.034
load-0.033
 rely-0.033
 pasture-0.033
ior-0.033
Token grabbed
Token ID13176
Feature activation-9.63e-03

Pos logit contributions
 bank+0.008
 roasted+0.008
load+0.008
 afloat+0.008
 rely+0.008
Neg logit contributions
arl-0.018
ily-0.018
lessness-0.017
anger-0.017
der-0.017
Token the
Token ID262
Feature activation+1.11e-02

Pos logit contributions
arl+0.012
lessness+0.011
ily+0.011
der+0.011
anish+0.011
Neg logit contributions
 bank-0.016
 roasted-0.016
load-0.016
ior-0.016
 discuss-0.016
Token listen
Token ID6004
Feature activation-3.55e-02

Pos logit contributions
arl+0.158
ily+0.157
lessness+0.153
der+0.147
iness+0.147
Neg logit contributions
 bank-0.136
 roasted-0.134
load-0.133
 afloat-0.132
 rely-0.130
Token.
Token ID13
Feature activation-2.15e-02

Pos logit contributions
anish+0.070
anger+0.066
bridge+0.066
arl+0.065
aces+0.065
Neg logit contributions
 asked-0.041
's-0.036
 bank-0.033
 called-0.033
 better-0.031
Token She
Token ID1375
Feature activation-7.11e-03

Pos logit contributions
iness+0.032
iest+0.030
ps+0.030
less+0.029
lessness+0.029
Neg logit contributions
 ask-0.028
ior-0.028
 asked-0.028
 discuss-0.027
 pasture-0.027
Token threw
Token ID9617
Feature activation+5.45e-02

Pos logit contributions
ily+0.011
der+0.011
ed+0.010
aces+0.010
lessness+0.010
Neg logit contributions
 afloat-0.010
load-0.009
bowl-0.009
 forth-0.009
ior-0.009
Token a
Token ID257
Feature activation-9.37e-03

Pos logit contributions
 bank+0.078
 forth+0.074
 sausage+0.072
 feed+0.068
 discuss+0.068
Neg logit contributions
arl-0.086
ider-0.085
lessness-0.084
anger-0.082
iness-0.080
Token tant
Token ID24246
Feature activation-1.91e-01

Pos logit contributions
arl+0.011
ily+0.011
lessness+0.010
der+0.010
aces+0.010
Neg logit contributions
 bank-0.016
 roasted-0.016
load-0.016
 afloat-0.015
bowl-0.015
Tokenrum
Token ID6582
Feature activation-2.84e-02

Pos logit contributions
arl+0.257
lessness+0.240
anger+0.238
joy+0.237
der+0.236
Neg logit contributions
oc-0.282
load-0.274
bowl-0.271
ior-0.270
 rely-0.265
Token in
Token ID287
Feature activation+4.80e-02

Pos logit contributions
arl+0.057
igsaw+0.053
anger+0.050
omed+0.049
ir+0.049
Neg logit contributions
 forth-0.030
 asked-0.026
 then-0.025
 called-0.024
 cub-0.023
Token the
Token ID262
Feature activation+1.65e-02

Pos logit contributions
 bank+0.058
 forth+0.057
 asked+0.056
 sausage+0.055
 feed+0.055
Neg logit contributions
overed-0.080
anger-0.080
der-0.079
arl-0.078
ative-0.078
Token store
Token ID3650
Feature activation+2.09e-02

Pos logit contributions
 rely+0.022
ior+0.021
 roasted+0.021
load+0.021
please+0.021
Neg logit contributions
arl-0.026
ily-0.025
lessness-0.024
anish-0.023
 words-0.023
Token.
Token ID13
Feature activation-1.36e-02

Pos logit contributions
 bank+0.033
 asked+0.027
 farm+0.027
 called+0.026
 forth+0.026
Neg logit contributions
arl-0.034
anish-0.031
lessness-0.030
ily-0.030
iness-0.029
Token
Token ID198
Feature activation+4.62e-03

Pos logit contributions
 bank+0.008
ior+0.008
load+0.008
 forth+0.008
 afloat+0.008
Neg logit contributions
ily-0.010
arl-0.009
lessness-0.009
der-0.009
anish-0.009
TokenCl
Token ID2601
Feature activation-2.14e-02

Pos logit contributions
 roasted+0.006
load+0.006
 bank+0.006
bowl+0.006
 discuss+0.006
Neg logit contributions
arl-0.007
anger-0.007
aces-0.006
lessness-0.006
iness-0.006
Tokenaire
Token ID7626
Feature activation+3.15e-02

Pos logit contributions
arl+0.045
lessness+0.043
anger+0.043
ily+0.042
aces+0.042
Neg logit contributions
 roasted-0.015
ior-0.015
load-0.015
bowl-0.015
 bank-0.015
Token was
Token ID373
Feature activation-8.49e-03

Pos logit contributions
 bank+0.034
 roasted+0.033
load+0.033
 rely+0.032
 afloat+0.032
Neg logit contributions
arl-0.056
ily-0.055
lessness-0.054
der-0.052
anger-0.052
Token over
Token ID625
Feature activation+5.07e-02

Pos logit contributions
arl+0.014
ily+0.013
anger+0.013
lessness+0.013
der+0.013
Neg logit contributions
 roasted-0.010
 bank-0.010
 rely-0.010
 afloat-0.010
load-0.010
Tokenjoy
Token ID2633
Feature activation-1.91e-01

Pos logit contributions
 asked+0.091
 nib+0.090
 pasture+0.087
 rely+0.087
 fed+0.086
Neg logit contributions
arl-0.068
aces-0.063
anger-0.062
anish-0.057
ily-0.056
Tokened
Token ID276
Feature activation-1.42e-02

Pos logit contributions
arl+0.200
anger+0.154
der+0.149
ps+0.142
hips+0.136
Neg logit contributions
 rely-0.360
 asked-0.358
ior-0.357
oc-0.356
 weighed-0.344
Token -
Token ID532
Feature activation+6.84e-03

Pos logit contributions
arl+0.024
anish+0.022
anger+0.022
adies+0.021
aces+0.021
Neg logit contributions
 forth-0.019
 rely-0.018
 asked-0.017
 bank-0.017
 pasture-0.017
Token her
Token ID607
Feature activation-5.54e-02

Pos logit contributions
 rely+0.011
 forth+0.011
 roasted+0.011
 discuss+0.011
 bank+0.011
Neg logit contributions
arl-0.009
anger-0.008
ily-0.008
aces-0.008
lessness-0.008
Token mug
Token ID25152
Feature activation+6.93e-02

Pos logit contributions
arl+0.096
ily+0.092
lessness+0.090
der+0.089
anish+0.089
Neg logit contributions
 sausage-0.064
 discuss-0.063
 rely-0.062
 forth-0.062
 farm-0.061
Token had
Token ID550
Feature activation-1.77e-02

Pos logit contributions
 bank+0.065
 rely+0.062
 roasted+0.060
 cub+0.060
 forth+0.058
Neg logit contributions
arl-0.146
ily-0.129
lessness-0.127
anger-0.126
anish-0.125
Token.
Token ID13
Feature activation+4.71e-03

Pos logit contributions
 bank+0.034
load+0.034
 afloat+0.034
ior+0.034
 rely+0.034
Neg logit contributions
ily-0.041
lessness-0.039
arl-0.039
ed-0.039
der-0.038
Token Tim
Token ID5045
Feature activation+1.73e-03

Pos logit contributions
 bank+0.007
 roasted+0.007
 afloat+0.007
load+0.007
 rely+0.007
Neg logit contributions
arl-0.006
ily-0.006
lessness-0.006
der-0.006
anish-0.006
Tokenmy
Token ID1820
Feature activation+1.12e-02

Pos logit contributions
 afloat+0.002
load+0.002
 bank+0.002
 roasted+0.002
 rely+0.002
Neg logit contributions
ily-0.003
ed-0.003
lessness-0.003
arl-0.003
iness-0.003
Token was
Token ID373
Feature activation-1.35e-02

Pos logit contributions
 afloat+0.016
load+0.015
 rely+0.014
 barbecue+0.014
 roasted+0.014
Neg logit contributions
ily-0.016
ed-0.016
der-0.015
aces-0.015
lessness-0.015
Token over
Token ID625
Feature activation+3.90e-02

Pos logit contributions
ily+0.018
aces+0.015
lessness+0.015
joy+0.015
arl+0.015
Neg logit contributions
 bank-0.022
ior-0.021
oc-0.021
load-0.021
bowl-0.020
Tokenjoy
Token ID2633
Feature activation-1.91e-01

Pos logit contributions
 rely+0.071
 asked+0.071
 discuss+0.071
 sausage+0.071
 pasture+0.070
Neg logit contributions
arl-0.045
aces-0.042
lessness-0.042
anger-0.042
ily-0.041
Tokened
Token ID276
Feature activation-5.91e-03

Pos logit contributions
arl+0.145
anger+0.118
ily+0.118
lessness+0.113
der+0.108
Neg logit contributions
ior-0.410
oc-0.405
 rely-0.401
 asked-0.397
 forth-0.397
Token and
Token ID290
Feature activation-7.06e-03

Pos logit contributions
arl+0.008
ily+0.008
anish+0.008
anger+0.008
aces+0.008
Neg logit contributions
 forth-0.009
 bank-0.009
 afloat-0.009
 rely-0.009
ior-0.009
Token said
Token ID531
Feature activation+6.80e-02

Pos logit contributions
ed+0.011
ily+0.011
lessness+0.010
der+0.010
ment+0.010
Neg logit contributions
ior-0.009
 afloat-0.009
 pasture-0.009
load-0.008
bowl-0.008
Token,
Token ID11
Feature activation-2.00e-02

Pos logit contributions
 asked+0.073
 rely+0.072
 sausage+0.072
 cub+0.072
 paddle+0.072
Neg logit contributions
arl-0.117
aces-0.111
anger-0.110
lessness-0.109
ily-0.108
Token "
Token ID366
Feature activation+1.30e-02

Pos logit contributions
ily+0.024
arl+0.024
lessness+0.023
iness+0.022
anger+0.022
Neg logit contributions
 bank-0.033
 roasted-0.032
load-0.032
 discuss-0.031
 rely-0.031
Token
Token ID198
Feature activation-6.77e-03

Pos logit contributions
ily+0.013
arl+0.012
lessness+0.011
anger+0.011
ed+0.011
Neg logit contributions
 forth-0.016
 bank-0.016
 afloat-0.016
 roasted-0.015
 discuss-0.015
TokenThe
Token ID464
Feature activation-1.20e-02

Pos logit contributions
arl+0.009
ily+0.009
lessness+0.008
der+0.008
anger+0.008
Neg logit contributions
 bank-0.011
 roasted-0.011
load-0.010
 afloat-0.010
 rely-0.010
Token rabbit
Token ID22746
Feature activation+5.70e-02

Pos logit contributions
ily+0.020
arl+0.020
lessness+0.019
der+0.018
anger+0.018
Neg logit contributions
load-0.015
 roasted-0.015
 bank-0.015
ior-0.015
 rely-0.015
Token was
Token ID373
Feature activation-2.19e-03

Pos logit contributions
 bank+0.069
 roasted+0.069
load+0.069
 afloat+0.069
 rely+0.067
Neg logit contributions
ily-0.090
arl-0.089
lessness-0.088
der-0.086
anish-0.084
Token over
Token ID625
Feature activation+5.24e-02

Pos logit contributions
ily+0.003
lessness+0.003
arl+0.003
der+0.003
aces+0.002
Neg logit contributions
ior-0.003
 bank-0.003
load-0.003
 forth-0.003
oc-0.003
Tokenjoy
Token ID2633
Feature activation-1.91e-01

Pos logit contributions
 nib+0.102
 asked+0.099
 cub+0.099
 afloat+0.096
 feed+0.096
Neg logit contributions
aces-0.064
anger-0.062
arl-0.061
iness-0.057
ily-0.054
Tokened
Token ID276
Feature activation-1.82e-02

Pos logit contributions
arl+0.143
der+0.114
anger+0.108
lessness+0.104
ily+0.102
Neg logit contributions
oc-0.424
ior-0.415
bowl-0.408
 cub-0.406
 rely-0.406
Token!
Token ID0
Feature activation-2.63e-02

Pos logit contributions
arl+0.030
anger+0.029
anish+0.028
aces+0.027
ily+0.027
Neg logit contributions
 forth-0.024
 asked-0.024
 cub-0.024
 afloat-0.023
 bank-0.023
Token He
Token ID679
Feature activation-8.69e-04

Pos logit contributions
arl+0.035
ily+0.035
lessness+0.034
der+0.033
anger+0.032
Neg logit contributions
 bank-0.039
 roasted-0.039
load-0.038
 afloat-0.038
 rely-0.038
Token hopped
Token ID45230
Feature activation-8.51e-03

Pos logit contributions
ily+0.001
der+0.001
ed+0.001
overed+0.001
 words+0.001
Neg logit contributions
 afloat-0.001
load-0.001
ior-0.001
 rely-0.001
bowl-0.001
Token up
Token ID510
Feature activation+2.48e-02

Pos logit contributions
der+0.015
anish+0.015
iness+0.015
arl+0.014
aces+0.014
Neg logit contributions
 bank-0.010
 afloat-0.010
 roasted-0.010
load-0.009
 nib-0.009
Token and
Token ID290
Feature activation-1.39e-02

Pos logit contributions
 asked+0.005
 cub+0.005
 bank+0.005
 sausage+0.005
 Junior+0.005
Neg logit contributions
arl-0.007
anish-0.006
ily-0.006
anger-0.006
alo-0.006
Token so
Token ID523
Feature activation+1.00e-01

Pos logit contributions
arl+0.024
ily+0.023
lessness+0.023
anger+0.022
der+0.022
Neg logit contributions
 bank-0.016
 roasted-0.016
load-0.015
 rely-0.015
ior-0.015
Token she
Token ID673
Feature activation-3.36e-02

Pos logit contributions
 forth+0.169
 asked+0.167
 roasted+0.167
 rely+0.166
 discuss+0.164
Neg logit contributions
arl-0.121
anger-0.115
anish-0.109
ily-0.108
der-0.105
Token threw
Token ID9617
Feature activation+4.23e-02

Pos logit contributions
ily+0.052
ed+0.048
t+0.044
der+0.042
te+0.041
Neg logit contributions
 afloat-0.052
 rely-0.047
load-0.047
 pasture-0.046
ior-0.045
Token a
Token ID257
Feature activation-1.28e-02

Pos logit contributions
 forth+0.079
 bank+0.077
 sausage+0.075
 discuss+0.074
bowl+0.074
Neg logit contributions
arl-0.048
lessness-0.044
anger-0.042
der-0.041
iness-0.041
Token tant
Token ID24246
Feature activation-1.91e-01

Pos logit contributions
arl+0.017
ily+0.016
lessness+0.016
anger+0.016
less+0.016
Neg logit contributions
 rely-0.019
 roasted-0.019
ior-0.019
 bank-0.019
load-0.019
Tokenrum
Token ID6582
Feature activation-3.44e-02

Pos logit contributions
arl+0.246
ily+0.228
lessness+0.223
der+0.220
anger+0.218
Neg logit contributions
bowl-0.289
load-0.288
 rely-0.288
oc-0.285
ior-0.284
Token when
Token ID618
Feature activation-1.33e-02

Pos logit contributions
arl+0.061
igsaw+0.054
ives+0.052
omed+0.051
anish+0.051
Neg logit contributions
 forth-0.043
 cub-0.042
 bank-0.041
 asked-0.039
 called-0.038
Token her
Token ID607
Feature activation-4.22e-02

Pos logit contributions
arl+0.020
der+0.017
anger+0.017
anish+0.017
ives+0.016
Neg logit contributions
 forth-0.021
 asked-0.021
 discuss-0.021
 bank-0.020
 roasted-0.020
Token parents
Token ID3397
Feature activation-1.18e-02

Pos logit contributions
ily+0.068
arl+0.067
lessness+0.066
anish+0.064
der+0.064
Neg logit contributions
 bank-0.053
 cub-0.051
 roasted-0.051
 afloat-0.050
 sausage-0.050
Token said
Token ID531
Feature activation+7.61e-02

Pos logit contributions
ily+0.019
ed+0.018
lessness+0.018
iness+0.018
t+0.018
Neg logit contributions
ior-0.015
 afloat-0.014
 pasture-0.014
 rely-0.014
die-0.014
Token sad
Token ID6507
Feature activation+1.24e-02

Pos logit contributions
ily+0.052
arl+0.051
lessness+0.051
der+0.049
ed+0.048
Neg logit contributions
 roasted-0.035
load-0.035
 afloat-0.035
 bank-0.035
bowl-0.034
Token.
Token ID13
Feature activation-1.90e-02

Pos logit contributions
 asked+0.014
 bank+0.013
 forth+0.013
 called+0.013
 rely+0.012
Neg logit contributions
adies-0.021
arl-0.020
anish-0.020
anger-0.020
aces-0.019
Token She
Token ID1375
Feature activation-3.06e-03

Pos logit contributions
ily+0.026
arl+0.026
lessness+0.025
der+0.024
anger+0.023
Neg logit contributions
 roasted-0.028
 bank-0.028
 afloat-0.028
load-0.028
 rely-0.027
Token threw
Token ID9617
Feature activation+5.23e-02

Pos logit contributions
ily+0.005
der+0.004
ed+0.004
 words+0.004
 herself+0.004
Neg logit contributions
 afloat-0.005
load-0.005
bowl-0.005
 rely-0.004
 roasted-0.004
Token a
Token ID257
Feature activation-9.58e-03

Pos logit contributions
 forth+0.075
 bank+0.074
 sausage+0.071
 discuss+0.070
load+0.069
Neg logit contributions
arl-0.082
ider-0.077
der-0.077
lessness-0.077
anger-0.074
Token tant
Token ID24246
Feature activation-1.90e-01

Pos logit contributions
arl+0.011
ily+0.011
lessness+0.011
der+0.010
anger+0.010
Neg logit contributions
 bank-0.016
 roasted-0.016
load-0.016
 afloat-0.016
 rely-0.016
Tokenrum
Token ID6582
Feature activation-3.23e-02

Pos logit contributions
arl+0.252
ily+0.233
lessness+0.232
der+0.230
anger+0.228
Neg logit contributions
oc-0.280
load-0.278
ior-0.278
bowl-0.277
 rely-0.275
Token and
Token ID290
Feature activation+2.63e-04

Pos logit contributions
arl+0.057
ives+0.050
igsaw+0.050
anger+0.049
anish+0.049
Neg logit contributions
 forth-0.044
 asked-0.038
 bank-0.037
 cub-0.037
 called-0.034
Token cried
Token ID16896
Feature activation+8.20e-03

Pos logit contributions
 bank+0.000
 roasted+0.000
load+0.000
 afloat+0.000
 rely+0.000
Neg logit contributions
arl-0.000
ily-0.000
lessness-0.000
der-0.000
anger-0.000
Token loudly
Token ID23112
Feature activation-4.33e-02

Pos logit contributions
 roasted+0.009
 cub+0.009
 bank+0.009
 forth+0.009
 afloat+0.009
Neg logit contributions
arl-0.013
anish-0.013
anger-0.013
adies-0.012
overed-0.012
Token.
Token ID13
Feature activation-1.58e-02

Pos logit contributions
arl+0.069
anish+0.067
lessness+0.066
ily+0.066
iness+0.065
Neg logit contributions
 bank-0.056
 asked-0.054
 cub-0.051
 sausage-0.048
 called-0.047
TokenThe
Token ID464
Feature activation-4.34e-03

Pos logit contributions
 bank+0.003
 roasted+0.002
ior+0.002
 afloat+0.002
 rely+0.002
Neg logit contributions
arl-0.002
ily-0.002
lessness-0.002
anger-0.002
der-0.002
Token little
Token ID1310
Feature activation+4.77e-02

Pos logit contributions
arl+0.006
ily+0.006
lessness+0.006
der+0.006
anish+0.006
Neg logit contributions
 bank-0.006
 cub-0.006
 forth-0.006
 roasted-0.006
 discuss-0.006
Token girl
Token ID2576
Feature activation+4.38e-02

Pos logit contributions
 forth+0.049
 bank+0.045
 discuss+0.042
 cub+0.042
 sausage+0.042
Neg logit contributions
arl-0.097
der-0.090
lessness-0.090
aces-0.088
anger-0.088
Token was
Token ID373
Feature activation-2.31e-03

Pos logit contributions
 afloat+0.062
ior+0.058
 roasted+0.057
 barbecue+0.057
load+0.057
Neg logit contributions
ily-0.064
ed-0.064
aces-0.060
der-0.058
anger-0.058
Token over
Token ID625
Feature activation+5.60e-02

Pos logit contributions
ily+0.003
lessness+0.003
arl+0.003
less+0.003
aces+0.003
Neg logit contributions
 bank-0.003
ior-0.003
load-0.003
 roasted-0.003
bowl-0.003
Tokenjoy
Token ID2633
Feature activation-1.90e-01

Pos logit contributions
 asked+0.099
 pasture+0.093
 kay+0.091
 nib+0.090
 feed+0.087
Neg logit contributions
aces-0.076
arl-0.074
iness-0.069
anish-0.068
anger-0.068
Tokened
Token ID276
Feature activation-1.36e-02

Pos logit contributions
arl+0.156
der+0.132
lessness+0.118
anger+0.118
ily+0.117
Neg logit contributions
ior-0.394
oc-0.390
 asked-0.389
 rely-0.382
bowl-0.374
Token and
Token ID290
Feature activation-1.91e-02

Pos logit contributions
arl+0.021
anish+0.020
anger+0.019
aces+0.019
ily+0.019
Neg logit contributions
 forth-0.019
 asked-0.018
 bank-0.018
 rely-0.018
 pasture-0.018
Token she
Token ID673
Feature activation-2.37e-02

Pos logit contributions
ily+0.028
lessness+0.028
ed+0.028
arl+0.027
less+0.027
Neg logit contributions
ior-0.025
 afloat-0.025
load-0.025
 bank-0.025
 roasted-0.025
Token thanked
Token ID26280
Feature activation-1.76e-02

Pos logit contributions
ed+0.039
ily+0.039
lessness+0.037
aces+0.036
der+0.036
Neg logit contributions
 afloat-0.028
ior-0.027
 barbecue-0.027
 roasted-0.027
bowl-0.026
Token her
Token ID607
Feature activation-3.28e-02

Pos logit contributions
arl+0.021
lessness+0.020
anish+0.019
ily+0.019
aces+0.019
Neg logit contributions
 rely-0.029
 bank-0.029
 roasted-0.029
 discuss-0.029
 forth-0.029
TokenR
Token ID49
Feature activation+1.02e-02

Pos logit contributions
ily+0.008
arl+0.008
lessness+0.007
der+0.007
anish+0.007
Neg logit contributions
 bank-0.009
ior-0.009
 forth-0.009
 afloat-0.009
 rely-0.009
Tokenuf
Token ID3046
Feature activation+7.61e-02

Pos logit contributions
 forth+0.009
 discuss+0.009
 bank+0.009
 roasted+0.009
load+0.008
Neg logit contributions
arl-0.021
ily-0.020
der-0.020
lessness-0.020
anger-0.019
Tokenus
Token ID385
Feature activation+1.16e-01

Pos logit contributions
 bank+0.081
 roasted+0.079
 afloat+0.078
 discuss+0.078
load+0.078
Neg logit contributions
arl-0.135
ily-0.134
lessness-0.132
der-0.127
anger-0.127
Token was
Token ID373
Feature activation-9.56e-03

Pos logit contributions
 bank+0.132
 roasted+0.129
load+0.125
bowl+0.122
 rely+0.122
Neg logit contributions
arl-0.206
ily-0.196
lessness-0.195
anger-0.190
iness-0.187
Token over
Token ID625
Feature activation+5.03e-02

Pos logit contributions
ily+0.014
lessness+0.013
arl+0.013
aces+0.012
less+0.012
Neg logit contributions
ior-0.014
 bank-0.014
load-0.014
bowl-0.013
 forth-0.013
Tokenjoy
Token ID2633
Feature activation-1.90e-01

Pos logit contributions
 cub+0.104
 nib+0.103
 asked+0.102
 afloat+0.102
 roasted+0.101
Neg logit contributions
arl-0.050
aces-0.045
anger-0.045
ily-0.044
anish-0.041
Tokened
Token ID276
Feature activation-1.39e-02

Pos logit contributions
arl+0.130
der+0.100
anger+0.099
ily+0.097
lessness+0.096
Neg logit contributions
oc-0.431
ior-0.424
 cub-0.421
 rely-0.415
bowl-0.410
Token and
Token ID290
Feature activation-2.15e-02

Pos logit contributions
arl+0.019
ily+0.018
anish+0.018
anger+0.017
aces+0.017
Neg logit contributions
 bank-0.022
 cub-0.021
 afloat-0.021
 rely-0.021
 sausage-0.020
Token as
Token ID355
Feature activation-5.77e-03

Pos logit contributions
ily+0.032
lessness+0.032
ed+0.032
ment+0.031
der+0.030
Neg logit contributions
ior-0.028
 pasture-0.027
load-0.027
 afloat-0.027
 rely-0.027
Token he
Token ID339
Feature activation-2.76e-02

Pos logit contributions
ily+0.008
lessness+0.008
arl+0.007
der+0.007
less+0.007
Neg logit contributions
 bank-0.009
load-0.009
ior-0.008
 discuss-0.008
 pasture-0.008
Token left
Token ID1364
Feature activation+1.15e-02

Pos logit contributions
ily+0.046
lessness+0.044
ed+0.044
der+0.044
arl+0.043
Neg logit contributions
ior-0.032
 afloat-0.031
 rely-0.030
load-0.030
 bank-0.030
Token
Token ID198
Feature activation+4.97e-03

Pos logit contributions
ily+0.015
arl+0.015
lessness+0.015
der+0.014
anger+0.014
Neg logit contributions
 bank-0.013
 roasted-0.013
 forth-0.013
ior-0.013
load-0.013
Token
Token ID198
Feature activation+6.13e-03

Pos logit contributions
 bank+0.007
 roasted+0.007
 rely+0.007
 afloat+0.007
 forth+0.007
Neg logit contributions
ily-0.007
arl-0.007
lessness-0.007
anish-0.007
der-0.007
TokenJack
Token ID14295
Feature activation-9.31e-03

Pos logit contributions
load+0.008
 bank+0.008
 roasted+0.008
bowl+0.008
 discuss+0.008
Neg logit contributions
arl-0.009
lessness-0.009
anger-0.009
ily-0.009
aces-0.009
Token was
Token ID373
Feature activation-1.53e-03

Pos logit contributions
arl+0.014
ily+0.014
lessness+0.013
anger+0.013
der+0.013
Neg logit contributions
 bank-0.012
 roasted-0.012
load-0.012
 afloat-0.012
 rely-0.012
Token over
Token ID625
Feature activation+5.34e-02

Pos logit contributions
ily+0.002
lessness+0.002
arl+0.002
der+0.002
ed+0.002
Neg logit contributions
 bank-0.002
ior-0.002
load-0.002
 roasted-0.002
 forth-0.002
Tokenjoy
Token ID2633
Feature activation-1.90e-01

Pos logit contributions
 cub+0.098
 asked+0.098
 nib+0.098
 discuss+0.095
 afloat+0.095
Neg logit contributions
arl-0.069
aces-0.066
anger-0.063
iness-0.057
ily-0.054
Tokened
Token ID276
Feature activation-1.47e-02

Pos logit contributions
arl+0.175
der+0.137
anger+0.137
ily+0.133
lessness+0.125
Neg logit contributions
oc-0.387
ior-0.380
 asked-0.380
 rely-0.377
 cub-0.376
Token.
Token ID13
Feature activation-9.04e-03

Pos logit contributions
arl+0.024
anger+0.022
anish+0.022
ily+0.022
aces+0.021
Neg logit contributions
 afloat-0.020
 forth-0.020
 cub-0.020
 bank-0.020
 asked-0.020
Token He
Token ID679
Feature activation+7.16e-03

Pos logit contributions
arl+0.014
ily+0.013
lessness+0.013
iness+0.013
anger+0.013
Neg logit contributions
 bank-0.012
load-0.012
 roasted-0.012
ior-0.012
bowl-0.012
Token and
Token ID290
Feature activation-6.77e-04

Pos logit contributions
 afloat+0.009
load+0.008
ior+0.008
bowl+0.008
 rely+0.008
Neg logit contributions
ily-0.012
der-0.011
ed-0.011
lessness-0.011
aces-0.011
Token Jill
Token ID22772
Feature activation-5.46e-02

Pos logit contributions
arl+0.001
anger+0.001
aces+0.001
lessness+0.001
ily+0.001
Neg logit contributions
 roasted-0.001
 bank-0.001
 forth-0.001
 discuss-0.001
 asked-0.001
TokenThe
Token ID464
Feature activation-1.66e-02

Pos logit contributions
ily+0.004
arl+0.004
lessness+0.004
anish+0.004
der+0.004
Neg logit contributions
 bank-0.006
 roasted-0.006
 afloat-0.006
ior-0.006
 rely-0.005
Token oct
Token ID19318
Feature activation+7.65e-03

Pos logit contributions
ily+0.021
arl+0.021
lessness+0.020
der+0.019
anger+0.019
Neg logit contributions
load-0.026
ior-0.025
 bank-0.025
 roasted-0.025
 rely-0.025
Tokenopus
Token ID25790
Feature activation+4.25e-02

Pos logit contributions
load+0.009
 bank+0.009
bowl+0.009
oc+0.009
 rely+0.009
Neg logit contributions
arl-0.013
ily-0.012
lessness-0.012
iness-0.012
der-0.012
Token was
Token ID373
Feature activation-3.80e-03

Pos logit contributions
 bank+0.049
load+0.049
 roasted+0.049
 afloat+0.048
ior+0.048
Neg logit contributions
ily-0.069
lessness-0.068
arl-0.068
der-0.066
iness-0.065
Token over
Token ID625
Feature activation+5.27e-02

Pos logit contributions
ily+0.005
lessness+0.005
arl+0.005
der+0.005
less+0.005
Neg logit contributions
 bank-0.005
ior-0.005
load-0.005
 roasted-0.005
bowl-0.005
Tokenjoy
Token ID2633
Feature activation-1.90e-01

Pos logit contributions
 nib+0.102
 cub+0.101
 asked+0.101
 afloat+0.100
 kay+0.099
Neg logit contributions
arl-0.062
aces-0.059
anger-0.058
ily-0.054
iness-0.051
Tokened
Token ID276
Feature activation-1.94e-02

Pos logit contributions
arl+0.166
der+0.129
ily+0.124
anger+0.124
lessness+0.116
Neg logit contributions
oc-0.400
ior-0.387
 rely-0.385
 cub-0.384
bowl-0.382
Token,
Token ID11
Feature activation-5.11e-02

Pos logit contributions
arl+0.031
anger+0.029
ily+0.029
anish+0.029
alo+0.027
Neg logit contributions
 afloat-0.027
 bank-0.026
 forth-0.026
 cub-0.026
 rely-0.025
Token and
Token ID290
Feature activation-2.39e-02

Pos logit contributions
arl+0.064
ily+0.062
anger+0.059
lessness+0.059
anish+0.058
Neg logit contributions
 bank-0.084
 roasted-0.083
 afloat-0.082
 rely-0.081
load-0.081
Token he
Token ID339
Feature activation-5.01e-03

Pos logit contributions
lessness+0.029
ily+0.029
ed+0.029
der+0.028
ment+0.027
Neg logit contributions
ior-0.037
 pasture-0.037
load-0.037
 discuss-0.036
 rely-0.036
Token thanked
Token ID26280
Feature activation-1.91e-02

Pos logit contributions
ily+0.008
ed+0.008
lessness+0.008
der+0.008
iness+0.008
Neg logit contributions
ior-0.006
load-0.006
 bank-0.006
 afloat-0.006
 pasture-0.006
Token her
Token ID607
Feature activation-7.39e-02

Pos logit contributions
arl+0.009
lessness+0.009
anger+0.008
iness+0.008
anish+0.008
Neg logit contributions
 bank-0.012
 forth-0.011
ior-0.011
 pasture-0.011
 cub-0.011
Token feet
Token ID3625
Feature activation-2.17e-02

Pos logit contributions
arl+0.119
ily+0.117
lessness+0.112
anish+0.110
der+0.107
Neg logit contributions
 bank-0.102
 forth-0.096
 cub-0.095
 afloat-0.093
 sausage-0.091
Token and
Token ID290
Feature activation-4.16e-03

Pos logit contributions
arl+0.035
anish+0.034
ily+0.033
adies+0.033
anger+0.032
Neg logit contributions
 bank-0.031
 forth-0.028
 afloat-0.027
 cub-0.026
bowl-0.026
Token threw
Token ID9617
Feature activation+5.62e-02

Pos logit contributions
ily+0.008
arl+0.008
lessness+0.008
der+0.007
aces+0.007
Neg logit contributions
 roasted-0.004
 bank-0.004
load-0.004
 afloat-0.004
 rely-0.004
Token a
Token ID257
Feature activation-8.29e-03

Pos logit contributions
 bank+0.092
 forth+0.085
 sausage+0.085
 cub+0.083
 feed+0.083
Neg logit contributions
arl-0.075
lessness-0.073
anger-0.070
anish-0.068
iness-0.068
Token tant
Token ID24246
Feature activation-1.89e-01

Pos logit contributions
arl+0.008
ily+0.008
lessness+0.008
der+0.007
anger+0.007
Neg logit contributions
 bank-0.015
 roasted-0.015
load-0.015
 afloat-0.015
 rely-0.015
Tokenrum
Token ID6582
Feature activation-2.18e-02

Pos logit contributions
arl+0.239
ily+0.224
lessness+0.222
der+0.218
anger+0.216
Neg logit contributions
load-0.292
ior-0.288
oc-0.288
bowl-0.288
 bank-0.287
Token.
Token ID13
Feature activation-1.07e-02

Pos logit contributions
arl+0.039
anish+0.034
igsaw+0.033
anger+0.033
ives+0.033
Neg logit contributions
 forth-0.027
 cub-0.025
 bank-0.025
 asked-0.024
 called-0.022
Token She
Token ID1375
Feature activation-6.87e-03

Pos logit contributions
iness+0.016
lessness+0.016
arl+0.015
less+0.015
anish+0.014
Neg logit contributions
 bank-0.015
 asked-0.015
 discuss-0.014
 pasture-0.014
ior-0.014
Token grabbed
Token ID13176
Feature activation-5.96e-04

Pos logit contributions
ily+0.011
ed+0.010
der+0.010
aces+0.010
 words+0.010
Neg logit contributions
 afloat-0.009
 rely-0.009
 pasture-0.009
ior-0.008
load-0.008
Token the
Token ID262
Feature activation+1.25e-02

Pos logit contributions
arl+0.001
lessness+0.001
anish+0.001
iness+0.001
der+0.001
Neg logit contributions
 bank-0.001
 roasted-0.001
 sausage-0.001
 discuss-0.001
 Junior-0.001
TokenS
Token ID50
Feature activation-6.06e-02

Pos logit contributions
 bank+0.014
 roasted+0.014
 afloat+0.014
ior+0.014
 forth+0.014
Neg logit contributions
ily-0.013
arl-0.013
lessness-0.012
anish-0.012
less-0.012
Tokenally
Token ID453
Feature activation+2.77e-02

Pos logit contributions
der+0.126
lessness+0.126
arl+0.124
aces+0.124
ps+0.122
Neg logit contributions
ior-0.040
 discuss-0.038
 rely-0.038
load-0.038
 bank-0.037
Token was
Token ID373
Feature activation-1.68e-03

Pos logit contributions
 bank+0.032
 roasted+0.031
load+0.031
 rely+0.030
 afloat+0.030
Neg logit contributions
arl-0.047
ily-0.046
lessness-0.046
anger-0.044
der-0.044
Token so
Token ID523
Feature activation+9.77e-02

Pos logit contributions
arl+0.003
ily+0.003
lessness+0.003
der+0.002
anger+0.002
Neg logit contributions
 bank-0.002
 roasted-0.002
load-0.002
 afloat-0.002
 rely-0.002
Token over
Token ID625
Feature activation+5.24e-02

Pos logit contributions
 roasted+0.101
 bank+0.100
load+0.098
 rely+0.098
 afloat+0.097
Neg logit contributions
arl-0.177
ily-0.174
lessness-0.170
anger-0.169
der-0.168
Tokenjoy
Token ID2633
Feature activation-1.89e-01

Pos logit contributions
 pasture+0.077
 asked+0.076
 forth+0.074
 rely+0.074
 feed+0.073
Neg logit contributions
arl-0.088
anger-0.080
aces-0.078
ily-0.075
anish-0.071
Tokened
Token ID276
Feature activation-8.81e-03

Pos logit contributions
arl+0.152
der+0.136
anger+0.124
ps+0.121
ily+0.118
Neg logit contributions
ior-0.387
oc-0.384
seed-0.381
 rely-0.380
 asked-0.373
Token with
Token ID351
Feature activation-4.09e-02

Pos logit contributions
arl+0.013
anish+0.012
anger+0.012
ily+0.012
aces+0.012
Neg logit contributions
 forth-0.013
 bank-0.012
 rely-0.012
 pasture-0.012
 Junior-0.012
Token her
Token ID607
Feature activation-5.57e-02

Pos logit contributions
anger+0.060
arl+0.057
anish+0.056
ed+0.053
ider+0.052
Neg logit contributions
 rely-0.064
 asked-0.061
 feed-0.060
 discuss-0.059
 roasted-0.059
Token present
Token ID1944
Feature activation-1.57e-02

Pos logit contributions
arl+0.089
ily+0.088
lessness+0.086
anish+0.084
der+0.083
Neg logit contributions
 bank-0.070
 roasted-0.070
 rely-0.069
 cub-0.067
 discuss-0.067
Token that
Token ID326
Feature activation+3.27e-02

Pos logit contributions
arl+0.023
ily+0.020
anish+0.019
lessness+0.019
adies+0.018
Neg logit contributions
 bank-0.025
 cub-0.024
 rely-0.023
 roasted-0.023
 pasture-0.023
Token The
Token ID383
Feature activation-9.85e-03

Pos logit contributions
ily+0.017
arl+0.017
lessness+0.016
der+0.016
anger+0.015
Neg logit contributions
 bank-0.025
 roasted-0.024
 afloat-0.024
 rely-0.024
load-0.024
Token bird
Token ID6512
Feature activation+1.29e-02

Pos logit contributions
ily+0.013
arl+0.013
lessness+0.013
der+0.013
iness+0.012
Neg logit contributions
load-0.015
 roasted-0.014
 rely-0.014
ior-0.014
 bank-0.014
Token was
Token ID373
Feature activation+5.96e-03

Pos logit contributions
 afloat+0.017
ior+0.016
 discuss+0.016
 rely+0.016
load+0.016
Neg logit contributions
ily-0.019
lessness-0.019
ed-0.019
der-0.018
aces-0.018
Token surprised
Token ID6655
Feature activation+3.29e-02

Pos logit contributions
ior+0.009
 bank+0.009
load+0.009
 roasted+0.008
bowl+0.008
Neg logit contributions
ily-0.008
lessness-0.008
arl-0.008
less-0.007
aces-0.007
Token but
Token ID475
Feature activation+1.31e-02

Pos logit contributions
 asked+0.038
 forth+0.035
 cub+0.032
 nib+0.031
 called+0.031
Neg logit contributions
arl-0.066
aces-0.065
anger-0.063
anish-0.061
alo-0.060
Token also
Token ID635
Feature activation+1.22e-01

Pos logit contributions
 bank+0.017
 roasted+0.016
load+0.016
ior+0.016
 afloat+0.016
Neg logit contributions
ily-0.021
arl-0.020
lessness-0.020
der-0.019
iness-0.019
Token scared
Token ID12008
Feature activation+5.14e-02

Pos logit contributions
 roasted+0.132
 bank+0.130
load+0.128
 rely+0.128
 afloat+0.127
Neg logit contributions
arl-0.223
anger-0.209
ily-0.209
lessness-0.205
anish-0.204
Token because
Token ID780
Feature activation+1.07e-02

Pos logit contributions
 cub+0.067
 asked+0.063
 Mighty+0.060
 Junior+0.060
 sausage+0.059
Neg logit contributions
arl-0.092
anish-0.086
anger-0.086
aces-0.083
ider-0.082
Token all
Token ID477
Feature activation+3.07e-02

Pos logit contributions
 roasted+0.015
 cub+0.015
 bank+0.015
 forth+0.015
 Junior+0.015
Neg logit contributions
arl-0.017
anger-0.015
anish-0.015
aces-0.015
ily-0.014
Tokenigators
Token ID25975
Feature activation+1.31e-01

Pos logit contributions
 bank+0.051
 roasted+0.051
load+0.050
 afloat+0.050
 rely+0.050
Neg logit contributions
arl-0.036
ily-0.035
lessness-0.034
anger-0.033
anish-0.033
Token are
Token ID389
Feature activation-3.83e-03

Pos logit contributions
ior+0.202
load+0.198
 roasted+0.193
 pasture+0.191
 bank+0.191
Neg logit contributions
lessness-0.171
ily-0.168
iness-0.162
ed-0.160
der-0.159
Token be
Token ID307
Feature activation+6.57e-03

Pos logit contributions
ily+0.015
arl+0.015
lessness+0.014
anish+0.014
iness+0.014
Neg logit contributions
 roasted-0.011
ior-0.011
bowl-0.011
load-0.011
 bank-0.011
Token seen
Token ID1775
Feature activation-3.81e-02

Pos logit contributions
 bank+0.007
 afloat+0.007
 roasted+0.007
load+0.007
bowl+0.007
Neg logit contributions
arl-0.012
anger-0.011
der-0.011
anish-0.011
ily-0.011
Token.
Token ID13
Feature activation-7.21e-04

Pos logit contributions
arl+0.056
ily+0.049
lessness+0.048
anger+0.048
anish+0.047
Neg logit contributions
 bank-0.058
 cub-0.057
 afloat-0.056
 forth-0.055
 rely-0.055
Token He
Token ID679
Feature activation+1.60e-02

Pos logit contributions
ily+0.001
arl+0.001
lessness+0.001
der+0.001
anger+0.001
Neg logit contributions
 forth-0.001
 afloat-0.001
 roasted-0.001
 rely-0.001
load-0.001
Token was
Token ID373
Feature activation+7.12e-03

Pos logit contributions
load+0.023
 afloat+0.023
 barbecue+0.022
ior+0.022
 rely+0.022
Neg logit contributions
ed-0.022
ily-0.022
der-0.021
lessness-0.020
 words-0.020
Token so
Token ID523
Feature activation+1.06e-01

Pos logit contributions
 bank+0.010
ior+0.010
load+0.010
 roasted+0.009
 rely+0.009
Neg logit contributions
ily-0.010
arl-0.010
lessness-0.010
der-0.010
less-0.009
Token scared
Token ID12008
Feature activation+4.19e-02

Pos logit contributions
 roasted+0.113
 bank+0.112
 afloat+0.112
load+0.111
 rely+0.110
Neg logit contributions
arl-0.185
ily-0.183
anger-0.183
anish-0.180
der-0.180
Token he
Token ID339
Feature activation-1.36e-02

Pos logit contributions
 cub+0.057
 Junior+0.057
 asked+0.055
 Mighty+0.054
 afloat+0.054
Neg logit contributions
anish-0.069
arl-0.066
aces-0.063
anger-0.061
ily-0.060
Token couldn
Token ID3521
Feature activation-4.17e-02

Pos logit contributions
ily+0.022
lessness+0.021
arl+0.021
ed+0.021
der+0.021
Neg logit contributions
load-0.017
 rely-0.016
ior-0.016
 roasted-0.016
bowl-0.016
Token't
Token ID470
Feature activation-8.28e-02

Pos logit contributions
arl+0.032
ily+0.031
lessness+0.030
der+0.028
iness+0.027
Neg logit contributions
 bank-0.086
 roasted-0.085
load-0.085
 rely-0.084
 afloat-0.084
Token move
Token ID1445
Feature activation+1.92e-02

Pos logit contributions
ily+0.134
lessness+0.125
arl+0.124
iness+0.121
der+0.120
Neg logit contributions
ior-0.106
load-0.104
 roasted-0.102
 pasture-0.100
bowl-0.098
Token with
Token ID351
Feature activation-1.93e-02

Pos logit contributions
 cub+0.073
 asked+0.073
 sausage+0.072
 Cub+0.069
 bank+0.069
Neg logit contributions
arl-0.108
lessness-0.098
aces-0.096
anger-0.095
iness-0.093
Token pride
Token ID11293
Feature activation-5.06e-02

Pos logit contributions
anger+0.027
arl+0.026
ider+0.024
anish+0.024
lessness+0.024
Neg logit contributions
 sausage-0.031
 roasted-0.030
 cub-0.030
 rely-0.030
 discuss-0.030
Token,
Token ID11
Feature activation-3.62e-02

Pos logit contributions
arl+0.084
ily+0.082
anish+0.082
anger+0.078
aces+0.077
Neg logit contributions
 Junior-0.064
 cub-0.063
 asked-0.061
 sausage-0.060
 forth-0.059
Token �
Token ID6184
Feature activation-1.20e-02

Pos logit contributions
arl+0.042
ily+0.042
lessness+0.040
anger+0.039
anish+0.039
Neg logit contributions
 bank-0.060
 roasted-0.060
load-0.059
 afloat-0.058
 rely-0.058
Token�
Token ID95
Feature activation-5.22e-03

Pos logit contributions
lessness+0.017
ily+0.017
arl+0.017
iness+0.016
anish+0.016
Neg logit contributions
 bank-0.017
load-0.017
 rely-0.017
 roasted-0.016
 afloat-0.016
Token€
Token ID26391
Feature activation+1.23e-01

Pos logit contributions
arl+0.008
lessness+0.008
ily+0.008
der+0.008
iness+0.007
Neg logit contributions
 bank-0.007
load-0.007
 roasted-0.007
 rely-0.007
ior-0.007
Token�
Token ID129
Feature activation-2.09e-02

Pos logit contributions
 bank+0.152
load+0.151
 roasted+0.151
bowl+0.149
 rely+0.148
Neg logit contributions
arl-0.197
ily-0.193
lessness-0.188
der-0.186
iness-0.182
Token�
Token ID241
Feature activation+1.32e-02

Pos logit contributions
arl+0.033
ily+0.033
lessness+0.032
der+0.031
anger+0.031
Neg logit contributions
 roasted-0.026
 bank-0.026
load-0.025
 afloat-0.025
bowl-0.025
TokenWe
Token ID1135
Feature activation+1.50e-02

Pos logit contributions
 roasted+0.019
 rely+0.018
 bank+0.018
load+0.018
 discuss+0.018
Neg logit contributions
arl-0.019
anger-0.018
lessness-0.018
iness-0.018
aces-0.018
Token made
Token ID925
Feature activation+3.94e-03

Pos logit contributions
 roasted+0.017
 discuss+0.016
 rely+0.016
 bank+0.016
bowl+0.016
Neg logit contributions
arl-0.026
anger-0.025
lessness-0.025
der-0.025
ily-0.025
Token this
Token ID428
Feature activation-3.07e-02

Pos logit contributions
 bank+0.007
 roasted+0.007
load+0.007
 rely+0.007
 afloat+0.007
Neg logit contributions
arl-0.004
ily-0.004
lessness-0.004
der-0.004
anger-0.004
Tokens
Token ID82
Feature activation+7.12e-02

Pos logit contributions
 bank+0.056
load+0.055
bowl+0.055
 roasted+0.054
 afloat+0.053
Neg logit contributions
arl-0.056
der-0.054
ily-0.053
lessness-0.053
ment-0.052
Token like
Token ID588
Feature activation-9.57e-03

Pos logit contributions
 bank+0.094
 rely+0.093
 roasted+0.093
 afloat+0.090
load+0.089
Neg logit contributions
arl-0.112
ily-0.107
lessness-0.105
anger-0.104
anish-0.102
Token this
Token ID428
Feature activation-4.13e-02

Pos logit contributions
arl+0.013
lessness+0.013
iness+0.013
anger+0.013
anish+0.013
Neg logit contributions
 rely-0.014
 roasted-0.014
 sausage-0.014
 Junior-0.014
 asked-0.013
Token,
Token ID11
Feature activation-2.07e-02

Pos logit contributions
arl+0.071
ily+0.067
lessness+0.066
anish+0.064
anger+0.064
Neg logit contributions
 bank-0.051
 rely-0.048
 roasted-0.048
 afloat-0.048
bowl-0.047
Tokenâ
Token ID22940
Feature activation+1.89e-02

Pos logit contributions
arl+0.030
anish+0.029
lessness+0.028
aces+0.028
anger+0.028
Neg logit contributions
 roasted-0.029
 rely-0.028
 bank-0.028
 discuss-0.028
 Junior-0.027
Token€
Token ID26391
Feature activation+1.14e-01

Pos logit contributions
 bank+0.016
 roasted+0.016
load+0.015
 afloat+0.015
 rely+0.015
Neg logit contributions
arl-0.038
ily-0.037
lessness-0.037
anger-0.036
der-0.036
Token she
Token ID673
Feature activation-1.07e-02

Pos logit contributions
 bank+0.118
 rely+0.117
 roasted+0.116
load+0.115
bowl+0.114
Neg logit contributions
arl-0.203
ily-0.200
lessness-0.198
der-0.196
iness-0.195
Token said
Token ID531
Feature activation+6.95e-02

Pos logit contributions
ily+0.017
lessness+0.017
aces+0.016
arl+0.016
ed+0.016
Neg logit contributions
 afloat-0.013
 bank-0.013
load-0.013
 roasted-0.013
ior-0.013
Token.
Token ID13
Feature activation-4.09e-03

Pos logit contributions
 rely+0.087
 asked+0.085
 cub+0.083
 bank+0.083
 feed+0.082
Neg logit contributions
arl-0.107
lessness-0.101
iness-0.096
der-0.093
aces-0.093
Token Mike
Token ID4995
Feature activation+1.69e-02

Pos logit contributions
arl+0.007
ily+0.006
lessness+0.006
der+0.006
anger+0.006
Neg logit contributions
 bank-0.005
 roasted-0.005
load-0.005
 rely-0.005
 afloat-0.005
Token tried
Token ID3088
Feature activation+1.84e-02

Pos logit contributions
 afloat+0.020
 bank+0.020
 roasted+0.020
load+0.019
 rely+0.019
Neg logit contributions
ily-0.028
arl-0.027
lessness-0.027
ed-0.026
der-0.026
Token
Token ID198
Feature activation+2.78e-02

Pos logit contributions
 bank+0.037
 roasted+0.037
load+0.036
 rely+0.036
ior+0.036
Neg logit contributions
arl-0.046
lessness-0.045
ily-0.045
iness-0.043
anger-0.043
Token
Token ID198
Feature activation+2.27e-02

Pos logit contributions
 bank+0.039
 afloat+0.039
 forth+0.039
 roasted+0.038
load+0.037
Neg logit contributions
ily-0.042
arl-0.041
lessness-0.038
anger-0.037
anish-0.037
TokenP
Token ID47
Feature activation+6.06e-03

Pos logit contributions
 bank+0.033
 roasted+0.032
load+0.032
 afloat+0.032
 rely+0.031
Neg logit contributions
arl-0.032
ily-0.032
lessness-0.031
der-0.029
anger-0.029
Tokenolly
Token ID5098
Feature activation+7.39e-02

Pos logit contributions
 rely+0.010
load+0.010
 bank+0.009
ior+0.009
bowl+0.009
Neg logit contributions
lessness-0.007
arl-0.007
der-0.007
iness-0.007
ily-0.007
Token was
Token ID373
Feature activation+4.67e-03

Pos logit contributions
 bank+0.069
 roasted+0.067
load+0.065
 rely+0.064
 discuss+0.063
Neg logit contributions
arl-0.146
lessness-0.140
ily-0.140
anger-0.135
iness-0.134
Token so
Token ID523
Feature activation+1.00e-01

Pos logit contributions
 bank+0.006
load+0.006
ior+0.006
 roasted+0.006
 afloat+0.006
Neg logit contributions
ily-0.007
arl-0.007
lessness-0.007
der-0.006
aces-0.006
Token excited
Token ID6568
Feature activation-2.01e-02

Pos logit contributions
 bank+0.118
 roasted+0.117
load+0.115
 rely+0.114
 afloat+0.114
Neg logit contributions
arl-0.167
ily-0.164
lessness-0.161
der-0.156
anger-0.156
Token,
Token ID11
Feature activation-3.65e-02

Pos logit contributions
arl+0.036
anish+0.031
lessness+0.030
aces+0.029
ily+0.029
Neg logit contributions
 asked-0.027
 bank-0.025
 forth-0.025
 called-0.025
 sausage-0.024
Token she
Token ID673
Feature activation-1.75e-02

Pos logit contributions
arl+0.045
anger+0.042
anish+0.041
ily+0.040
lessness+0.040
Neg logit contributions
 bank-0.061
 sausage-0.060
 forth-0.060
 roasted-0.059
 pasture-0.059
Token pract
Token ID1970
Feature activation-2.46e-02

Pos logit contributions
ily+0.030
lessness+0.029
arl+0.029
der+0.028
ed+0.028
Neg logit contributions
 afloat-0.020
ior-0.019
 bank-0.019
 roasted-0.019
load-0.019
Tokenised
Token ID1417
Feature activation+2.27e-02

Pos logit contributions
arl+0.040
anger+0.038
ily+0.037
lessness+0.037
less+0.036
Neg logit contributions
load-0.031
 bank-0.031
 rely-0.031
ior-0.031
 forth-0.031
Token,
Token ID11
Feature activation+1.70e-02

Pos logit contributions
arl+0.022
ily+0.022
lessness+0.021
der+0.020
anger+0.020
Neg logit contributions
 bank-0.040
 roasted-0.040
load-0.039
 afloat-0.039
 rely-0.039
Token it
Token ID340
Feature activation+1.67e-02

Pos logit contributions
 sausage+0.021
 forth+0.021
 feed+0.021
 bank+0.020
 discuss+0.020
Neg logit contributions
arl-0.028
joy-0.027
ative-0.027
lessness-0.026
overed-0.026
Token's
Token ID338
Feature activation+1.08e-01

Pos logit contributions
 roasted+0.016
 afloat+0.015
 pasture+0.015
 bank+0.015
ior+0.015
Neg logit contributions
ily-0.032
arl-0.031
ed-0.031
anish-0.031
aces-0.031
Token mine
Token ID6164
Feature activation+2.28e-03

Pos logit contributions
 roasted+0.184
 bank+0.184
bowl+0.183
load+0.181
 pasture+0.181
Neg logit contributions
ily-0.123
arl-0.121
aces-0.111
less-0.111
lessness-0.109
Token,
Token ID11
Feature activation+1.89e-02

Pos logit contributions
 forth+0.002
load+0.002
 bank+0.002
 afloat+0.002
 rely+0.002
Neg logit contributions
arl-0.005
lessness-0.004
joy-0.004
anish-0.004
iness-0.004
Token I
Token ID314
Feature activation+1.80e-02

Pos logit contributions
 sausage+0.024
 forth+0.022
 barbecue+0.022
 bank+0.022
 feed+0.022
Neg logit contributions
arl-0.031
ative-0.030
joy-0.030
ment-0.030
lessness-0.029
Token saw
Token ID2497
Feature activation-3.25e-02

Pos logit contributions
 pasture+0.026
ior+0.026
 afloat+0.025
 bank+0.025
 roasted+0.025
Neg logit contributions
ily-0.026
arl-0.026
less-0.025
t-0.024
lessness-0.024
Token it
Token ID340
Feature activation-3.53e-03

Pos logit contributions
arl+0.047
lessness+0.045
iness+0.042
anish+0.041
anger+0.041
Neg logit contributions
 bank-0.048
load-0.047
 forth-0.047
 roasted-0.046
 sausage-0.045
Token first
Token ID717
Feature activation+6.64e-02

Pos logit contributions
arl+0.005
lessness+0.005
ily+0.005
anish+0.004
der+0.004
Neg logit contributions
 bank-0.005
load-0.005
 roasted-0.005
 rely-0.005
 afloat-0.005
Token!"
Token ID2474
Feature activation-1.80e-02

Pos logit contributions
 bank+0.087
load+0.084
 rely+0.083
 roasted+0.083
 afloat+0.083
Neg logit contributions
arl-0.103
lessness-0.100
ily-0.099
der-0.095
anger-0.095
Token Sam
Token ID3409
Feature activation-6.42e-02

Pos logit contributions
arl+0.022
ily+0.021
lessness+0.021
der+0.020
iness+0.020
Neg logit contributions
 bank-0.030
 roasted-0.029
load-0.029
 discuss-0.029
 rely-0.029
Token,"
Token ID553
Feature activation+1.90e-02

Pos logit contributions
 roasted+0.092
 bank+0.092
load+0.091
 afloat+0.090
 rely+0.090
Neg logit contributions
arl-0.102
ily-0.101
lessness-0.099
der-0.096
anger-0.095
Token her
Token ID607
Feature activation-5.16e-02

Pos logit contributions
 afloat+0.046
load+0.044
 roasted+0.044
 bank+0.044
 pasture+0.044
Neg logit contributions
ily-0.011
lessness-0.007
arl-0.007
anish-0.007
 words-0.007
Token mom
Token ID1995
Feature activation-3.20e-02

Pos logit contributions
arl+0.074
ily+0.073
lessness+0.071
der+0.068
anger+0.068
Neg logit contributions
 bank-0.073
 roasted-0.073
load-0.072
 afloat-0.071
 rely-0.071
Token replied
Token ID8712
Feature activation+2.70e-02

Pos logit contributions
ily+0.056
ed+0.052
lessness+0.050
fully+0.049
der+0.048
Neg logit contributions
 afloat-0.041
 pasture-0.040
 bank-0.039
 roasted-0.039
 barbecue-0.036
Token.
Token ID13
Feature activation-7.44e-03

Pos logit contributions
 bank+0.040
 cub+0.039
 afloat+0.039
 rely+0.038
load+0.038
Neg logit contributions
arl-0.038
anger-0.034
anish-0.034
lessness-0.033
ily-0.033
Token
Token ID198
Feature activation+1.38e-03

Pos logit contributions
arl+0.009
lessness+0.008
ily+0.008
iness+0.008
anger+0.008
Neg logit contributions
 bank-0.013
 roasted-0.012
load-0.012
ior-0.012
 discuss-0.012
Token
Token ID198
Feature activation-1.36e-04

Pos logit contributions
 afloat+0.002
 bank+0.002
 roasted+0.002
 rely+0.002
 forth+0.002
Neg logit contributions
ily-0.002
arl-0.002
lessness-0.002
anger-0.002
anish-0.002
TokenL
Token ID43
Feature activation-1.18e-01

Pos logit contributions
arl+0.000
ily+0.000
lessness+0.000
anger+0.000
der+0.000
Neg logit contributions
 bank-0.000
load-0.000
 roasted-0.000
ior-0.000
 afloat-0.000
Tokenily
Token ID813
Feature activation-1.61e-02

Pos logit contributions
joy+0.102
arl+0.083
less+0.081
lessness+0.077
stretched+0.074
Neg logit contributions
ackers-0.216
bowl-0.213
dy-0.210
 asked-0.209
ior-0.207
Token didn
Token ID1422
Feature activation-1.04e-01

Pos logit contributions
ily+0.025
ed+0.024
der+0.024
lessness+0.023
anish+0.023
Neg logit contributions
 afloat-0.021
 rely-0.020
load-0.020
 roasted-0.020
 bank-0.020
Token't
Token ID470
Feature activation-8.79e-02

Pos logit contributions
lessness+0.096
arl+0.094
iness+0.089
ily+0.089
aces+0.086
Neg logit contributions
 bank-0.197
load-0.196
 roasted-0.196
 rely-0.194
 discuss-0.194
Token Lily
Token ID20037
Feature activation-3.79e-02

Pos logit contributions
 bank+0.010
 roasted+0.010
ior+0.010
load+0.010
 discuss+0.010
Neg logit contributions
arl-0.012
ily-0.012
lessness-0.012
iness-0.011
anger-0.011
Token smiled
Token ID13541
Feature activation-5.66e-02

Pos logit contributions
ily+0.051
ed+0.049
der+0.047
aces+0.045
 words+0.044
Neg logit contributions
 afloat-0.061
load-0.057
 rely-0.056
 pasture-0.056
 bank-0.055
Token and
Token ID290
Feature activation-2.09e-02

Pos logit contributions
anger+0.085
arl+0.085
anish+0.082
ily+0.080
aces+0.079
Neg logit contributions
 cub-0.078
 afloat-0.078
 sausage-0.077
 forth-0.075
 asked-0.075
Token said
Token ID531
Feature activation+6.37e-02

Pos logit contributions
ed+0.033
ily+0.032
der+0.029
 herself+0.028
ment+0.028
Neg logit contributions
 afloat-0.030
load-0.030
 bank-0.030
 pasture-0.029
oc-0.029
Token,
Token ID11
Feature activation-2.99e-02

Pos logit contributions
 asked+0.063
 sausage+0.062
 grilled+0.061
 forth+0.059
 feed+0.059
Neg logit contributions
arl-0.113
anger-0.106
angs-0.104
lessness-0.103
aces-0.101
Token "
Token ID366
Feature activation+9.12e-03

Pos logit contributions
arl+0.032
ily+0.031
lessness+0.030
anger+0.029
der+0.029
Neg logit contributions
 bank-0.053
 roasted-0.052
load-0.052
 afloat-0.051
 rely-0.051
TokenI
Token ID40
Feature activation+3.60e-02

Pos logit contributions
 roasted+0.012
 bank+0.012
load+0.012
 rely+0.012
ior+0.012
Neg logit contributions
arl-0.014
ily-0.013
lessness-0.013
anger-0.013
der-0.013
Token know
Token ID760
Feature activation+3.68e-02

Pos logit contributions
 bank+0.051
 afloat+0.050
load+0.050
ior+0.050
 roasted+0.049
Neg logit contributions
ily-0.051
arl-0.050
lessness-0.050
less-0.047
der-0.047
Token,
Token ID11
Feature activation-1.18e-03

Pos logit contributions
 forth+0.049
 rely+0.049
 roasted+0.048
 discuss+0.048
 cub+0.048
Neg logit contributions
arl-0.057
lessness-0.053
anger-0.053
iness-0.050
ily-0.050
Token my
Token ID616
Feature activation-1.56e-02

Pos logit contributions
arl+0.002
ily+0.002
lessness+0.002
anger+0.002
der+0.002
Neg logit contributions
 roasted-0.002
 bank-0.002
 rely-0.002
 discuss-0.002
load-0.002
Token grandma
Token ID49890
Feature activation-2.86e-02

Pos logit contributions
arl+0.023
ily+0.023
lessness+0.022
der+0.021
anger+0.021
Neg logit contributions
 bank-0.021
 roasted-0.021
load-0.021
 rely-0.021
 afloat-0.020
Token kept
Token ID4030
Feature activation+4.46e-02

Pos logit contributions
 roasted+0.016
 bank+0.015
 forth+0.015
 rely+0.015
 discuss+0.015
Neg logit contributions
arl-0.031
anger-0.029
ily-0.029
lessness-0.029
anish-0.029
Token on
Token ID319
Feature activation+3.12e-02

Pos logit contributions
 bank+0.061
 roasted+0.060
 afloat+0.060
 rely+0.059
 forth+0.059
Neg logit contributions
arl-0.066
ily-0.065
lessness-0.064
anger-0.063
der-0.062
Token playing
Token ID2712
Feature activation+3.31e-02

Pos logit contributions
 bank+0.039
 roasted+0.037
 afloat+0.037
 rely+0.037
 forth+0.036
Neg logit contributions
arl-0.054
ily-0.052
lessness-0.052
anger-0.051
iness-0.050
Token.
Token ID13
Feature activation-2.79e-03

Pos logit contributions
 bank+0.050
 afloat+0.046
 forth+0.046
bowl+0.045
oc+0.044
Neg logit contributions
arl-0.053
lessness-0.045
iness-0.045
anger-0.044
itted-0.044
Token
Token ID198
Feature activation+1.14e-02

Pos logit contributions
ily+0.004
arl+0.004
lessness+0.004
der+0.004
aces+0.004
Neg logit contributions
 bank-0.004
 afloat-0.004
 roasted-0.004
load-0.004
 forth-0.004
Token
Token ID198
Feature activation+1.04e-02

Pos logit contributions
 bank+0.016
 roasted+0.015
 afloat+0.015
 forth+0.015
ior+0.015
Neg logit contributions
ily-0.018
arl-0.017
lessness-0.016
anish-0.015
anger-0.015
TokenThe
Token ID464
Feature activation-1.09e-03

Pos logit contributions
 bank+0.014
 roasted+0.014
load+0.014
 rely+0.014
 afloat+0.014
Neg logit contributions
arl-0.015
ily-0.015
lessness-0.015
der-0.014
anger-0.014
Token little
Token ID1310
Feature activation+5.72e-02

Pos logit contributions
arl+0.002
ily+0.002
lessness+0.002
der+0.002
iness+0.002
Neg logit contributions
load-0.001
 roasted-0.001
 bank-0.001
bowl-0.001
 afloat-0.001
Token girl
Token ID2576
Feature activation+4.57e-02

Pos logit contributions
 bank+0.069
 forth+0.067
 afloat+0.066
ior+0.065
 discuss+0.065
Neg logit contributions
arl-0.096
ily-0.093
lessness-0.092
anger-0.090
der-0.089
Token and
Token ID290
Feature activation+1.07e-03

Pos logit contributions
 afloat+0.058
load+0.057
ior+0.056
 rely+0.054
 bank+0.054
Neg logit contributions
ily-0.072
ed-0.068
der-0.067
lessness-0.067
aces-0.066
Token the
Token ID262
Feature activation+2.30e-02

Pos logit contributions
 bank+0.002
 roasted+0.002
load+0.002
 afloat+0.002
 rely+0.002
Neg logit contributions
ily-0.001
arl-0.001
lessness-0.001
der-0.001
anish-0.001
Token her
Token ID607
Feature activation-7.05e-02

Pos logit contributions
 bank+0.039
 roasted+0.038
load+0.038
 afloat+0.038
 rely+0.038
Neg logit contributions
arl-0.033
ily-0.033
lessness-0.032
der-0.031
anger-0.031
Token butterfly
Token ID35113
Feature activation-3.43e-02

Pos logit contributions
arl+0.119
lessness+0.116
ily+0.112
der+0.110
anish+0.106
Neg logit contributions
 bank-0.086
 discuss-0.086
 rely-0.086
 forth-0.085
 feed-0.084
Token,
Token ID11
Feature activation-3.18e-02

Pos logit contributions
arl+0.050
ily+0.047
lessness+0.046
anger+0.044
der+0.044
Neg logit contributions
 bank-0.051
 afloat-0.050
 rely-0.050
 forth-0.049
 roasted-0.048
Token but
Token ID475
Feature activation+1.88e-02

Pos logit contributions
arl+0.052
anger+0.049
anish+0.047
ily+0.046
aces+0.045
Neg logit contributions
 forth-0.042
 rely-0.042
 bank-0.041
 roasted-0.041
 asked-0.041
Token at
Token ID379
Feature activation-2.99e-02

Pos logit contributions
 rely+0.032
 forth+0.031
 bank+0.031
 asked+0.031
 roasted+0.031
Neg logit contributions
arl-0.024
anger-0.021
aces-0.020
anish-0.020
ily-0.020
Token least
Token ID1551
Feature activation+2.08e-02

Pos logit contributions
arl+0.052
ily+0.051
lessness+0.051
der+0.049
anger+0.049
Neg logit contributions
 bank-0.033
 roasted-0.032
load-0.032
 afloat-0.032
 rely-0.031
Token she
Token ID673
Feature activation-2.80e-02

Pos logit contributions
 rely+0.036
 bank+0.035
 discuss+0.034
 roasted+0.034
 asked+0.034
Neg logit contributions
arl-0.025
lessness-0.023
anish-0.022
anger-0.022
iness-0.021
Token had
Token ID550
Feature activation-1.74e-02

Pos logit contributions
ily+0.045
lessness+0.043
der+0.043
ed+0.042
iness+0.042
Neg logit contributions
 afloat-0.034
load-0.034
ior-0.033
 roasted-0.033
 bank-0.033
Token a
Token ID257
Feature activation-9.91e-03

Pos logit contributions
arl+0.023
lessness+0.021
anger+0.021
iness+0.020
ily+0.019
Neg logit contributions
 bank-0.029
 rely-0.029
 roasted-0.028
 discuss-0.028
 asked-0.028
Token fun
Token ID1257
Feature activation-5.28e-02

Pos logit contributions
arl+0.015
ily+0.014
lessness+0.014
less+0.014
joy+0.013
Neg logit contributions
load-0.013
ior-0.013
 roasted-0.013
 bank-0.013
 afloat-0.013
Token story
Token ID1621
Feature activation-1.11e-01

Pos logit contributions
arl+0.092
ily+0.089
lessness+0.089
aces+0.085
der+0.085
Neg logit contributions
 bank-0.060
 rely-0.059
 roasted-0.058
 afloat-0.057
bowl-0.056
Token all
Token ID477
Feature activation+3.08e-02

Pos logit contributions
 rely+0.106
load+0.105
 afloat+0.105
 roasted+0.105
ior+0.104
Neg logit contributions
ily-0.067
arl-0.066
der-0.061
aces-0.059
anish-0.058
Token your
Token ID534
Feature activation-4.06e-02

Pos logit contributions
 bank+0.051
 roasted+0.050
load+0.050
 rely+0.049
ior+0.049
Neg logit contributions
arl-0.037
ily-0.036
lessness-0.035
anger-0.034
der-0.034
Token dinner
Token ID8073
Feature activation+3.61e-02

Pos logit contributions
ily+0.056
arl+0.055
aces+0.053
 words+0.052
lessness+0.052
Neg logit contributions
 afloat-0.059
load-0.058
 roasted-0.057
 bank-0.056
 rely-0.056
Token,
Token ID11
Feature activation+1.46e-04

Pos logit contributions
 bank+0.061
 roasted+0.060
load+0.059
 rely+0.059
 afloat+0.059
Neg logit contributions
arl-0.041
ily-0.041
lessness-0.040
der-0.038
anger-0.037
Token I
Token ID314
Feature activation+3.76e-03

Pos logit contributions
 bank+0.000
 roasted+0.000
load+0.000
 afloat+0.000
 rely+0.000
Neg logit contributions
arl-0.000
ily-0.000
lessness-0.000
der-0.000
anger-0.000
Token will
Token ID481
Feature activation-1.18e-02

Pos logit contributions
 forth+0.006
 afloat+0.006
ior+0.006
 pasture+0.005
load+0.005
Neg logit contributions
ily-0.005
less-0.005
arl-0.005
t-0.005
lessness-0.005
Token give
Token ID1577
Feature activation+3.14e-02

Pos logit contributions
arl+0.019
ily+0.019
anish+0.018
der+0.017
 herself+0.017
Neg logit contributions
ior-0.014
 afloat-0.014
 forth-0.013
load-0.013
bowl-0.013
Token you
Token ID345
Feature activation-4.90e-02

Pos logit contributions
 bank+0.053
 roasted+0.053
load+0.052
ior+0.052
 rely+0.051
Neg logit contributions
arl-0.036
lessness-0.035
ily-0.034
der-0.033
anger-0.033
Token a
Token ID257
Feature activation+3.28e-02

Pos logit contributions
arl+0.063
lessness+0.061
anger+0.060
iness+0.056
ily+0.056
Neg logit contributions
 roasted-0.081
 bank-0.080
 sausage-0.079
 feed-0.078
load-0.078
Token special
Token ID2041
Feature activation-2.26e-02

Pos logit contributions
 forth+0.053
 afloat+0.052
ior+0.051
 bank+0.049
load+0.049
Neg logit contributions
less-0.045
arl-0.043
 words-0.040
ily-0.039
anger-0.039
Token reward
Token ID6721
Feature activation-3.90e-02

Pos logit contributions
arl+0.041
ily+0.041
lessness+0.040
anger+0.039
der+0.039
Neg logit contributions
 bank-0.022
 roasted-0.022
load-0.022
 afloat-0.022
ior-0.021
Token have
Token ID423
Feature activation-1.39e-02

Pos logit contributions
ily+0.032
lessness+0.030
arl+0.030
less+0.029
iness+0.029
Neg logit contributions
 bank-0.027
load-0.027
 afloat-0.026
ior-0.026
 roasted-0.025
Token him
Token ID683
Feature activation-5.21e-02

Pos logit contributions
arl+0.018
lessness+0.017
anger+0.017
ily+0.016
iness+0.016
Neg logit contributions
 bank-0.023
 roasted-0.023
 rely-0.022
 discuss-0.022
 sausage-0.022
Token with
Token ID351
Feature activation-3.07e-02

Pos logit contributions
arl+0.060
lessness+0.056
ily+0.056
anger+0.055
der+0.053
Neg logit contributions
 bank-0.090
 rely-0.088
 roasted-0.088
load-0.087
 discuss-0.086
Token her
Token ID607
Feature activation-5.43e-02

Pos logit contributions
arl+0.049
lessness+0.048
anger+0.048
overed+0.046
anish+0.046
Neg logit contributions
 bank-0.040
 sausage-0.039
 Junior-0.039
 cub-0.038
ior-0.038
Token on
Token ID319
Feature activation+7.26e-03

Pos logit contributions
arl+0.073
ily+0.071
lessness+0.069
anger+0.066
der+0.066
Neg logit contributions
 bank-0.084
 rely-0.082
 roasted-0.080
 cub-0.080
 afloat-0.079
Token their
Token ID511
Feature activation-3.09e-02

Pos logit contributions
 bank+0.010
 pasture+0.009
 farm+0.009
 sausage+0.009
 asked+0.009
Neg logit contributions
lessness-0.013
arl-0.012
ed-0.012
ily-0.012
iness-0.012
Token trip
Token ID5296
Feature activation-6.13e-02

Pos logit contributions
arl+0.047
ily+0.046
lessness+0.045
der+0.044
anger+0.043
Neg logit contributions
 bank-0.041
 roasted-0.040
load-0.040
 afloat-0.039
 rely-0.039
Token.
Token ID13
Feature activation-5.68e-03

Pos logit contributions
arl+0.088
anish+0.081
ily+0.081
lessness+0.079
der+0.079
Neg logit contributions
 bank-0.094
load-0.087
 rely-0.084
 afloat-0.082
 asked-0.082
Token<|endoftext|>
Token ID50256
Feature activation-2.57e-02

Pos logit contributions
arl+0.007
ily+0.007
lessness+0.007
der+0.006
anish+0.006
Neg logit contributions
 bank-0.009
 afloat-0.009
 roasted-0.009
 forth-0.009
load-0.009
TokenOnce
Token ID7454
Feature activation-2.46e-02

Pos logit contributions
ily+0.040
arl+0.039
lessness+0.038
anish+0.036
anger+0.036
Neg logit contributions
 bank-0.034
 roasted-0.033
load-0.032
 afloat-0.032
ior-0.032
Token upon
Token ID2402
Feature activation-1.14e-01

Pos logit contributions
arl+0.024
der+0.024
anish+0.024
aces+0.023
anger+0.022
Neg logit contributions
bowl-0.043
 roasted-0.043
 afloat-0.042
 cub-0.042
 asked-0.042
Token together
Token ID1978
Feature activation+4.75e-03

Pos logit contributions
ior+0.004
 rely+0.004
 afloat+0.004
load+0.004
 bank+0.004
Neg logit contributions
ily-0.005
lessness-0.005
ed-0.005
less-0.005
der-0.005
Token they
Token ID484
Feature activation-7.16e-03

Pos logit contributions
 bank+0.007
 roasted+0.006
load+0.006
 afloat+0.006
 rely+0.006
Neg logit contributions
arl-0.007
ily-0.007
lessness-0.007
anger-0.006
der-0.006
Token all
Token ID477
Feature activation+1.43e-02

Pos logit contributions
arl+0.012
ily+0.012
lessness+0.012
der+0.012
anger+0.012
Neg logit contributions
 bank-0.008
 roasted-0.008
load-0.008
 afloat-0.007
 rely-0.007
Token worked
Token ID3111
Feature activation-1.87e-03

Pos logit contributions
 bank+0.015
load+0.015
ior+0.015
 afloat+0.015
 rely+0.015
Neg logit contributions
lessness-0.025
ily-0.025
iness-0.024
arl-0.024
ed-0.024
Token together
Token ID1978
Feature activation-1.29e-02

Pos logit contributions
arl+0.003
ily+0.003
lessness+0.003
anish+0.003
anger+0.003
Neg logit contributions
 bank-0.002
 afloat-0.002
load-0.002
 roasted-0.002
 rely-0.002
Token to
Token ID284
Feature activation-1.69e-02

Pos logit contributions
arl+0.017
ily+0.015
lessness+0.014
anger+0.014
anish+0.014
Neg logit contributions
 bank-0.022
 afloat-0.022
 rely-0.022
 roasted-0.021
bowl-0.021
Token turn
Token ID1210
Feature activation-1.50e-02

Pos logit contributions
ily+0.029
arl+0.029
lessness+0.028
anish+0.028
der+0.027
Neg logit contributions
ior-0.018
 roasted-0.017
bowl-0.016
load-0.016
 forth-0.016
Token it
Token ID340
Feature activation-1.58e-02

Pos logit contributions
arl+0.023
ily+0.022
anish+0.022
anger+0.021
ider+0.021
Neg logit contributions
 afloat-0.022
 bank-0.021
 roasted-0.021
 forth-0.020
 sausage-0.020
Token back
Token ID736
Feature activation+4.07e-02

Pos logit contributions
arl+0.023
ily+0.022
anish+0.022
lessness+0.021
der+0.021
Neg logit contributions
 bank-0.023
 afloat-0.023
 roasted-0.022
 forth-0.022
load-0.022
Token into
Token ID656
Feature activation+5.39e-02

Pos logit contributions
 bank+0.058
 afloat+0.057
 forth+0.057
load+0.054
bowl+0.054
Neg logit contributions
ily-0.061
arl-0.060
anish-0.057
lessness-0.056
iness-0.054
Token a
Token ID257
Feature activation+7.97e-04

Pos logit contributions
 bank+0.090
 roasted+0.089
 afloat+0.088
load+0.088
 rely+0.087
Neg logit contributions
arl-0.065
ily-0.063
lessness-0.061
anger-0.060
aces-0.059
Token ready
Token ID3492
Feature activation+5.53e-02

Pos logit contributions
 bank+0.032
ior+0.032
load+0.032
 roasted+0.031
bowl+0.031
Neg logit contributions
ily-0.039
arl-0.039
lessness-0.039
less-0.037
der-0.036
Token.
Token ID13
Feature activation-8.37e-03

Pos logit contributions
 rely+0.074
 asked+0.073
 roasted+0.073
 bank+0.073
 cooked+0.069
Neg logit contributions
arl-0.088
anish-0.082
ily-0.074
lessness-0.074
anger-0.073
Token
Token ID220
Feature activation+2.02e-03

Pos logit contributions
ily+0.017
arl+0.017
lessness+0.017
anger+0.016
der+0.016
Neg logit contributions
 bank-0.006
 roasted-0.006
load-0.006
 afloat-0.006
 rely-0.006
Token
Token ID198
Feature activation+3.64e-03

Pos logit contributions
 bank+0.002
 roasted+0.002
load+0.002
 rely+0.002
 afloat+0.002
Neg logit contributions
arl-0.003
ily-0.003
lessness-0.003
der-0.003
iness-0.003
Token
Token ID198
Feature activation+1.57e-03

Pos logit contributions
 forth+0.006
 bank+0.006
 afloat+0.006
ior+0.005
 roasted+0.005
Neg logit contributions
ily-0.005
arl-0.005
lessness-0.005
anger-0.004
ed-0.004
TokenAs
Token ID1722
Feature activation-4.56e-02

Pos logit contributions
 bank+0.002
 roasted+0.002
load+0.002
bowl+0.002
 discuss+0.002
Neg logit contributions
arl-0.003
lessness-0.003
iness-0.003
der-0.003
anger-0.003
Token P
Token ID350
Feature activation-5.92e-02

Pos logit contributions
arl+0.049
anish+0.045
lessness+0.045
aces+0.045
ily+0.044
Neg logit contributions
 roasted-0.083
 bank-0.082
 afloat-0.080
 forth-0.079
 rely-0.079
Tokenia
Token ID544
Feature activation-6.79e-02

Pos logit contributions
lessness+0.079
arl+0.067
lessly+0.066
der+0.064
ative+0.064
Neg logit contributions
ior-0.090
 rely-0.090
dy-0.089
 pasture-0.089
bowl-0.088
Token spread
Token ID4104
Feature activation-7.10e-03

Pos logit contributions
ed+0.107
ily+0.101
aces+0.096
anger+0.096
der+0.095
Neg logit contributions
 afloat-0.086
ior-0.083
 rely-0.083
 forth-0.079
itionally-0.078
Token her
Token ID607
Feature activation-7.50e-02

Pos logit contributions
arl+0.012
anish+0.011
der+0.010
ider+0.010
anger+0.009
Neg logit contributions
 bank-0.010
 roasted-0.010
 afloat-0.010
 forth-0.010
 pasture-0.010
Token wings
Token ID12098
Feature activation-6.54e-02

Pos logit contributions
ily+0.131
arl+0.130
der+0.128
lessness+0.126
anish+0.126
Neg logit contributions
 bank-0.091
 cub-0.084
 roasted-0.084
 rely-0.082
 farm-0.082
Token.
Token ID13
Feature activation-1.07e-02

Pos logit contributions
 bank+0.020
bowl+0.019
load+0.019
 afloat+0.018
 roasted+0.018
Neg logit contributions
arl-0.020
anish-0.019
der-0.019
ps-0.018
aces-0.018
Token<|endoftext|>
Token ID50256
Feature activation-1.98e-02

Pos logit contributions
ily+0.016
arl+0.016
lessness+0.016
der+0.015
anish+0.015
Neg logit contributions
 bank-0.014
 afloat-0.014
load-0.014
 roasted-0.014
 forth-0.014
TokenOnce
Token ID7454
Feature activation-2.09e-02

Pos logit contributions
ily+0.030
arl+0.029
lessness+0.028
anish+0.027
anger+0.027
Neg logit contributions
 bank-0.027
 roasted-0.026
load-0.026
ior-0.026
 forth-0.026
Token upon
Token ID2402
Feature activation-1.05e-01

Pos logit contributions
arl+0.019
der+0.019
anish+0.018
lessness+0.018
aces+0.018
Neg logit contributions
 roasted-0.038
bowl-0.037
 bank-0.037
 afloat-0.037
load-0.037
Token a
Token ID257
Feature activation+2.20e-02

Pos logit contributions
arl+0.110
lessness+0.102
anger+0.102
iness+0.098
der+0.098
Neg logit contributions
 roasted-0.193
 discuss-0.188
 bank-0.187
 rely-0.186
load-0.186
Token time
Token ID640
Feature activation-1.25e-02

Pos logit contributions
 bank+0.040
load+0.040
 afloat+0.039
 roasted+0.039
 forth+0.038
Neg logit contributions
ily-0.024
arl-0.024
lessness-0.021
less-0.020
anish-0.020
Token,
Token ID11
Feature activation-3.34e-02

Pos logit contributions
der+0.020
arl+0.019
lessness+0.019
anger+0.018
aces+0.018
Neg logit contributions
 cub-0.015
bowl-0.015
 afloat-0.015
 rely-0.015
oc-0.014
Token in
Token ID287
Feature activation+2.87e-02

Pos logit contributions
arl+0.029
ily+0.029
lessness+0.028
der+0.026
anger+0.025
Neg logit contributions
 bank-0.066
 roasted-0.065
load-0.065
 afloat-0.064
 rely-0.064
Token a
Token ID257
Feature activation-3.61e-03

Pos logit contributions
 roasted+0.046
 cub+0.046
 feed+0.045
 Junior+0.045
 discuss+0.045
Neg logit contributions
arl-0.038
lessness-0.037
iness-0.037
der-0.037
anger-0.036
Token small
Token ID1402
Feature activation-1.38e-02

Pos logit contributions
ily+0.003
arl+0.003
joy+0.003
anish+0.002
lessness+0.002
Neg logit contributions
 afloat-0.007
 rely-0.007
 bank-0.007
ior-0.007
 roasted-0.007
Token house
Token ID2156
Feature activation-6.05e-02

Pos logit contributions
arl+0.019
ily+0.019
lessness+0.018
anish+0.018
joy+0.017
Neg logit contributions
 rely-0.020
 roasted-0.019
 afloat-0.019
load-0.019
 bank-0.018
Token mistake
Token ID7457
Feature activation-3.41e-02

Pos logit contributions
arl+0.057
ily+0.056
lessness+0.056
der+0.053
anger+0.053
Neg logit contributions
 bank-0.050
 roasted-0.048
 rely-0.048
 afloat-0.047
 discuss-0.047
Token."
Token ID526
Feature activation+2.95e-03

Pos logit contributions
arl+0.054
overed+0.053
anger+0.052
joy+0.052
anish+0.051
Neg logit contributions
 cub-0.040
ior-0.040
 asked-0.040
 bank-0.039
oc-0.038
Token
Token ID198
Feature activation+9.88e-04

Pos logit contributions
 forth+0.004
 afloat+0.004
 roasted+0.004
 rely+0.004
load+0.004
Neg logit contributions
ily-0.004
arl-0.004
lessness-0.004
der-0.004
anger-0.004
Token
Token ID198
Feature activation+1.34e-03

Pos logit contributions
 forth+0.002
 bank+0.002
 roasted+0.001
 afloat+0.001
 discuss+0.001
Neg logit contributions
ily-0.001
arl-0.001
lessness-0.001
der-0.001
ment-0.001
TokenGod
Token ID13482
Feature activation-2.51e-03

Pos logit contributions
 roasted+0.002
 bank+0.002
 afloat+0.002
 forth+0.002
 rely+0.002
Neg logit contributions
ily-0.002
arl-0.002
lessness-0.002
der-0.001
anish-0.001
Token heard
Token ID2982
Feature activation-1.11e-01

Pos logit contributions
arl+0.004
ily+0.004
lessness+0.004
anger+0.004
der+0.004
Neg logit contributions
 bank-0.003
 roasted-0.003
load-0.003
 rely-0.003
 afloat-0.003
Token his
Token ID465
Feature activation-6.59e-02

Pos logit contributions
lessness+0.175
arl+0.174
aces+0.170
anish+0.169
iness+0.167
Neg logit contributions
 bank-0.140
 Junior-0.139
 roasted-0.139
 cub-0.139
 sausage-0.137
Token prayer
Token ID11443
Feature activation-2.04e-02

Pos logit contributions
arl+0.070
ily+0.069
lessness+0.066
der+0.065
 words+0.062
Neg logit contributions
 bank-0.117
 roasted-0.117
load-0.116
bowl-0.116
 afloat-0.115
Token and
Token ID290
Feature activation-6.08e-03

Pos logit contributions
ily+0.028
anish+0.028
arl+0.027
anger+0.026
adies+0.026
Neg logit contributions
 bank-0.031
 afloat-0.029
 cub-0.029
 roasted-0.029
load-0.029
Token felt
Token ID2936
Feature activation-9.71e-03

Pos logit contributions
arl+0.011
ily+0.011
lessness+0.011
anger+0.010
aces+0.010
Neg logit contributions
 bank-0.006
 roasted-0.006
load-0.006
 rely-0.006
 afloat-0.006
Token sorry
Token ID7926
Feature activation-8.68e-03

Pos logit contributions
ily+0.012
lessness+0.011
arl+0.011
der+0.011
ed+0.010
Neg logit contributions
ior-0.016
 bank-0.016
load-0.016
 roasted-0.015
 forth-0.015
Token just
Token ID655
Feature activation-1.69e-02

Pos logit contributions
ily+0.044
arl+0.043
lessness+0.042
der+0.041
aces+0.041
Neg logit contributions
 bank-0.025
load-0.025
 roasted-0.025
 afloat-0.025
ior-0.025
Token couldn
Token ID3521
Feature activation-4.59e-02

Pos logit contributions
arl+0.029
ily+0.029
lessness+0.028
anger+0.028
anish+0.027
Neg logit contributions
 bank-0.019
 roasted-0.018
 rely-0.018
load-0.018
 afloat-0.018
Tokenâ
Token ID22940
Feature activation-6.19e-03

Pos logit contributions
arl+0.052
lessness+0.049
ily+0.048
anish+0.045
iness+0.045
Neg logit contributions
 bank-0.081
 rely-0.079
 roasted-0.078
load-0.077
 afloat-0.077
Token€
Token ID26391
Feature activation+8.00e-02

Pos logit contributions
ily+0.011
arl+0.011
lessness+0.011
iness+0.010
aces+0.010
Neg logit contributions
 roasted-0.006
 bank-0.006
load-0.006
bowl-0.006
 afloat-0.006
Tokenâ„¢
Token ID8151
Feature activation-4.33e-03

Pos logit contributions
 bank+0.098
 roasted+0.096
load+0.095
 afloat+0.094
 rely+0.094
Neg logit contributions
arl-0.128
ily-0.127
lessness-0.124
der-0.120
anger-0.120
Tokent
Token ID83
Feature activation-1.17e-01

Pos logit contributions
arl+0.003
ily+0.002
anish+0.002
lessness+0.002
der+0.002
Neg logit contributions
 bank-0.010
 roasted-0.009
load-0.009
bowl-0.009
 afloat-0.009
Token reach
Token ID3151
Feature activation-1.53e-02

Pos logit contributions
arl+0.187
ily+0.179
lessness+0.177
anish+0.175
anger+0.174
Neg logit contributions
 bank-0.149
 rely-0.147
 roasted-0.145
 afloat-0.143
load-0.141
Token it
Token ID340
Feature activation-2.87e-02

Pos logit contributions
arl+0.019
ily+0.018
lessness+0.018
anish+0.018
der+0.017
Neg logit contributions
 bank-0.025
 afloat-0.024
 roasted-0.024
 rely-0.024
load-0.023
Token.
Token ID13
Feature activation-8.61e-04

Pos logit contributions
arl+0.033
ily+0.032
lessness+0.031
anish+0.030
anger+0.029
Neg logit contributions
 bank-0.050
 afloat-0.048
 rely-0.047
 roasted-0.047
bowl-0.047
Token Then
Token ID3244
Feature activation+7.73e-02

Pos logit contributions
ily+0.001
arl+0.001
lessness+0.001
der+0.001
anger+0.001
Neg logit contributions
 roasted-0.001
 forth-0.001
 bank-0.001
 afloat-0.001
load-0.001
Token a
Token ID257
Feature activation-2.29e-03

Pos logit contributions
 bank+0.116
 roasted+0.114
 rely+0.112
 afloat+0.112
load+0.111
Neg logit contributions
arl-0.106
ily-0.102
lessness-0.101
der-0.097
anger-0.096
Token soft
Token ID2705
Feature activation+3.56e-02

Pos logit contributions
arl+0.011
ily+0.011
lessness+0.010
der+0.010
anger+0.010
Neg logit contributions
 bank-0.010
 roasted-0.009
load-0.009
 rely-0.009
 afloat-0.009
Token sweater
Token ID35685
Feature activation-8.23e-03

Pos logit contributions
 bank+0.048
 roasted+0.045
 sausage+0.045
 pasture+0.044
bowl+0.044
Neg logit contributions
arl-0.056
ily-0.054
lessness-0.054
aces-0.050
der-0.050
Token.
Token ID13
Feature activation+4.35e-03

Pos logit contributions
arl+0.012
joy+0.011
lessness+0.011
anish+0.011
ily+0.011
Neg logit contributions
 bank-0.013
 roasted-0.011
 rely-0.011
bowl-0.011
 weighed-0.011
Token And
Token ID843
Feature activation+2.04e-03

Pos logit contributions
 bank+0.007
 afloat+0.007
 roasted+0.007
load+0.007
 rely+0.007
Neg logit contributions
ily-0.006
arl-0.006
lessness-0.005
der-0.005
aces-0.005
Token he
Token ID339
Feature activation+2.00e-02

Pos logit contributions
 bank+0.003
 roasted+0.003
 rely+0.003
load+0.003
 afloat+0.003
Neg logit contributions
arl-0.003
ily-0.003
lessness-0.003
anger-0.003
der-0.003
Token never
Token ID1239
Feature activation-1.14e-01

Pos logit contributions
 bank+0.021
 roasted+0.021
load+0.021
 afloat+0.021
ior+0.020
Neg logit contributions
ily-0.035
arl-0.035
lessness-0.034
der-0.033
anger-0.033
Token opened
Token ID4721
Feature activation-3.00e-03

Pos logit contributions
ily+0.213
arl+0.211
lessness+0.209
der+0.203
iness+0.202
Neg logit contributions
load-0.107
 bank-0.107
 roasted-0.105
 afloat-0.105
ior-0.103
Token the
Token ID262
Feature activation+4.20e-03

Pos logit contributions
arl+0.005
anish+0.005
lessness+0.005
ily+0.005
iness+0.005
Neg logit contributions
 bank-0.004
 afloat-0.004
 Junior-0.004
 sausage-0.004
 cub-0.004
Token zipper
Token ID48992
Feature activation-1.17e-03

Pos logit contributions
 bank+0.005
 pasture+0.005
 sausage+0.005
 forth+0.005
 cub+0.005
Neg logit contributions
ily-0.007
lessness-0.007
iness-0.007
anish-0.007
arl-0.007
Token coat
Token ID13209
Feature activation-9.34e-03

Pos logit contributions
arl+0.002
anish+0.002
ment+0.002
lessness+0.002
ily+0.002
Neg logit contributions
 bank-0.001
 forth-0.001
 afloat-0.001
field-0.001
bowl-0.001
Token's
Token ID338
Feature activation+5.97e-02

Pos logit contributions
arl+0.015
ily+0.014
anish+0.014
lessness+0.014
ment+0.014
Neg logit contributions
 bank-0.013
 forth-0.011
 cub-0.011
 weighed-0.011
 sausage-0.011
Token again
Token ID757
Feature activation-3.42e-02

Pos logit contributions
 bank+0.147
bowl+0.142
 roasted+0.140
 sausage+0.138
 afloat+0.138
Neg logit contributions
arl-0.132
lessness-0.120
ily-0.119
anger-0.116
anish-0.115
Token tomorrow
Token ID9439
Feature activation-4.76e-02

Pos logit contributions
ily+0.029
arl+0.027
der+0.026
lessness+0.026
ment+0.025
Neg logit contributions
 bank-0.067
 afloat-0.066
load-0.066
 roasted-0.066
ior-0.065
Token.
Token ID13
Feature activation-4.90e-03

Pos logit contributions
arl+0.043
ily+0.043
lessness+0.041
der+0.039
anger+0.038
Neg logit contributions
 bank-0.090
 roasted-0.090
 afloat-0.090
load-0.090
 rely-0.089
Token<|endoftext|>
Token ID50256
Feature activation-3.47e-02

Pos logit contributions
ily+0.007
lessness+0.006
arl+0.006
der+0.006
less+0.006
Neg logit contributions
 bank-0.008
 afloat-0.008
 forth-0.008
load-0.008
 rely-0.008
TokenOnce
Token ID7454
Feature activation-2.77e-02

Pos logit contributions
arl+0.057
ily+0.056
lessness+0.055
der+0.053
anger+0.053
Neg logit contributions
 bank-0.042
 roasted-0.041
load-0.040
 afloat-0.040
 rely-0.040
Token upon
Token ID2402
Feature activation-1.06e-01

Pos logit contributions
arl+0.025
der+0.024
aces+0.024
anish+0.024
ily+0.023
Neg logit contributions
 roasted-0.051
bowl-0.051
 bank-0.050
 afloat-0.050
 rely-0.050
Token a
Token ID257
Feature activation+2.92e-02

Pos logit contributions
arl+0.121
anger+0.112
lessness+0.110
iness+0.108
der+0.105
Neg logit contributions
 roasted-0.190
 discuss-0.184
bowl-0.182
 bank-0.182
 rely-0.182
Token time
Token ID640
Feature activation-6.62e-03

Pos logit contributions
 bank+0.051
load+0.050
 afloat+0.049
 roasted+0.049
 forth+0.048
Neg logit contributions
arl-0.034
ily-0.034
lessness-0.030
less-0.029
anish-0.029
Token,
Token ID11
Feature activation-2.48e-02

Pos logit contributions
der+0.011
arl+0.011
lessness+0.011
ps+0.011
aces+0.011
Neg logit contributions
 cub-0.007
bowl-0.007
 afloat-0.007
oc-0.007
 rely-0.007
Token there
Token ID612
Feature activation+1.19e-02

Pos logit contributions
arl+0.023
lessness+0.022
ily+0.021
der+0.021
anger+0.021
Neg logit contributions
 roasted-0.047
 bank-0.046
 afloat-0.046
load-0.046
bowl-0.046
Token was
Token ID373
Feature activation+5.64e-03

Pos logit contributions
ior+0.017
 bank+0.017
 afloat+0.017
load+0.017
 roasted+0.016
Neg logit contributions
ily-0.018
anish-0.016
ed-0.016
lessness-0.016
less-0.016
Token cried
Token ID16896
Feature activation-7.54e-03

Pos logit contributions
ily+0.093
lessness+0.089
ed+0.089
arl+0.087
aces+0.087
Neg logit contributions
 roasted-0.053
 rely-0.052
 afloat-0.051
load-0.051
 bank-0.051
Token.
Token ID13
Feature activation-2.09e-02

Pos logit contributions
anish+0.009
arl+0.009
lessness+0.009
anger+0.009
iness+0.009
Neg logit contributions
 afloat-0.011
 discuss-0.011
 forth-0.011
 bank-0.011
 cub-0.011
Token
Token ID198
Feature activation-5.46e-03

Pos logit contributions
iness+0.039
ier+0.036
less+0.035
lessness+0.035
arl+0.035
Neg logit contributions
 asked-0.022
 discuss-0.020
 feed-0.020
 ask-0.020
 Junior-0.019
Token
Token ID198
Feature activation-5.52e-03

Pos logit contributions
arl+0.008
ily+0.008
lessness+0.008
anger+0.008
der+0.007
Neg logit contributions
 bank-0.008
 roasted-0.007
 afloat-0.007
load-0.007
ior-0.007
TokenBen
Token ID11696
Feature activation-4.10e-02

Pos logit contributions
arl+0.009
lessness+0.009
iness+0.009
der+0.009
aces+0.009
Neg logit contributions
load-0.007
 discuss-0.007
 bank-0.007
 roasted-0.007
 forth-0.006
Token heard
Token ID2982
Feature activation-1.13e-01

Pos logit contributions
arl+0.076
lessness+0.071
iness+0.069
anger+0.069
less+0.068
Neg logit contributions
 bank-0.046
 roasted-0.043
 cub-0.043
load-0.042
 forth-0.042
Token Lily
Token ID20037
Feature activation-6.34e-02

Pos logit contributions
arl+0.175
anish+0.175
aces+0.174
lessness+0.172
less+0.170
Neg logit contributions
 roasted-0.146
 discuss-0.144
 feed-0.141
 sausage-0.140
 Junior-0.139
Token.
Token ID13
Feature activation-2.14e-02

Pos logit contributions
arl+0.108
ily+0.107
lessness+0.105
der+0.102
anger+0.101
Neg logit contributions
 bank-0.071
 roasted-0.070
load-0.069
 afloat-0.068
 rely-0.068
Token He
Token ID679
Feature activation+4.27e-03

Pos logit contributions
arl+0.036
iness+0.036
less+0.035
aces+0.035
anish+0.034
Neg logit contributions
 bank-0.024
 cub-0.024
load-0.023
ior-0.023
bowl-0.023
Token ran
Token ID4966
Feature activation-1.25e-02

Pos logit contributions
 bank+0.005
 roasted+0.005
 afloat+0.005
load+0.005
 rely+0.005
Neg logit contributions
ily-0.007
arl-0.007
lessness-0.007
der-0.007
ed-0.007
Token to
Token ID284
Feature activation-2.17e-02

Pos logit contributions
iness+0.020
anish+0.020
aces+0.019
der+0.019
lessness+0.019
Neg logit contributions
 bank-0.018
 asked-0.017
load-0.017
 ask-0.017
 feed-0.017