TOP ACTIVATIONS
MAX = 8.709

cried , dropping the magn ifying glass . "
examine it with the magn ifying glass ?" "
the watch with the magn ifying glass . He saw the
He pointed his magn ifying glass at different classmates and
Hey , hey , hey ! What is going on here
borrowed her mom 's magn ifying glass to take a closer
and handed him the magn ifying glass . He
, handing him the magn ifying glass . She looked around
said , holding the magn ifying glass over a black ant
the necklace and the magn ifying glass and started to examine
the necklace and the magn ifying glass and told him that
hat and grabbed her magn ifying glass . She was ready
. " Help ! Help !" they scream .
. " Help ! Help ! Someone help Tom
Hey , hey , hey ! What is going on here
He took out a magn ifying glass and a notebook and
. He cries " Help ! Help ! Jen is hurt
. " Help ! Help !" Sam said .
She took out a magn ifying glass and looked very carefully
. " Help ! Help !" Lily and Tom

MIN ACTIVATIONS
MIN = -7.716

and were happy they could design something together . <|endoftext|> Once
loved to play make - bel ieve . Today she was
liked to play make - bel ieve . One
and they played make - bel ieve . Finally , they
. Alice loved how c udd ly and responsive her puppy
, because you have wonderful imag inations ." The boy and
years old and loved to design . Every day he would
He loved playing make - bel ieve with his friends .
imagination . She loved to design things and one day she
of friends and loved to create beautiful things together . <|endoftext|>
to use his imagination to create his own news . <|endoftext|>
red cape and make - bel ieve he had super powers
el cr ay ons to create beautiful pictures . <|endoftext|> Once
things . She wanted to design something new and fun ,
her even more things to design . She brought out some
Lily . She loved to create things with her toys .
things . She liked to create things with her friends and
special . She wanted to design a big , black anchor
always be a team and create amazing things together . The
using his imag inations to create something fun . Joe and

INTERVAL 4.603 - 8.709
CONTAINS 0.253%

to the green toy . " Grab it , Ben !"
OK ?" Sam asked . " You are hurt !"
spraying , a man came up to him and asked ,
opened the door and climbed in . " Wow
is dangerous and not for you . You could have hurt

INTERVAL 0.496 - 4.603
CONTAINS 33.579%

look for another treasure tomorrow , in a different place .
dad 's suit anymore . He only cared about having fun
tree , but I 'm scared ." Her mom said ,
Once upon a time there was a beautiful flower in a
when he heard a noise coming from the forest nearby .

INTERVAL -3.610 - 0.496
CONTAINS 65.198%

was proud of them . She knew they learned a lesson
You have to go to school and learn new things ."
fl apped their wings with all their might and suddenly ,
and it looked like the shape that had passed him by
finally said yes . They went to the garden and the

INTERVAL -7.716 - -3.610
CONTAINS 0.970%

and celebrated every time they made something new .
She realized that sometimes things can seem scary , but they
the yacht and started to play . He felt very comfort
loved to draw and make things . One day , she
wanted to stay home and play . Grand ma
Token cried
Token ID16896
Feature activation+1.67e+00

Pos logit contributions
 trash+0.034
 extingu+0.033
gy+0.032
 bruised+0.032
oc+0.032
Neg logit contributions
isy-0.032
lf-0.031
 performance-0.030
fulness-0.029
 trophy-0.029
Token,
Token ID11
Feature activation+4.15e+00

Pos logit contributions
oc+0.038
 trash+0.036
c+0.035
 dece+0.035
Bad+0.034
Neg logit contributions
isy-0.035
 performance-0.034
lf-0.034
fulness-0.033
is-0.032
Token dropping
Token ID12047
Feature activation+1.85e+00

Pos logit contributions
oc+0.098
 trash+0.097
 extingu+0.094
 dece+0.092
gy+0.092
Neg logit contributions
lf-0.089
isy-0.087
 performance-0.081
 accomplishment-0.075
 trophy-0.075
Token the
Token ID262
Feature activation+1.12e+00

Pos logit contributions
oc+0.051
o+0.048
ric+0.048
gy+0.047
enn+0.047
Neg logit contributions
fulness-0.027
 accomplishment-0.027
 trophy-0.027
 poems-0.027
lf-0.027
Token magn
Token ID7842
Feature activation+2.11e+00

Pos logit contributions
oc+0.025
gy+0.025
 extingu+0.024
o+0.024
 dece+0.023
Neg logit contributions
isy-0.026
lf-0.025
 performance-0.024
 trophy-0.024
is-0.023
Tokenifying
Token ID4035
Feature activation+8.71e+00

Pos logit contributions
 trash+0.018
oc+0.016
 dece+0.016
 extingu+0.015
 bruised+0.015
Neg logit contributions
isy-0.077
lf-0.076
 performance-0.074
fulness-0.073
 trophy-0.072
Token glass
Token ID5405
Feature activation+2.30e+00

Pos logit contributions
cod+0.231
 dece+0.230
lves+0.218
gy+0.218
lich+0.218
Neg logit contributions
 performance-0.148
 trophy-0.143
 prize-0.143
 ceremony-0.134
lf-0.133
Token.
Token ID13
Feature activation+1.80e+00

Pos logit contributions
 dece+0.047
oc+0.047
 trash+0.046
 extingu+0.046
gy+0.046
Neg logit contributions
lf-0.054
isy-0.054
 performance-0.051
 trophy-0.051
fulness-0.049
Token
Token ID198
Feature activation+2.16e+00

Pos logit contributions
 trash+0.040
 extingu+0.039
oc+0.039
 bruised+0.038
gy+0.038
Neg logit contributions
lf-0.040
isy-0.039
 performance-0.038
fulness-0.036
 trophy-0.036
Token
Token ID198
Feature activation+1.75e+00

Pos logit contributions
 extingu+0.046
 bruised+0.046
 trash+0.046
gy+0.044
 dece+0.043
Neg logit contributions
lf-0.052
isy-0.050
ves-0.047
is-0.047
fulness-0.046
Token"
Token ID1
Feature activation+4.12e+00

Pos logit contributions
 extingu+0.047
 bruised+0.046
 trash+0.044
gy+0.044
 dece+0.043
Neg logit contributions
lf-0.036
isy-0.033
is-0.030
ves-0.030
pron-0.028
Token examine
Token ID10716
Feature activation-1.47e+00

Pos logit contributions
 trash+0.014
 extingu+0.014
 bruised+0.014
 dece+0.013
oc+0.013
Neg logit contributions
isy-0.013
lf-0.012
 performance-0.012
 trophy-0.012
is-0.011
Token it
Token ID340
Feature activation+1.51e+00

Pos logit contributions
lf+0.023
isy+0.023
 performance+0.022
 achievement+0.020
 accomplishment+0.020
Neg logit contributions
 trash-0.043
 extingu-0.041
oc-0.041
 bruised-0.041
gy-0.041
Token with
Token ID351
Feature activation+2.83e+00

Pos logit contributions
 trash+0.022
gy+0.022
oc+0.022
 extingu+0.021
o+0.021
Neg logit contributions
isy-0.043
lf-0.043
 performance-0.043
 accomplishment-0.042
 achievement-0.041
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
 extingu+0.066
gy+0.066
oc+0.065
 trash+0.065
 bruised+0.064
Neg logit contributions
isy-0.059
lf-0.059
 performance-0.057
fulness-0.054
 trophy-0.054
Token magn
Token ID7842
Feature activation+9.25e-01

Pos logit contributions
 trash+0.026
 extingu+0.025
 bruised+0.025
gy+0.025
oc+0.024
Neg logit contributions
lf-0.021
isy-0.021
 performance-0.020
fulness-0.018
 trophy-0.018
Tokenifying
Token ID4035
Feature activation+8.02e+00

Pos logit contributions
 extingu+0.005
gy+0.004
 trash+0.004
 bruised+0.004
oc+0.004
Neg logit contributions
lf-0.037
isy-0.036
 performance-0.035
 accomplishment-0.035
 achievement-0.035
Token glass
Token ID5405
Feature activation+1.31e+00

Pos logit contributions
gy+0.208
lves+0.203
cod+0.201
 dece+0.201
lich+0.200
Neg logit contributions
 trophy-0.147
 performance-0.145
 prize-0.143
 medal-0.136
 ceremony-0.136
Token?"
Token ID1701
Feature activation-1.36e+00

Pos logit contributions
 trash+0.024
 extingu+0.023
gy+0.023
 bruised+0.023
oc+0.022
Neg logit contributions
lf-0.034
isy-0.034
 performance-0.033
fulness-0.032
 trophy-0.031
Token
Token ID198
Feature activation+2.21e-01

Pos logit contributions
lf+0.036
isy+0.036
 performance+0.035
is+0.033
 trophy+0.033
Neg logit contributions
 extingu-0.024
 trash-0.024
 bruised-0.023
gy-0.023
oc-0.023
Token
Token ID198
Feature activation-3.74e-01

Pos logit contributions
 extingu+0.005
 trash+0.005
 bruised+0.004
gy+0.004
 dece+0.004
Neg logit contributions
isy-0.005
lf-0.005
is-0.005
fulness-0.005
ves-0.005
Token"
Token ID1
Feature activation+2.44e+00

Pos logit contributions
isy+0.008
lf+0.008
is+0.008
pron+0.007
ves+0.007
Neg logit contributions
 extingu-0.009
 bruised-0.009
 trash-0.008
ric-0.008
 cages-0.008
Token the
Token ID262
Feature activation+1.60e-01

Pos logit contributions
oc+0.014
 extingu+0.014
 trash+0.013
 dece+0.013
 bruised+0.013
Neg logit contributions
lf-0.013
isy-0.013
 performance-0.012
 trophy-0.012
 accomplishment-0.012
Token watch
Token ID2342
Feature activation+6.69e-01

Pos logit contributions
 trash+0.004
 extingu+0.004
 bruised+0.004
oc+0.004
gy+0.004
Neg logit contributions
lf-0.003
isy-0.003
 performance-0.003
fulness-0.003
 trophy-0.003
Token with
Token ID351
Feature activation+2.80e+00

Pos logit contributions
 trash+0.011
 extingu+0.011
gy+0.011
 bruised+0.011
oc+0.011
Neg logit contributions
isy-0.018
lf-0.017
 performance-0.017
 accomplishment-0.017
 achievement-0.016
Token the
Token ID262
Feature activation+1.98e-01

Pos logit contributions
oc+0.058
 extingu+0.056
gy+0.055
o+0.055
 trash+0.055
Neg logit contributions
lf-0.066
 performance-0.065
isy-0.064
 accomplishment-0.063
 trophy-0.062
Token magn
Token ID7842
Feature activation+8.57e-01

Pos logit contributions
 trash+0.005
 extingu+0.005
 bruised+0.005
oc+0.004
 dece+0.004
Neg logit contributions
lf-0.004
isy-0.004
 performance-0.004
fulness-0.004
 trophy-0.004
Tokenifying
Token ID4035
Feature activation+8.01e+00

Pos logit contributions
 extingu+0.004
 trash+0.004
gy+0.003
 bruised+0.003
o+0.003
Neg logit contributions
lf-0.035
isy-0.034
 performance-0.033
 accomplishment-0.033
 achievement-0.033
Token glass
Token ID5405
Feature activation+9.85e-01

Pos logit contributions
 dece+0.198
gy+0.197
cod+0.194
lves+0.194
ety+0.190
Neg logit contributions
 trophy-0.152
 performance-0.151
 prize-0.145
 ceremony-0.142
 medal-0.138
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
 trash+0.018
 extingu+0.017
 bruised+0.017
gy+0.017
oc+0.016
Neg logit contributions
lf-0.026
isy-0.026
 performance-0.025
fulness-0.024
is-0.024
Token He
Token ID679
Feature activation+8.60e-01

Pos logit contributions
 extingu+0.008
 trash+0.008
oc+0.008
 bruised+0.008
gy+0.008
Neg logit contributions
lf-0.009
isy-0.009
 performance-0.009
 trophy-0.009
fulness-0.008
Token saw
Token ID2497
Feature activation+4.42e-01

Pos logit contributions
 extingu+0.016
 trash+0.014
gy+0.014
 bruised+0.014
oc+0.014
Neg logit contributions
lf-0.025
isy-0.024
 performance-0.022
is-0.022
pron-0.021
Token the
Token ID262
Feature activation+4.70e-01

Pos logit contributions
oc+0.010
 extingu+0.010
gy+0.010
 hyd+0.009
enn+0.009
Neg logit contributions
lf-0.010
isy-0.010
 trophy-0.009
 performance-0.009
 medal-0.009
Token
Token ID198
Feature activation+3.01e-01

Pos logit contributions
 trash+0.010
 bruised+0.010
 extingu+0.010
gy+0.009
 hyd+0.009
Neg logit contributions
lf-0.015
isy-0.014
 performance-0.013
is-0.013
fulness-0.013
TokenHe
Token ID1544
Feature activation+7.26e-01

Pos logit contributions
 bruised+0.008
 trash+0.008
 extingu+0.008
 hyd+0.007
gy+0.007
Neg logit contributions
lf-0.007
isy-0.006
ves-0.005
is-0.005
 performance-0.005
Token pointed
Token ID6235
Feature activation+1.06e+00

Pos logit contributions
 trash+0.015
 extingu+0.014
 bruised+0.014
gy+0.014
oc+0.014
Neg logit contributions
lf-0.018
isy-0.018
 performance-0.017
 trophy-0.016
is-0.016
Token his
Token ID465
Feature activation+8.69e-01

Pos logit contributions
 trash+0.021
 extingu+0.020
 bruised+0.020
gy+0.020
oc+0.020
Neg logit contributions
lf-0.027
isy-0.027
 performance-0.026
fulness-0.024
is-0.024
Token magn
Token ID7842
Feature activation+1.56e+00

Pos logit contributions
 extingu+0.020
gy+0.019
 trash+0.019
oc+0.019
 bruised+0.019
Neg logit contributions
isy-0.019
lf-0.019
 performance-0.019
 trophy-0.018
pron-0.017
Tokenifying
Token ID4035
Feature activation+7.99e+00

Pos logit contributions
 trash+0.009
 extingu+0.009
gy+0.008
 bruised+0.008
oc+0.008
Neg logit contributions
lf-0.060
isy-0.060
 performance-0.059
fulness-0.057
 trophy-0.057
Token glass
Token ID5405
Feature activation+1.24e+00

Pos logit contributions
gy+0.193
cod+0.192
 dece+0.191
Bad+0.189
lves+0.183
Neg logit contributions
 trophy-0.158
 performance-0.154
 medal-0.147
 prize-0.146
 ceremony-0.141
Token at
Token ID379
Feature activation+1.28e+00

Pos logit contributions
 trash+0.023
 extingu+0.023
gy+0.022
 bruised+0.022
oc+0.022
Neg logit contributions
lf-0.032
isy-0.032
 performance-0.031
fulness-0.029
 trophy-0.029
Token different
Token ID1180
Feature activation+9.10e-02

Pos logit contributions
 trash+0.029
 extingu+0.029
 bruised+0.028
oc+0.028
 dece+0.028
Neg logit contributions
lf-0.028
isy-0.027
 performance-0.026
fulness-0.026
 trophy-0.025
Token classmates
Token ID28999
Feature activation+1.75e-01

Pos logit contributions
 extingu+0.002
 trash+0.002
gy+0.002
 bruised+0.002
oc+0.002
Neg logit contributions
lf-0.002
isy-0.002
 performance-0.002
 trophy-0.001
is-0.001
Token and
Token ID290
Feature activation+3.02e-01

Pos logit contributions
 trash+0.002
oc+0.002
 extingu+0.002
gy+0.002
 bruised+0.002
Neg logit contributions
isy-0.005
lf-0.005
 performance-0.005
pron-0.005
 accomplishment-0.005
TokenHey
Token ID10814
Feature activation+3.33e+00

Pos logit contributions
gy+0.093
oc+0.090
 bruised+0.087
 extingu+0.085
fired+0.084
Neg logit contributions
lf-0.115
isy-0.111
is-0.109
 performance-0.104
 couple-0.103
Token,
Token ID11
Feature activation+4.13e+00

Pos logit contributions
 extingu+0.071
gy+0.071
 trash+0.071
oc+0.070
 bruised+0.069
Neg logit contributions
lf-0.076
isy-0.075
 performance-0.072
 trophy-0.069
is-0.067
Token hey
Token ID17207
Feature activation+4.57e+00

Pos logit contributions
oc+0.102
gy+0.101
c+0.098
 extingu+0.097
 dece+0.096
Neg logit contributions
isy-0.084
lf-0.082
 performance-0.080
 trophy-0.077
fulness-0.074
Token,
Token ID11
Feature activation+5.03e+00

Pos logit contributions
 trash+0.099
gy+0.099
 extingu+0.099
 bruised+0.098
oc+0.095
Neg logit contributions
lf-0.106
isy-0.103
 performance-0.097
is-0.094
fulness-0.091
Token hey
Token ID17207
Feature activation+4.18e+00

Pos logit contributions
oc+0.117
c+0.114
gy+0.114
o+0.107
 bruised+0.106
Neg logit contributions
isy-0.109
 performance-0.108
lf-0.108
 trophy-0.105
 accomplishment-0.098
Token!
Token ID0
Feature activation+7.98e+00

Pos logit contributions
 extingu+0.089
gy+0.089
 bruised+0.088
 trash+0.088
oc+0.085
Neg logit contributions
lf-0.098
isy-0.096
 performance-0.091
is-0.087
fulness-0.085
Token What
Token ID1867
Feature activation+4.54e+00

Pos logit contributions
 dece+0.153
 extingu+0.147
 bruised+0.144
 trash+0.143
gy+0.143
Neg logit contributions
lf-0.189
 performance-0.189
 trophy-0.175
ner-0.170
 wedding-0.163
Token is
Token ID318
Feature activation+1.74e+00

Pos logit contributions
 extingu+0.080
gy+0.080
 bruised+0.078
oc+0.077
 trash+0.075
Neg logit contributions
lf-0.124
isy-0.117
 performance-0.117
 trophy-0.115
fulness-0.110
Token going
Token ID1016
Feature activation+2.06e+00

Pos logit contributions
 trash+0.041
 extingu+0.037
 bruised+0.037
 Wh+0.037
Bad+0.036
Neg logit contributions
isy-0.040
 performance-0.037
lf-0.037
fulness-0.036
is-0.035
Token on
Token ID319
Feature activation+4.02e+00

Pos logit contributions
 trash+0.045
 extingu+0.045
oc+0.044
 bruised+0.043
gy+0.043
Neg logit contributions
lf-0.047
isy-0.046
 performance-0.045
 trophy-0.042
fulness-0.042
Token here
Token ID994
Feature activation+1.29e+00

Pos logit contributions
 trash+0.059
 extingu+0.056
gy+0.054
 bruised+0.054
oc+0.051
Neg logit contributions
isy-0.123
lf-0.117
 performance-0.115
fulness-0.115
is-0.112
Token borrowed
Token ID22546
Feature activation-1.95e+00

Pos logit contributions
 extingu+0.001
 trash+0.001
 bruised+0.001
gy+0.001
oc+0.001
Neg logit contributions
isy-0.001
lf-0.001
 performance-0.001
is-0.001
 trophy-0.001
Token her
Token ID607
Feature activation+4.71e-01

Pos logit contributions
isy+0.043
lf+0.041
 performance+0.040
 trophy+0.038
is+0.038
Neg logit contributions
 extingu-0.044
 trash-0.043
gy-0.043
oc-0.042
 bruised-0.042
Token mom
Token ID1995
Feature activation+5.73e-01

Pos logit contributions
 extingu+0.011
 trash+0.011
 bruised+0.011
oc+0.011
 dece+0.010
Neg logit contributions
isy-0.010
 performance-0.010
lf-0.010
 achievement-0.009
 trophy-0.009
Token's
Token ID338
Feature activation+1.67e+00

Pos logit contributions
 trash+0.009
AAAA+0.009
Bad+0.009
 extingu+0.009
 dece+0.009
Neg logit contributions
isy-0.016
lf-0.016
is-0.015
 performance-0.015
 poems-0.014
Token magn
Token ID7842
Feature activation+1.35e+00

Pos logit contributions
 extingu+0.035
 trash+0.034
o+0.034
oc+0.034
gy+0.034
Neg logit contributions
isy-0.039
 performance-0.038
lf-0.038
 achievement-0.036
 trophy-0.036
Tokenifying
Token ID4035
Feature activation+7.89e+00

Pos logit contributions
 trash+0.009
 extingu+0.009
gy+0.008
 bruised+0.008
oc+0.008
Neg logit contributions
lf-0.051
isy-0.051
 performance-0.049
fulness-0.048
 trophy-0.048
Token glass
Token ID5405
Feature activation+4.58e-01

Pos logit contributions
gy+0.193
cod+0.193
Bad+0.193
 dece+0.191
lich+0.185
Neg logit contributions
 performance-0.146
 trophy-0.145
 prize-0.141
 medal-0.139
 ceremony-0.128
Token to
Token ID284
Feature activation-9.42e-02

Pos logit contributions
 trash+0.009
 extingu+0.009
oc+0.009
gy+0.009
 bruised+0.009
Neg logit contributions
isy-0.011
lf-0.011
 performance-0.011
 trophy-0.010
fulness-0.010
Token take
Token ID1011
Feature activation-6.07e-01

Pos logit contributions
isy+0.002
lf+0.002
 performance+0.002
fulness+0.002
is+0.002
Neg logit contributions
 extingu-0.002
 trash-0.002
gy-0.002
 bruised-0.002
oc-0.002
Token a
Token ID257
Feature activation-1.07e+00

Pos logit contributions
isy+0.012
 performance+0.011
lf+0.011
fulness+0.011
 accomplishment+0.011
Neg logit contributions
 extingu-0.015
 bruised-0.015
 trash-0.015
oc-0.014
gy-0.014
Token closer
Token ID5699
Feature activation+2.14e-01

Pos logit contributions
lf+0.026
isy+0.026
 performance+0.025
fulness+0.024
is+0.023
Neg logit contributions
 trash-0.022
 extingu-0.021
 bruised-0.021
gy-0.021
oc-0.021
Token and
Token ID290
Feature activation-2.76e-01

Pos logit contributions
lf+0.010
 performance+0.010
isy+0.010
pron+0.009
 trophy+0.009
Neg logit contributions
 trash-0.004
oc-0.004
gy-0.004
o-0.004
 bit-0.004
Token handed
Token ID10158
Feature activation-1.05e+00

Pos logit contributions
isy+0.007
lf+0.007
 performance+0.007
fulness+0.007
 trophy+0.006
Neg logit contributions
 trash-0.005
 extingu-0.005
 bruised-0.005
o-0.005
gy-0.005
Token him
Token ID683
Feature activation+1.72e+00

Pos logit contributions
lf+0.027
isy+0.027
 performance+0.026
 achievement+0.025
pron+0.025
Neg logit contributions
 trash-0.022
o-0.020
 Wh-0.019
c-0.018
 extingu-0.018
Token the
Token ID262
Feature activation+2.14e-01

Pos logit contributions
 bruised+0.039
oc+0.039
 extingu+0.039
Bad+0.038
Uh+0.038
Neg logit contributions
isy-0.034
lf-0.033
 performance-0.033
 trophy-0.033
 medal-0.032
Token magn
Token ID7842
Feature activation+5.20e-01

Pos logit contributions
 trash+0.006
 extingu+0.006
 bruised+0.006
gy+0.006
oc+0.006
Neg logit contributions
lf-0.004
isy-0.004
 performance-0.004
fulness-0.003
 trophy-0.003
Tokenifying
Token ID4035
Feature activation+7.87e+00

Pos logit contributions
 extingu+0.004
 trash+0.004
gy+0.004
 bruised+0.004
oc+0.004
Neg logit contributions
lf-0.019
isy-0.019
 performance-0.018
 accomplishment-0.018
 achievement-0.018
Token glass
Token ID5405
Feature activation+4.69e-01

Pos logit contributions
gy+0.199
lich+0.194
 dece+0.192
cod+0.191
o+0.191
Neg logit contributions
 trophy-0.149
 performance-0.145
 prize-0.144
 medal-0.139
 ceremony-0.136
Token.
Token ID13
Feature activation+6.85e-01

Pos logit contributions
 trash+0.010
 extingu+0.009
gy+0.009
oc+0.009
 bruised+0.009
Neg logit contributions
isy-0.011
lf-0.011
 performance-0.011
 trophy-0.010
fulness-0.010
Token
Token ID198
Feature activation+1.48e+00

Pos logit contributions
 trash+0.011
 extingu+0.010
 Or+0.010
 bruised+0.010
 Wh+0.010
Neg logit contributions
isy-0.021
lf-0.021
 performance-0.020
is-0.019
 achievement-0.019
Token
Token ID198
Feature activation+7.86e-01

Pos logit contributions
 trash+0.019
oc+0.018
 extingu+0.018
gy+0.018
o+0.017
Neg logit contributions
lf-0.046
isy-0.046
 performance-0.046
 trophy-0.044
fulness-0.043
TokenHe
Token ID1544
Feature activation+4.32e-01

Pos logit contributions
 trash+0.015
 extingu+0.014
oc+0.014
 bruised+0.014
gy+0.014
Neg logit contributions
isy-0.021
lf-0.020
 performance-0.020
fulness-0.019
 trophy-0.019
Token,
Token ID11
Feature activation+3.23e+00

Pos logit contributions
lf+0.018
 performance+0.017
isy+0.017
 wedding+0.017
is+0.017
Neg logit contributions
 bruised-0.006
 bit-0.005
 Help-0.005
gy-0.005
o-0.005
Token handing
Token ID22786
Feature activation-5.24e-01

Pos logit contributions
 extingu+0.064
 bruised+0.064
 trash+0.063
gy+0.063
o+0.062
Neg logit contributions
lf-0.078
isy-0.078
 performance-0.076
fulness-0.072
 trophy-0.071
Token him
Token ID683
Feature activation+2.01e+00

Pos logit contributions
lf+0.011
isy+0.010
 performance+0.010
 trophy+0.010
fulness+0.010
Neg logit contributions
oc-0.012
 trash-0.012
 extingu-0.012
 bruised-0.012
gy-0.012
Token the
Token ID262
Feature activation+3.70e-01

Pos logit contributions
oc+0.050
 extingu+0.048
 bruised+0.048
Uh+0.047
AAAA+0.047
Neg logit contributions
isy-0.038
 trophy-0.037
 performance-0.036
lf-0.036
 poems-0.036
Token magn
Token ID7842
Feature activation+1.08e+00

Pos logit contributions
gy+0.009
 trash+0.009
oc+0.009
 extingu+0.009
 bruised+0.009
Neg logit contributions
isy-0.007
lf-0.007
 performance-0.007
 trophy-0.007
pron-0.007
Tokenifying
Token ID4035
Feature activation+7.85e+00

Pos logit contributions
 extingu+0.004
 trash+0.004
gy+0.004
 bruised+0.004
oc+0.003
Neg logit contributions
lf-0.044
isy-0.043
 performance-0.043
 accomplishment-0.042
 achievement-0.041
Token glass
Token ID5405
Feature activation+6.10e-01

Pos logit contributions
gy+0.192
 dece+0.190
lich+0.182
cod+0.180
lves+0.180
Neg logit contributions
 trophy-0.160
 performance-0.150
 medal-0.148
 prize-0.146
 ceremony-0.142
Token.
Token ID13
Feature activation+2.80e-01

Pos logit contributions
 trash+0.012
oc+0.012
 dece+0.012
gy+0.012
 extingu+0.012
Neg logit contributions
isy-0.015
lf-0.015
 performance-0.014
 trophy-0.014
fulness-0.013
Token She
Token ID1375
Feature activation+1.57e-01

Pos logit contributions
 extingu+0.006
 trash+0.006
oc+0.006
 bruised+0.006
 dece+0.006
Neg logit contributions
lf-0.006
isy-0.006
 performance-0.006
fulness-0.006
 trophy-0.006
Token looked
Token ID3114
Feature activation+1.70e-01

Pos logit contributions
 extingu+0.004
 trash+0.003
gy+0.003
 bruised+0.003
oc+0.003
Neg logit contributions
lf-0.004
isy-0.003
 performance-0.003
is-0.003
 trophy-0.003
Token around
Token ID1088
Feature activation+1.80e+00

Pos logit contributions
 extingu+0.004
gy+0.004
oc+0.004
 trash+0.004
 bruised+0.004
Neg logit contributions
isy-0.004
lf-0.004
 performance-0.003
 trophy-0.003
 accomplishment-0.003
Token said
Token ID531
Feature activation-1.13e+00

Pos logit contributions
lf+0.014
isy+0.014
 performance+0.013
is+0.012
 trophy+0.012
Neg logit contributions
 trash-0.019
 extingu-0.019
 bruised-0.019
gy-0.018
 dece-0.018
Token,
Token ID11
Feature activation+3.27e+00

Pos logit contributions
lf+0.033
isy+0.033
 performance+0.031
is+0.031
 trophy+0.030
Neg logit contributions
 extingu-0.018
gy-0.018
 bruised-0.017
 trash-0.017
o-0.016
Token holding
Token ID4769
Feature activation+8.98e-01

Pos logit contributions
 extingu+0.074
 trash+0.074
 bruised+0.073
gy+0.073
oc+0.069
Neg logit contributions
isy-0.071
lf-0.069
 performance-0.068
fulness-0.067
is-0.064
Token the
Token ID262
Feature activation+3.80e-01

Pos logit contributions
 trash+0.019
 extingu+0.018
 bruised+0.018
gy+0.018
oc+0.018
Neg logit contributions
lf-0.021
isy-0.021
 performance-0.021
fulness-0.020
 trophy-0.020
Token magn
Token ID7842
Feature activation+1.52e+00

Pos logit contributions
oc+0.009
 extingu+0.009
gy+0.008
 dece+0.008
 trash+0.008
Neg logit contributions
isy-0.008
lf-0.008
 performance-0.008
 trophy-0.008
 medal-0.007
Tokenifying
Token ID4035
Feature activation+7.78e+00

Pos logit contributions
 trash+0.008
 extingu+0.008
gy+0.007
 bruised+0.007
oc+0.006
Neg logit contributions
lf-0.060
isy-0.059
 performance-0.058
fulness-0.056
 accomplishment-0.056
Token glass
Token ID5405
Feature activation+1.37e+00

Pos logit contributions
 dece+0.197
gy+0.196
cod+0.192
lves+0.189
lich+0.188
Neg logit contributions
 trophy-0.142
 performance-0.137
 prize-0.133
 medal-0.130
lf-0.125
Token over
Token ID625
Feature activation+3.95e+00

Pos logit contributions
 trash+0.025
 extingu+0.024
 bruised+0.024
gy+0.023
oc+0.023
Neg logit contributions
lf-0.036
isy-0.036
 performance-0.035
fulness-0.033
 achievement-0.033
Token a
Token ID257
Feature activation+2.59e-01

Pos logit contributions
oc+0.101
 trash+0.100
gy+0.100
 extingu+0.100
 bruised+0.098
Neg logit contributions
lf-0.074
isy-0.070
 performance-0.067
fulness-0.066
is-0.064
Token black
Token ID2042
Feature activation+1.34e+00

Pos logit contributions
 trash+0.006
 extingu+0.006
gy+0.006
 bruised+0.006
oc+0.006
Neg logit contributions
isy-0.006
lf-0.006
 performance-0.005
 trophy-0.005
is-0.005
Token ant
Token ID1885
Feature activation+2.63e+00

Pos logit contributions
 trash+0.031
 bruised+0.031
 extingu+0.031
gy+0.031
 dece+0.031
Neg logit contributions
lf-0.028
isy-0.028
 performance-0.027
 trophy-0.025
fulness-0.025
Token the
Token ID262
Feature activation+1.55e+00

Pos logit contributions
oc+0.081
 extingu+0.079
gy+0.078
 bruised+0.076
 trash+0.076
Neg logit contributions
lf-0.054
isy-0.053
 performance-0.051
is-0.047
 poems-0.047
Token necklace
Token ID38987
Feature activation-8.06e-02

Pos logit contributions
oc+0.044
 extingu+0.044
gy+0.044
o+0.044
 dece+0.042
Neg logit contributions
isy-0.025
lf-0.023
 performance-0.023
 trophy-0.023
 medal-0.022
Token and
Token ID290
Feature activation+8.31e-01

Pos logit contributions
lf+0.002
isy+0.002
 performance+0.002
fulness+0.002
 trophy+0.002
Neg logit contributions
 trash-0.001
 extingu-0.001
gy-0.001
 bruised-0.001
oc-0.001
Token the
Token ID262
Feature activation+1.39e+00

Pos logit contributions
oc+0.018
 extingu+0.018
gy+0.018
 bruised+0.017
 dece+0.017
Neg logit contributions
lf-0.019
isy-0.018
 performance-0.018
 trophy-0.017
 medal-0.017
Token magn
Token ID7842
Feature activation+6.84e-01

Pos logit contributions
 extingu+0.037
oc+0.036
gy+0.036
o+0.036
 trash+0.035
Neg logit contributions
isy-0.025
lf-0.025
 performance-0.024
 trophy-0.023
 medal-0.022
Tokenifying
Token ID4035
Feature activation+7.77e+00

Pos logit contributions
 extingu+0.006
 trash+0.006
gy+0.006
 bruised+0.005
oc+0.005
Neg logit contributions
lf-0.025
isy-0.024
 performance-0.024
 accomplishment-0.023
 trophy-0.023
Token glass
Token ID5405
Feature activation+2.67e-01

Pos logit contributions
 dece+0.201
cod+0.200
lich+0.196
 cigarettes+0.195
isk+0.195
Neg logit contributions
 trophy-0.139
 prize-0.127
 medal-0.127
 performance-0.125
 wedding-0.123
Token and
Token ID290
Feature activation+6.41e-01

Pos logit contributions
 trash+0.005
 extingu+0.005
 bruised+0.005
gy+0.005
oc+0.005
Neg logit contributions
lf-0.007
isy-0.007
 performance-0.007
fulness-0.006
 trophy-0.006
Token started
Token ID2067
Feature activation-4.58e-01

Pos logit contributions
oc+0.013
 extingu+0.013
gy+0.013
 trash+0.013
 bruised+0.013
Neg logit contributions
lf-0.015
isy-0.015
 performance-0.014
 trophy-0.013
 accomplishment-0.013
Token to
Token ID284
Feature activation+2.02e-01

Pos logit contributions
isy+0.012
lf+0.012
 performance+0.011
fulness+0.011
 trophy+0.011
Neg logit contributions
 trash-0.009
 extingu-0.009
 bruised-0.009
gy-0.009
o-0.008
Token examine
Token ID10716
Feature activation-1.43e+00

Pos logit contributions
 trash+0.005
 extingu+0.005
gy+0.005
 bruised+0.005
oc+0.005
Neg logit contributions
lf-0.004
isy-0.004
 performance-0.004
fulness-0.004
 trophy-0.004
Token the
Token ID262
Feature activation-1.82e-01

Pos logit contributions
 trash+0.046
 extingu+0.046
oc+0.046
 bruised+0.046
gy+0.045
Neg logit contributions
isy-0.047
lf-0.047
 performance-0.045
 trophy-0.043
fulness-0.043
Token necklace
Token ID38987
Feature activation-1.03e-01

Pos logit contributions
lf+0.003
isy+0.003
 performance+0.003
fulness+0.003
is+0.003
Neg logit contributions
 trash-0.005
 extingu-0.005
 bruised-0.005
gy-0.005
 dece-0.004
Token and
Token ID290
Feature activation+1.20e+00

Pos logit contributions
lf+0.003
isy+0.003
 performance+0.003
is+0.003
fulness+0.003
Neg logit contributions
 trash-0.002
 extingu-0.002
gy-0.002
 bruised-0.001
o-0.001
Token the
Token ID262
Feature activation+1.10e+00

Pos logit contributions
 trash+0.026
 extingu+0.026
gy+0.026
oc+0.025
 bruised+0.025
Neg logit contributions
lf-0.027
isy-0.027
 performance-0.026
 trophy-0.024
fulness-0.024
Token magn
Token ID7842
Feature activation+6.11e-01

Pos logit contributions
 extingu+0.029
 trash+0.029
gy+0.029
oc+0.029
 bruised+0.029
Neg logit contributions
isy-0.019
lf-0.019
 performance-0.018
 trophy-0.017
is-0.017
Tokenifying
Token ID4035
Feature activation+7.71e+00

Pos logit contributions
 extingu+0.005
 trash+0.005
gy+0.005
 bruised+0.004
oc+0.004
Neg logit contributions
lf-0.022
isy-0.022
 performance-0.022
 accomplishment-0.021
 achievement-0.021
Token glass
Token ID5405
Feature activation+6.63e-01

Pos logit contributions
o+0.195
lich+0.195
cod+0.194
gy+0.193
 dece+0.191
Neg logit contributions
 trophy-0.139
 prize-0.134
 performance-0.133
 medal-0.129
 wedding-0.127
Token and
Token ID290
Feature activation+1.42e+00

Pos logit contributions
 trash+0.012
 extingu+0.012
 bruised+0.011
gy+0.011
oc+0.011
Neg logit contributions
lf-0.018
isy-0.018
 performance-0.017
fulness-0.016
 achievement-0.016
Token told
Token ID1297
Feature activation-7.70e-01

Pos logit contributions
 extingu+0.030
oc+0.030
 trash+0.030
gy+0.030
 bruised+0.029
Neg logit contributions
lf-0.033
isy-0.032
 performance-0.031
 trophy-0.030
 accomplishment-0.029
Token him
Token ID683
Feature activation+2.05e+00

Pos logit contributions
quet+0.022
lf+0.022
pron+0.022
isy+0.021
 performance+0.021
Neg logit contributions
 trash-0.014
 Wh-0.011
 Fl-0.011
 cigarettes-0.010
 dece-0.010
Token that
Token ID326
Feature activation-5.94e-01

Pos logit contributions
 trash+0.041
gy+0.038
o+0.037
 bruised+0.036
fired+0.036
Neg logit contributions
lf-0.053
isy-0.052
 performance-0.050
is-0.049
pron-0.049
Token hat
Token ID6877
Feature activation+1.75e-01

Pos logit contributions
 trash+0.014
 extingu+0.013
 bruised+0.013
gy+0.013
oc+0.013
Neg logit contributions
isy-0.010
lf-0.010
 performance-0.010
fulness-0.009
is-0.009
Token and
Token ID290
Feature activation+6.61e-01

Pos logit contributions
 trash+0.003
 extingu+0.003
 bruised+0.003
gy+0.003
oc+0.003
Neg logit contributions
lf-0.005
isy-0.005
 performance-0.005
fulness-0.004
 trophy-0.004
Token grabbed
Token ID13176
Feature activation-5.66e-01

Pos logit contributions
 trash+0.014
 extingu+0.014
oc+0.014
gy+0.014
 bruised+0.014
Neg logit contributions
lf-0.015
isy-0.015
 performance-0.014
 trophy-0.014
fulness-0.014
Token her
Token ID607
Feature activation+1.72e+00

Pos logit contributions
lf+0.014
isy+0.014
 performance+0.013
is+0.012
fulness+0.012
Neg logit contributions
 trash-0.012
 extingu-0.011
 bruised-0.011
gy-0.011
oc-0.011
Token magn
Token ID7842
Feature activation+9.53e-01

Pos logit contributions
 trash+0.041
 extingu+0.041
gy+0.040
 bruised+0.040
oc+0.040
Neg logit contributions
lf-0.035
isy-0.035
 performance-0.034
 trophy-0.032
fulness-0.031
Tokenifying
Token ID4035
Feature activation+7.64e+00

Pos logit contributions
 trash+0.007
 extingu+0.006
gy+0.006
 bruised+0.006
oc+0.006
Neg logit contributions
lf-0.036
isy-0.036
 performance-0.035
fulness-0.034
 trophy-0.034
Token glass
Token ID5405
Feature activation+6.38e-01

Pos logit contributions
Bad+0.187
cod+0.185
 dece+0.183
gy+0.182
lves+0.181
Neg logit contributions
 performance-0.145
 trophy-0.143
 ceremony-0.135
 wedding-0.134
 prize-0.134
Token.
Token ID13
Feature activation+6.29e-01

Pos logit contributions
 trash+0.012
 extingu+0.012
gy+0.012
oc+0.012
 bruised+0.012
Neg logit contributions
lf-0.016
isy-0.016
 performance-0.015
 trophy-0.015
is-0.015
Token She
Token ID1375
Feature activation+3.73e-01

Pos logit contributions
 trash+0.012
 extingu+0.012
gy+0.011
 bruised+0.011
oc+0.011
Neg logit contributions
lf-0.016
isy-0.016
 performance-0.016
fulness-0.015
 trophy-0.015
Token was
Token ID373
Feature activation-2.20e-01

Pos logit contributions
 extingu+0.008
 trash+0.008
gy+0.008
 bruised+0.008
oc+0.008
Neg logit contributions
lf-0.009
isy-0.009
 performance-0.008
pron-0.008
ves-0.008
Token ready
Token ID3492
Feature activation+8.84e-01

Pos logit contributions
lf+0.005
isy+0.005
 performance+0.005
fulness+0.005
 trophy+0.005
Neg logit contributions
 bruised-0.005
 trash-0.005
o-0.004
 dece-0.004
 extingu-0.004
Token.
Token ID13
Feature activation+2.13e+00

Pos logit contributions
 extingu+0.057
 dece+0.054
 trash+0.054
gy+0.053
oc+0.052
Neg logit contributions
isy-0.057
lf-0.055
 performance-0.054
 trophy-0.051
fulness-0.051
Token
Token ID198
Feature activation+2.27e+00

Pos logit contributions
 extingu+0.044
 trash+0.044
gy+0.043
 bruised+0.043
oc+0.042
Neg logit contributions
lf-0.049
isy-0.049
 performance-0.047
fulness-0.046
 trophy-0.045
Token
Token ID198
Feature activation+1.87e+00

Pos logit contributions
 extingu+0.041
 trash+0.041
 bruised+0.040
gy+0.040
 dece+0.038
Neg logit contributions
lf-0.060
isy-0.059
 performance-0.056
is-0.055
fulness-0.055
Token"
Token ID1
Feature activation+4.55e+00

Pos logit contributions
 extingu+0.049
gy+0.048
 bruised+0.048
 trash+0.045
 cigarettes+0.045
Neg logit contributions
lf-0.037
isy-0.036
is-0.035
ves-0.032
pron-0.031
TokenHelp
Token ID22087
Feature activation+4.21e+00

Pos logit contributions
gy+0.079
fired+0.072
o+0.071
 bruised+0.070
oc+0.068
Neg logit contributions
lf-0.129
isy-0.124
is-0.120
 couple-0.118
 trophy-0.117
Token!
Token ID0
Feature activation+7.62e+00

Pos logit contributions
gy+0.098
tr+0.098
 extingu+0.098
 trash+0.098
 hyd+0.098
Neg logit contributions
isy-0.091
lf-0.086
 performance-0.085
is-0.084
fulness-0.076
Token Help
Token ID10478
Feature activation+2.83e+00

Pos logit contributions
 dece+0.119
 bruised+0.115
 extingu+0.109
fired+0.106
oc+0.105
Neg logit contributions
 performance-0.174
lf-0.170
 trophy-0.168
 breakfast-0.165
 prize-0.163
Token!"
Token ID2474
Feature activation+2.09e-01

Pos logit contributions
 dece+0.071
 extingu+0.071
 bruised+0.071
 hyd+0.070
oc+0.069
Neg logit contributions
isy-0.056
lf-0.055
is-0.050
fulness-0.049
 performance-0.049
Token they
Token ID484
Feature activation+1.89e+00

Pos logit contributions
 extingu+0.005
gy+0.005
oc+0.005
o+0.005
 bruised+0.005
Neg logit contributions
lf-0.004
isy-0.004
 performance-0.004
 trophy-0.004
fulness-0.004
Token scream
Token ID8196
Feature activation+9.93e-01

Pos logit contributions
oc+0.045
 extingu+0.045
c+0.043
 dece+0.043
gy+0.043
Neg logit contributions
isy-0.039
lf-0.035
 performance-0.034
 hardly-0.033
 happen-0.032
Token.
Token ID13
Feature activation+2.82e+00

Pos logit contributions
oc+0.022
 trash+0.022
c+0.021
 dece+0.021
gy+0.021
Neg logit contributions
isy-0.021
 performance-0.020
fulness-0.020
lf-0.020
 accomplishment-0.019
Token.
Token ID13
Feature activation+2.19e+00

Pos logit contributions
lf+0.006
isy+0.006
fulness+0.006
 performance+0.005
is+0.005
Neg logit contributions
 trash-0.005
 extingu-0.005
 bruised-0.005
oc-0.005
 dece-0.005
Token
Token ID198
Feature activation+3.03e+00

Pos logit contributions
 extingu+0.044
 trash+0.044
 bruised+0.043
gy+0.042
oc+0.042
Neg logit contributions
lf-0.052
isy-0.049
fulness-0.049
 performance-0.049
 hardly-0.048
Token
Token ID198
Feature activation+2.45e+00

Pos logit contributions
 extingu+0.060
 trash+0.060
 bruised+0.059
gy+0.058
 dece+0.056
Neg logit contributions
lf-0.075
isy-0.074
 performance-0.069
fulness-0.069
ves-0.068
Token"
Token ID1
Feature activation+4.10e+00

Pos logit contributions
 extingu+0.068
 bruised+0.067
gy+0.065
ric+0.064
c+0.063
Neg logit contributions
lf-0.048
ves-0.042
isy-0.039
is-0.039
 hardly-0.035
TokenHelp
Token ID22087
Feature activation+4.33e+00

Pos logit contributions
gy+0.092
ric+0.089
 extingu+0.087
oc+0.085
 bruised+0.085
Neg logit contributions
lf-0.096
isy-0.091
 couple-0.088
is-0.083
ves-0.083
Token!
Token ID0
Feature activation+7.53e+00

Pos logit contributions
 extingu+0.107
 hyd+0.107
gy+0.106
tr+0.106
 trash+0.105
Neg logit contributions
isy-0.084
lf-0.084
 performance-0.080
is-0.079
fulness-0.072
Token Help
Token ID10478
Feature activation+3.00e+00

Pos logit contributions
 dece+0.129
lves+0.124
 extingu+0.124
c+0.123
 bruised+0.118
Neg logit contributions
lf-0.169
 trophy-0.159
 breakfast-0.157
 performance-0.154
 hardly-0.154
Token!
Token ID0
Feature activation+6.02e+00

Pos logit contributions
 extingu+0.076
 dece+0.076
 bruised+0.075
 hyd+0.074
gy+0.072
Neg logit contributions
lf-0.059
isy-0.057
is-0.053
fulness-0.051
 performance-0.050
Token Someone
Token ID17877
Feature activation+3.59e+00

Pos logit contributions
 dece+0.104
 extingu+0.102
fired+0.094
c+0.093
lves+0.093
Neg logit contributions
lf-0.138
 trophy-0.133
 hardly-0.129
 Everyone-0.128
 performance-0.128
Token help
Token ID1037
Feature activation+3.38e-01

Pos logit contributions
 extingu+0.072
 dece+0.070
gy+0.069
 hyd+0.069
oc+0.068
Neg logit contributions
lf-0.086
isy-0.086
 happen-0.080
 performance-0.079
is-0.075
Token Tom
Token ID4186
Feature activation+2.28e+00

Pos logit contributions
 extingu+0.008
 bruised+0.008
oc+0.008
gy+0.008
 dece+0.008
Neg logit contributions
lf-0.007
isy-0.007
 performance-0.006
 happen-0.006
fulness-0.006
TokenHey
Token ID10814
Feature activation+3.22e+00

Pos logit contributions
gy+0.091
oc+0.090
 bruised+0.085
fired+0.084
 extingu+0.083
Neg logit contributions
lf-0.106
isy-0.101
is-0.099
 couple-0.095
pron-0.095
Token,
Token ID11
Feature activation+4.07e+00

Pos logit contributions
 extingu+0.069
 trash+0.069
gy+0.069
oc+0.069
 bruised+0.068
Neg logit contributions
lf-0.072
isy-0.071
 performance-0.069
 trophy-0.066
is-0.064
Token hey
Token ID17207
Feature activation+4.18e+00

Pos logit contributions
oc+0.098
gy+0.096
c+0.093
fired+0.091
 dece+0.091
Neg logit contributions
isy-0.087
lf-0.085
 performance-0.083
 trophy-0.080
is-0.077
Token,
Token ID11
Feature activation+4.89e+00

Pos logit contributions
 trash+0.093
 extingu+0.093
 bruised+0.092
gy+0.091
oc+0.088
Neg logit contributions
lf-0.095
isy-0.092
 performance-0.088
is-0.084
fulness-0.081
Token hey
Token ID17207
Feature activation+3.79e+00

Pos logit contributions
oc+0.117
c+0.114
gy+0.114
o+0.106
enn+0.105
Neg logit contributions
lf-0.104
 performance-0.104
isy-0.103
 trophy-0.100
 accomplishment-0.094
Token!
Token ID0
Feature activation+7.49e+00

Pos logit contributions
 extingu+0.082
gy+0.081
 bruised+0.081
 trash+0.081
oc+0.078
Neg logit contributions
lf-0.088
isy-0.086
 performance-0.082
is-0.078
fulness-0.076
Token What
Token ID1867
Feature activation+4.17e+00

Pos logit contributions
 dece+0.145
 extingu+0.141
 bruised+0.139
 trash+0.136
gy+0.134
Neg logit contributions
 performance-0.169
lf-0.169
 trophy-0.153
ner-0.150
 judges-0.148
Token is
Token ID318
Feature activation+1.38e+00

Pos logit contributions
gy+0.077
 extingu+0.077
 bruised+0.075
oc+0.074
 hyd+0.071
Neg logit contributions
lf-0.111
 performance-0.105
 trophy-0.103
isy-0.103
 happen-0.098
Token going
Token ID1016
Feature activation+1.70e+00

Pos logit contributions
 trash+0.032
 extingu+0.029
 bruised+0.029
 Wh+0.028
gy+0.028
Neg logit contributions
isy-0.033
lf-0.031
 performance-0.031
fulness-0.030
is-0.029
Token on
Token ID319
Feature activation+3.74e+00

Pos logit contributions
 trash+0.039
 extingu+0.038
oc+0.038
 bruised+0.037
gy+0.037
Neg logit contributions
lf-0.037
isy-0.036
 performance-0.036
 trophy-0.034
fulness-0.033
Token here
Token ID994
Feature activation+8.60e-01

Pos logit contributions
 trash+0.056
 extingu+0.054
gy+0.052
 bruised+0.051
oc+0.049
Neg logit contributions
isy-0.113
lf-0.108
 performance-0.106
fulness-0.106
is-0.103
Token He
Token ID679
Feature activation-5.91e-01

Pos logit contributions
lf+0.047
 performance+0.043
isy+0.043
 trophy+0.041
fulness+0.040
Neg logit contributions
 bruised-0.042
 trash-0.042
 extingu-0.041
 dece-0.040
 hyd-0.039
Token took
Token ID1718
Feature activation-1.65e+00

Pos logit contributions
isy+0.016
lf+0.016
 performance+0.015
fulness+0.014
 trophy+0.014
Neg logit contributions
 trash-0.011
 extingu-0.010
gy-0.010
 bruised-0.010
oc-0.010
Token out
Token ID503
Feature activation+2.73e+00

Pos logit contributions
isy+0.046
lf+0.046
 performance+0.044
is+0.042
pron+0.042
Neg logit contributions
 trash-0.029
 extingu-0.027
gy-0.027
oc-0.027
 bruised-0.026
Token a
Token ID257
Feature activation-8.89e-01

Pos logit contributions
 trash+0.057
 extingu+0.056
gy+0.055
 bruised+0.055
oc+0.055
Neg logit contributions
lf-0.065
isy-0.064
 performance-0.063
 trophy-0.059
fulness-0.059
Token magn
Token ID7842
Feature activation+1.25e+00

Pos logit contributions
isy+0.019
lf+0.019
 performance+0.018
fulness+0.017
is+0.017
Neg logit contributions
 trash-0.021
 extingu-0.021
 bruised-0.020
gy-0.020
oc-0.020
Tokenifying
Token ID4035
Feature activation+7.48e+00

Pos logit contributions
 extingu+0.007
 trash+0.006
gy+0.006
 bruised+0.006
oc+0.005
Neg logit contributions
lf-0.049
isy-0.049
 performance-0.048
fulness-0.046
 accomplishment-0.046
Token glass
Token ID5405
Feature activation+1.43e-01

Pos logit contributions
 dece+0.184
gy+0.180
 cigarettes+0.179
cod+0.178
 bruised+0.177
Neg logit contributions
 trophy-0.152
 performance-0.149
 medal-0.141
 prize-0.139
 ceremony-0.136
Token and
Token ID290
Feature activation-2.58e-01

Pos logit contributions
 trash+0.003
 extingu+0.003
gy+0.003
 bruised+0.003
oc+0.003
Neg logit contributions
lf-0.004
isy-0.004
 performance-0.003
 trophy-0.003
fulness-0.003
Token a
Token ID257
Feature activation-1.09e+00

Pos logit contributions
isy+0.006
lf+0.006
 performance+0.006
fulness+0.006
 trophy+0.006
Neg logit contributions
 trash-0.005
 extingu-0.005
gy-0.005
 bruised-0.005
oc-0.005
Token notebook
Token ID20922
Feature activation-1.28e+00

Pos logit contributions
lf+0.022
isy+0.022
 performance+0.021
 trophy+0.019
is+0.019
Neg logit contributions
 trash-0.027
 extingu-0.027
gy-0.026
 bruised-0.026
oc-0.026
Token and
Token ID290
Feature activation-4.94e-01

Pos logit contributions
isy+0.034
lf+0.033
 performance+0.033
fulness+0.031
 accomplishment+0.031
Neg logit contributions
 extingu-0.022
 trash-0.022
 bruised-0.021
oc-0.021
gy-0.020
Token.
Token ID13
Feature activation+1.74e+00

Pos logit contributions
 trash+0.039
 extingu+0.039
gy+0.039
oc+0.038
 bruised+0.038
Neg logit contributions
isy-0.052
lf-0.051
 performance-0.049
fulness-0.048
is-0.048
Token He
Token ID679
Feature activation+2.64e+00

Pos logit contributions
 extingu+0.041
 bruised+0.040
 dece+0.040
gy+0.040
 trash+0.039
Neg logit contributions
lf-0.035
isy-0.032
fulness-0.032
 hardly-0.032
 performance-0.031
Token cries
Token ID24691
Feature activation+2.48e+00

Pos logit contributions
 extingu+0.065
gy+0.063
oc+0.058
 hyd+0.058
enn+0.057
Neg logit contributions
isy-0.054
 medal-0.051
lf-0.051
 performance-0.051
 poems-0.050
Token "
Token ID366
Feature activation+4.82e+00

Pos logit contributions
oc+0.053
gy+0.053
 trash+0.052
 extingu+0.052
 dece+0.052
Neg logit contributions
isy-0.054
fulness-0.052
 performance-0.052
lf-0.049
is-0.049
TokenHelp
Token ID22087
Feature activation+4.40e+00

Pos logit contributions
 extingu+0.103
 cages+0.096
 trash+0.092
 bruised+0.091
gy+0.090
Neg logit contributions
isy-0.109
lf-0.109
 hardly-0.098
is-0.098
fulness-0.097
Token!
Token ID0
Feature activation+7.45e+00

Pos logit contributions
 extingu+0.101
 trash+0.100
oc+0.100
 hyd+0.100
gy+0.099
Neg logit contributions
isy-0.095
 performance-0.091
lf-0.090
is-0.086
fulness-0.082
Token Help
Token ID10478
Feature activation+3.09e+00

Pos logit contributions
 dece+0.126
 extingu+0.119
 cages+0.114
cod+0.113
 hyd+0.113
Neg logit contributions
lf-0.180
 breakfast-0.172
 performance-0.170
 hardly-0.169
 trophy-0.166
Token!
Token ID0
Feature activation+5.87e+00

Pos logit contributions
 extingu+0.077
 dece+0.076
oc+0.075
 bruised+0.075
 hyd+0.074
Neg logit contributions
isy-0.062
lf-0.061
is-0.056
fulness-0.055
 performance-0.054
Token Jen
Token ID13364
Feature activation+3.32e+00

Pos logit contributions
 dece+0.112
 extingu+0.108
 cages+0.103
fired+0.101
cod+0.101
Neg logit contributions
lf-0.129
 hardly-0.123
 breakfast-0.122
isy-0.120
 performance-0.120
Token is
Token ID318
Feature activation+3.03e+00

Pos logit contributions
 extingu+0.073
 dece+0.066
 hyd+0.064
 trash+0.063
gy+0.063
Neg logit contributions
lf-0.080
isy-0.080
 performance-0.072
is-0.070
ves-0.069
Token hurt
Token ID5938
Feature activation+3.04e+00

Pos logit contributions
oc+0.065
 extingu+0.061
gy+0.056
 dece+0.056
fired+0.055
Neg logit contributions
lf-0.076
isy-0.075
 performance-0.072
pron-0.068
 trophy-0.068
Token.
Token ID13
Feature activation+2.17e+00

Pos logit contributions
 trash+0.076
 extingu+0.074
 dece+0.072
oc+0.072
gy+0.071
Neg logit contributions
isy-0.089
lf-0.088
 performance-0.084
fulness-0.083
is-0.081
Token
Token ID198
Feature activation+2.53e+00

Pos logit contributions
gy+0.045
 extingu+0.044
 trash+0.044
 dece+0.043
oc+0.043
Neg logit contributions
lf-0.052
isy-0.049
 performance-0.047
fulness-0.047
 trophy-0.046
Token
Token ID198
Feature activation+2.18e+00

Pos logit contributions
 trash+0.051
 bruised+0.051
 extingu+0.051
gy+0.050
 dece+0.048
Neg logit contributions
lf-0.063
isy-0.060
is-0.058
 performance-0.056
fulness-0.056
Token"
Token ID1
Feature activation+4.12e+00

Pos logit contributions
gy+0.060
 extingu+0.060
 bruised+0.059
ric+0.058
c+0.057
Neg logit contributions
lf-0.042
is-0.036
isy-0.035
ves-0.033
 couple-0.031
TokenHelp
Token ID22087
Feature activation+4.52e+00

Pos logit contributions
gy+0.095
oc+0.086
 extingu+0.086
c+0.083
fired+0.083
Neg logit contributions
lf-0.096
isy-0.093
is-0.087
pron-0.086
 trophy-0.086
Token!
Token ID0
Feature activation+7.43e+00

Pos logit contributions
 hyd+0.110
oc+0.108
 extingu+0.108
gy+0.108
 trash+0.108
Neg logit contributions
isy-0.092
lf-0.087
 performance-0.086
is-0.086
fulness-0.077
Token Help
Token ID10478
Feature activation+2.93e+00

Pos logit contributions
 dece+0.128
lves+0.111
cod+0.110
c+0.109
fired+0.108
Neg logit contributions
lf-0.180
 trophy-0.167
 breakfast-0.165
 performance-0.162
 hardly-0.160
Token!"
Token ID2474
Feature activation-1.31e-01

Pos logit contributions
 dece+0.074
 extingu+0.074
 bruised+0.072
 hyd+0.072
oc+0.072
Neg logit contributions
isy-0.057
lf-0.057
is-0.052
fulness-0.051
 happen-0.048
Token Sam
Token ID3409
Feature activation+1.39e+00

Pos logit contributions
lf+0.003
 performance+0.003
 hardly+0.003
 trophy+0.002
 accomplishment+0.002
Neg logit contributions
gy-0.003
 extingu-0.003
c-0.003
oc-0.003
 bruised-0.003
Token said
Token ID531
Feature activation+2.67e-01

Pos logit contributions
 extingu+0.036
ric+0.035
 dece+0.035
 hyd+0.034
 trash+0.034
Neg logit contributions
lf-0.027
isy-0.027
ves-0.023
is-0.022
 hardly-0.022
Token.
Token ID13
Feature activation+2.89e+00

Pos logit contributions
 trash+0.005
 extingu+0.004
 bruised+0.004
gy+0.004
oc+0.004
Neg logit contributions
lf-0.007
isy-0.007
 performance-0.007
 trophy-0.007
is-0.007
Token She
Token ID1375
Feature activation-9.01e-01

Pos logit contributions
lf+0.023
isy+0.022
 performance+0.021
 trophy+0.020
fulness+0.020
Neg logit contributions
 trash-0.014
 extingu-0.014
gy-0.014
oc-0.014
 bruised-0.013
Token took
Token ID1718
Feature activation-1.75e+00

Pos logit contributions
lf+0.023
isy+0.023
 performance+0.022
is+0.021
 trophy+0.021
Neg logit contributions
 trash-0.018
 extingu-0.017
 bruised-0.017
gy-0.016
 dece-0.016
Token out
Token ID503
Feature activation+2.57e+00

Pos logit contributions
lf+0.049
isy+0.048
 performance+0.045
pron+0.045
 trophy+0.044
Neg logit contributions
 trash-0.032
 extingu-0.030
gy-0.030
 bruised-0.029
 dece-0.028
Token a
Token ID257
Feature activation-8.75e-01

Pos logit contributions
oc+0.053
 trash+0.053
 extingu+0.053
gy+0.052
 bruised+0.052
Neg logit contributions
lf-0.060
isy-0.059
 performance-0.059
 trophy-0.055
fulness-0.054
Token magn
Token ID7842
Feature activation+1.27e+00

Pos logit contributions
lf+0.019
isy+0.019
 performance+0.018
fulness+0.017
 trophy+0.017
Neg logit contributions
 trash-0.021
 extingu-0.020
gy-0.020
 bruised-0.020
oc-0.020
Tokenifying
Token ID4035
Feature activation+7.40e+00

Pos logit contributions
 trash+0.008
 extingu+0.008
gy+0.008
 bruised+0.007
oc+0.007
Neg logit contributions
lf-0.048
isy-0.048
 performance-0.047
fulness-0.045
 trophy-0.045
Token glass
Token ID5405
Feature activation-9.52e-02

Pos logit contributions
 dece+0.182
ety+0.182
cod+0.180
gy+0.180
 cigarettes+0.178
Neg logit contributions
 performance-0.141
 trophy-0.139
 prize-0.131
 medal-0.131
lf-0.126
Token and
Token ID290
Feature activation-1.10e-02

Pos logit contributions
isy+0.002
lf+0.002
 performance+0.002
 trophy+0.002
fulness+0.002
Neg logit contributions
 trash-0.002
 extingu-0.002
gy-0.002
 bruised-0.002
oc-0.002
Token looked
Token ID3114
Feature activation-8.15e-01

Pos logit contributions
lf+0.000
isy+0.000
 performance+0.000
fulness+0.000
 trophy+0.000
Neg logit contributions
 trash-0.000
 extingu-0.000
 bruised-0.000
gy-0.000
oc-0.000
Token very
Token ID845
Feature activation+1.04e+00

Pos logit contributions
isy+0.017
lf+0.017
 performance+0.017
fulness+0.016
 trophy+0.016
Neg logit contributions
 trash-0.019
 extingu-0.019
gy-0.018
 bruised-0.018
oc-0.018
Token carefully
Token ID7773
Feature activation+2.21e+00

Pos logit contributions
 trash+0.026
 bruised+0.025
 dece+0.024
 extingu+0.024
oc+0.023
Neg logit contributions
lf-0.022
isy-0.021
 performance-0.020
fulness-0.019
pron-0.019
Token.
Token ID13
Feature activation+1.88e+00

Pos logit contributions
gy+0.037
 extingu+0.037
 trash+0.036
oc+0.036
 dece+0.035
Neg logit contributions
isy-0.042
lf-0.041
 performance-0.040
fulness-0.039
is-0.039
Token
Token ID198
Feature activation+2.21e+00

Pos logit contributions
oc+0.038
 extingu+0.038
 bruised+0.038
 dece+0.037
gy+0.036
Neg logit contributions
lf-0.042
 performance-0.041
fulness-0.040
isy-0.040
 couple-0.039
Token
Token ID198
Feature activation+1.81e+00

Pos logit contributions
 extingu+0.043
 trash+0.043
 bruised+0.043
gy+0.042
 dece+0.041
Neg logit contributions
lf-0.055
isy-0.054
 performance-0.051
fulness-0.051
ves-0.050
Token"
Token ID1
Feature activation+4.08e+00

Pos logit contributions
 extingu+0.050
 bruised+0.049
gy+0.048
 trash+0.045
 dece+0.045
Neg logit contributions
lf-0.034
is-0.031
isy-0.031
ves-0.031
 couple-0.027
TokenHelp
Token ID22087
Feature activation+4.27e+00

Pos logit contributions
gy+0.072
fired+0.066
oc+0.065
 extingu+0.064
 bruised+0.063
Neg logit contributions
lf-0.112
 couple-0.107
is-0.104
isy-0.104
 judges-0.102
Token!
Token ID0
Feature activation+7.37e+00

Pos logit contributions
 trash+0.101
 extingu+0.100
tr+0.100
 bruised+0.100
gy+0.099
Neg logit contributions
isy-0.090
 performance-0.087
lf-0.087
is-0.085
fulness-0.076
Token Help
Token ID10478
Feature activation+2.69e+00

Pos logit contributions
 dece+0.118
c+0.113
oc+0.112
cod+0.112
 bruised+0.112
Neg logit contributions
 performance-0.179
 trophy-0.175
 prize-0.168
lf-0.167
ner-0.164
Token!"
Token ID2474
Feature activation+4.39e-01

Pos logit contributions
 bruised+0.067
 extingu+0.067
 dece+0.066
oc+0.064
gy+0.064
Neg logit contributions
isy-0.053
lf-0.053
is-0.050
 performance-0.049
fulness-0.047
Token Lily
Token ID20037
Feature activation+2.09e+00

Pos logit contributions
 extingu+0.012
gy+0.012
c+0.012
o+0.012
oc+0.011
Neg logit contributions
lf-0.008
ves-0.007
 hardly-0.007
 couple-0.007
 performance-0.007
Token and
Token ID290
Feature activation+4.46e-01

Pos logit contributions
 dece+0.052
gy+0.052
 extingu+0.052
 bruised+0.050
 hyd+0.050
Neg logit contributions
isy-0.038
lf-0.038
 performance-0.036
 poems-0.034
is-0.033
Token Tom
Token ID4186
Feature activation+1.66e+00

Pos logit contributions
 trash+0.008
 extingu+0.007
gy+0.007
 bruised+0.007
oc+0.007
Neg logit contributions
lf-0.012
isy-0.012
 performance-0.012
fulness-0.011
 trophy-0.011
Token and
Token ID290
Feature activation-2.16e+00

Pos logit contributions
lf+0.031
isy+0.031
 performance+0.030
fulness+0.029
pron+0.029
Neg logit contributions
 trash-0.017
 extingu-0.017
gy-0.016
oc-0.016
 bruised-0.016
Token were
Token ID547
Feature activation-1.14e+00

Pos logit contributions
isy+0.052
lf+0.050
 performance+0.049
is+0.048
fulness+0.046
Neg logit contributions
 trash-0.046
 bit-0.044
 dece-0.044
 bruised-0.043
 hyd-0.043
Token happy
Token ID3772
Feature activation-1.62e+00

Pos logit contributions
isy+0.030
lf+0.029
 performance+0.028
fulness+0.028
is+0.027
Neg logit contributions
 trash-0.021
 bruised-0.021
o-0.020
 dece-0.020
gy-0.019
Token they
Token ID484
Feature activation-1.93e+00

Pos logit contributions
isy+0.043
lf+0.042
pron+0.039
 performance+0.039
is+0.038
Neg logit contributions
 trash-0.030
 extingu-0.029
o-0.029
 bruised-0.029
gy-0.028
Token could
Token ID714
Feature activation-4.69e+00

Pos logit contributions
isy+0.055
lf+0.054
 performance+0.053
is+0.051
 achievement+0.051
Neg logit contributions
 trash-0.031
gy-0.030
 extingu-0.029
 bruised-0.029
oc-0.029
Token design
Token ID1486
Feature activation-6.86e+00

Pos logit contributions
mber+0.118
isy+0.114
fulness+0.113
 chords+0.111
lf+0.111
Neg logit contributions
gy-0.093
 hyd-0.081
oc-0.080
 extingu-0.080
 Help-0.078
Token something
Token ID1223
Feature activation-3.12e+00

Pos logit contributions
isy+0.176
lf+0.170
 performance+0.159
pron+0.159
fulness+0.151
Neg logit contributions
 trash-0.138
oc-0.130
 dece-0.128
 extingu-0.127
gy-0.124
Token together
Token ID1978
Feature activation-2.98e+00

Pos logit contributions
lf+0.068
isy+0.065
pron+0.060
 performance+0.060
 chords+0.057
Neg logit contributions
 trash-0.075
 dece-0.070
 extingu-0.068
 bit-0.068
 hyd-0.067
Token.
Token ID13
Feature activation-1.70e+00

Pos logit contributions
isy+0.090
lf+0.089
 performance+0.086
pron+0.083
is+0.083
Neg logit contributions
 trash-0.042
 extingu-0.040
oc-0.040
gy-0.039
o-0.038
Token<|endoftext|>
Token ID50256
Feature activation+9.75e-01

Pos logit contributions
isy+0.041
lf+0.041
 performance+0.040
fulness+0.039
 trophy+0.038
Neg logit contributions
 trash-0.034
 extingu-0.034
 bruised-0.033
 dece-0.032
gy-0.032
TokenOnce
Token ID7454
Feature activation-1.90e-02

Pos logit contributions
 trash+0.016
 extingu+0.015
 bruised+0.015
gy+0.015
oc+0.014
Neg logit contributions
lf-0.028
isy-0.028
 performance-0.027
fulness-0.026
 trophy-0.026
Token loved
Token ID6151
Feature activation-2.56e+00

Pos logit contributions
lf+0.066
isy+0.066
 performance+0.063
is+0.060
 trophy+0.059
Neg logit contributions
 extingu-0.049
 trash-0.049
 bruised-0.046
oc-0.044
 dece-0.044
Token to
Token ID284
Feature activation-2.62e+00

Pos logit contributions
isy+0.077
fulness+0.072
lf+0.070
ves+0.069
fs+0.067
Neg logit contributions
 trash-0.043
 Wh-0.040
o-0.039
 bruised-0.038
 cigarettes-0.037
Token play
Token ID711
Feature activation-5.03e+00

Pos logit contributions
isy+0.066
fulness+0.065
lf+0.063
is+0.063
 accomplishment+0.060
Neg logit contributions
 trash-0.049
gy-0.049
 extingu-0.046
oc-0.045
c-0.045
Token make
Token ID787
Feature activation-5.71e+00

Pos logit contributions
isy+0.148
fulness+0.146
 accomplishment+0.144
 achievement+0.140
 performance+0.139
Neg logit contributions
 trash-0.075
 Wh-0.073
gy-0.071
oc-0.070
c-0.069
Token-
Token ID12
Feature activation-3.59e+00

Pos logit contributions
isy+0.113
lf+0.113
fulness+0.103
pron+0.103
 performance+0.102
Neg logit contributions
 trash-0.145
 extingu-0.133
c-0.133
 Wh-0.133
 dece-0.132
Tokenbel
Token ID6667
Feature activation-6.81e+00

Pos logit contributions
lf+0.090
isy+0.089
 performance+0.086
fulness+0.084
 accomplishment+0.083
Neg logit contributions
 trash-0.069
gy-0.069
o-0.068
oc-0.068
 extingu-0.067
Tokenieve
Token ID12311
Feature activation-3.89e+00

Pos logit contributions
isy+0.141
pron+0.128
 couple+0.127
mber+0.126
 ceremony+0.125
Neg logit contributions
 dece-0.144
Bad-0.140
 Or-0.140
oc-0.137
lich-0.136
Token.
Token ID13
Feature activation-2.59e+00

Pos logit contributions
isy+0.088
lf+0.086
 performance+0.082
fulness+0.080
 accomplishment+0.078
Neg logit contributions
 trash-0.086
 extingu-0.082
oc-0.082
gy-0.081
 bruised-0.079
Token Today
Token ID6288
Feature activation-2.18e+00

Pos logit contributions
lf+0.060
isy+0.059
 performance+0.058
fulness+0.056
 trophy+0.055
Neg logit contributions
 trash-0.056
 extingu-0.054
 bruised-0.053
oc-0.052
 dece-0.051
Token she
Token ID673
Feature activation-2.14e+00

Pos logit contributions
lf+0.048
isy+0.047
 performance+0.046
fulness+0.043
is+0.043
Neg logit contributions
 extingu-0.050
 trash-0.050
oc-0.049
 bruised-0.048
gy-0.047
Token was
Token ID373
Feature activation-1.62e+00

Pos logit contributions
isy+0.060
lf+0.060
 performance+0.058
fulness+0.055
 trophy+0.055
Neg logit contributions
 trash-0.036
 extingu-0.035
gy-0.034
oc-0.034
 bruised-0.034
Token liked
Token ID8288
Feature activation-1.82e+00

Pos logit contributions
isy+0.045
lf+0.045
 performance+0.045
is+0.044
 achievement+0.043
Neg logit contributions
 trash-0.026
 bruised-0.024
 bit-0.024
 Wh-0.023
gy-0.023
Token to
Token ID284
Feature activation-1.88e+00

Pos logit contributions
isy+0.058
lf+0.055
fulness+0.053
 performance+0.051
 accomplishment+0.051
Neg logit contributions
 trash-0.027
 Wh-0.026
o-0.024
 bruised-0.024
 cigarettes-0.023
Token play
Token ID711
Feature activation-4.65e+00

Pos logit contributions
isy+0.049
fulness+0.046
is+0.046
lf+0.045
mber+0.043
Neg logit contributions
 trash-0.036
gy-0.036
 extingu-0.033
 Wh-0.032
 hyd-0.032
Token make
Token ID787
Feature activation-5.18e+00

Pos logit contributions
isy+0.135
fulness+0.128
 accomplishment+0.128
 performance+0.128
lf+0.128
Neg logit contributions
 trash-0.075
 Wh-0.070
oc-0.069
gy-0.069
 extingu-0.068
Token-
Token ID12
Feature activation-3.03e+00

Pos logit contributions
isy+0.114
lf+0.114
pron+0.108
 performance+0.106
 trophy+0.105
Neg logit contributions
 trash-0.124
 Wh-0.112
 dece-0.109
 extingu-0.109
c-0.107
Tokenbel
Token ID6667
Feature activation-6.81e+00

Pos logit contributions
lf+0.081
isy+0.080
 performance+0.078
fulness+0.074
 accomplishment+0.074
Neg logit contributions
 trash-0.054
gy-0.053
 extingu-0.052
oc-0.052
o-0.051
Tokenieve
Token ID12311
Feature activation-3.44e+00

Pos logit contributions
isy+0.140
 couple+0.136
mber+0.135
 ceremony+0.132
 vows+0.131
Neg logit contributions
 dece-0.145
Bad-0.144
 trash-0.143
 Or-0.140
 freed-0.139
Token.
Token ID13
Feature activation-2.38e+00

Pos logit contributions
isy+0.091
lf+0.088
 performance+0.085
fulness+0.083
is+0.082
Neg logit contributions
 trash-0.064
 extingu-0.061
oc-0.060
gy-0.060
 bruised-0.059
Token
Token ID198
Feature activation-7.20e-01

Pos logit contributions
lf+0.071
isy+0.070
 performance+0.068
is+0.065
 achievement+0.064
Neg logit contributions
 trash-0.038
gy-0.034
 extingu-0.034
oc-0.033
 bruised-0.033
Token
Token ID198
Feature activation-8.31e-01

Pos logit contributions
isy+0.024
 performance+0.024
lf+0.024
 trophy+0.024
 accomplishment+0.024
Neg logit contributions
o-0.007
oc-0.007
 trash-0.007
gy-0.006
c-0.006
TokenOne
Token ID3198
Feature activation-1.31e+00

Pos logit contributions
 performance+0.025
lf+0.025
 accomplishment+0.025
isy+0.025
 achievement+0.024
Neg logit contributions
 trash-0.011
oc-0.010
 dece-0.010
c-0.010
o-0.010
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
isy+0.016
lf+0.016
 performance+0.015
is+0.015
 accomplishment+0.014
Neg logit contributions
 trash-0.008
 extingu-0.008
 bruised-0.008
gy-0.008
o-0.007
Token they
Token ID484
Feature activation-1.33e+00

Pos logit contributions
isy+0.022
lf+0.021
is+0.020
 performance+0.020
fulness+0.020
Neg logit contributions
 trash-0.024
 bruised-0.022
gy-0.022
 extingu-0.022
 Wh-0.022
Token played
Token ID2826
Feature activation-4.83e+00

Pos logit contributions
lf+0.035
isy+0.035
 performance+0.034
is+0.033
fulness+0.033
Neg logit contributions
 trash-0.023
gy-0.023
 bruised-0.022
o-0.022
oc-0.022
Token make
Token ID787
Feature activation-4.61e+00

Pos logit contributions
isy+0.141
lf+0.133
is+0.128
 performance+0.128
pron+0.126
Neg logit contributions
oc-0.073
 trash-0.073
gy-0.072
 Wh-0.072
 extingu-0.068
Token-
Token ID12
Feature activation-2.15e+00

Pos logit contributions
lf+0.111
isy+0.110
pron+0.104
 ceremony+0.101
 performance+0.101
Neg logit contributions
 trash-0.094
 Wh-0.089
o-0.087
oc-0.087
 dece-0.086
Tokenbel
Token ID6667
Feature activation-6.71e+00

Pos logit contributions
lf+0.058
isy+0.058
 performance+0.056
fulness+0.053
 trophy+0.053
Neg logit contributions
 trash-0.038
 extingu-0.037
gy-0.036
oc-0.036
 bruised-0.036
Tokenieve
Token ID12311
Feature activation-3.65e+00

Pos logit contributions
isy+0.133
 couple+0.128
mber+0.127
 wedding+0.122
 ceremony+0.121
Neg logit contributions
Bad-0.147
 dece-0.144
oc-0.141
 trash-0.140
 Or-0.139
Token.
Token ID13
Feature activation-7.34e-01

Pos logit contributions
isy+0.104
lf+0.098
 performance+0.095
pron+0.094
is+0.093
Neg logit contributions
 trash-0.062
oc-0.059
gy-0.058
 extingu-0.057
o-0.055
Token Finally
Token ID9461
Feature activation+1.46e+00

Pos logit contributions
lf+0.020
isy+0.020
 performance+0.019
 achievement+0.018
 trophy+0.018
Neg logit contributions
 trash-0.013
oc-0.012
 extingu-0.012
o-0.012
gy-0.012
Token,
Token ID11
Feature activation-4.09e-01

Pos logit contributions
 trash+0.018
 bit+0.016
 Wh+0.015
 bruised+0.015
 extingu+0.014
Neg logit contributions
isy-0.049
lf-0.046
 performance-0.045
 chords-0.045
pron-0.044
Token they
Token ID484
Feature activation-1.35e+00

Pos logit contributions
isy+0.011
lf+0.011
 performance+0.010
fulness+0.010
is+0.010
Neg logit contributions
 trash-0.008
 bit-0.007
o-0.007
Bad-0.007
 hyd-0.007
Token.
Token ID13
Feature activation-1.04e+00

Pos logit contributions
 extingu+0.003
 trash+0.003
 bruised+0.003
oc+0.003
 dece+0.003
Neg logit contributions
lf-0.004
isy-0.003
 performance-0.003
 trophy-0.003
fulness-0.003
Token Alice
Token ID14862
Feature activation-6.99e-01

Pos logit contributions
lf+0.024
isy+0.024
 performance+0.023
fulness+0.022
 trophy+0.022
Neg logit contributions
 trash-0.022
 extingu-0.022
 bruised-0.021
 dece-0.020
gy-0.020
Token loved
Token ID6151
Feature activation-2.43e+00

Pos logit contributions
lf+0.017
isy+0.017
 performance+0.017
is+0.016
 trophy+0.016
Neg logit contributions
 extingu-0.014
 trash-0.014
 bruised-0.013
 dece-0.013
 cigarettes-0.013
Token how
Token ID703
Feature activation-8.41e-01

Pos logit contributions
isy+0.068
lf+0.064
fulness+0.063
quet+0.060
 performance+0.059
Neg logit contributions
 trash-0.044
o-0.043
 Wh-0.042
 bruised-0.040
 extingu-0.040
Token c
Token ID269
Feature activation-5.15e+00

Pos logit contributions
lf+0.020
isy+0.020
 performance+0.019
is+0.018
fulness+0.018
Neg logit contributions
 trash-0.019
o-0.018
 bruised-0.018
gy-0.017
 Wh-0.017
Tokenudd
Token ID4185
Feature activation-6.68e+00

Pos logit contributions
lf+0.120
 performance+0.113
 trophy+0.106
 accomplishment+0.105
 ceremony+0.104
Neg logit contributions
oc-0.113
o-0.109
gy-0.108
 trash-0.108
c-0.107
Tokenly
Token ID306
Feature activation-3.31e+00

Pos logit contributions
 performance+0.135
lf+0.129
 ceremony+0.121
 wedding+0.120
 achievement+0.120
Neg logit contributions
 trash-0.160
oc-0.146
 Wh-0.144
Bad-0.142
c-0.142
Token and
Token ID290
Feature activation-2.64e+00

Pos logit contributions
lf+0.061
isy+0.061
 performance+0.060
 trophy+0.056
 achievement+0.056
Neg logit contributions
 trash-0.086
 extingu-0.081
 bruised-0.081
oc-0.080
gy-0.080
Token responsive
Token ID21802
Feature activation-2.71e+00

Pos logit contributions
lf+0.059
isy+0.059
 performance+0.058
 trophy+0.056
 achievement+0.054
Neg logit contributions
 trash-0.058
 bruised-0.057
 Wh-0.055
c-0.055
o-0.055
Token her
Token ID607
Feature activation+3.35e-01

Pos logit contributions
lf+0.070
isy+0.068
 performance+0.065
 accomplishment+0.064
 trophy+0.064
Neg logit contributions
 trash-0.051
o-0.049
gy-0.049
 extingu-0.048
 bruised-0.048
Token puppy
Token ID26188
Feature activation-6.22e-01

Pos logit contributions
 trash+0.008
 extingu+0.008
 bruised+0.008
gy+0.008
oc+0.008
Neg logit contributions
lf-0.007
isy-0.007
 performance-0.006
fulness-0.006
 trophy-0.006
Token,
Token ID11
Feature activation-1.86e+00

Pos logit contributions
 extingu+0.072
 trash+0.071
gy+0.069
 bruised+0.068
oc+0.067
Neg logit contributions
lf-0.082
isy-0.081
 performance-0.078
is-0.075
fulness-0.074
Token because
Token ID780
Feature activation+2.35e-01

Pos logit contributions
isy+0.047
lf+0.047
 performance+0.046
 trophy+0.044
fulness+0.044
Neg logit contributions
 trash-0.035
 extingu-0.035
gy-0.034
oc-0.034
 bruised-0.033
Token you
Token ID345
Feature activation+1.21e+00

Pos logit contributions
 trash+0.005
 bruised+0.005
 extingu+0.005
 Wh+0.005
 dece+0.005
Neg logit contributions
isy-0.006
lf-0.005
 performance-0.005
fulness-0.005
pron-0.005
Token have
Token ID423
Feature activation+3.20e-01

Pos logit contributions
 trash+0.024
 extingu+0.024
 bruised+0.023
gy+0.023
oc+0.022
Neg logit contributions
isy-0.030
lf-0.030
 performance-0.029
 trophy-0.028
fulness-0.027
Token wonderful
Token ID7932
Feature activation-2.61e-01

Pos logit contributions
oc+0.007
 extingu+0.007
gy+0.007
 bruised+0.007
 trash+0.007
Neg logit contributions
 performance-0.007
isy-0.007
lf-0.007
 poems-0.006
 trophy-0.006
Token imag
Token ID3590
Feature activation-6.62e+00

Pos logit contributions
lf+0.005
 performance+0.005
isy+0.005
 trophy+0.004
 accomplishment+0.004
Neg logit contributions
 extingu-0.007
gy-0.007
 trash-0.007
oc-0.006
 bruised-0.006
Tokeninations
Token ID7352
Feature activation-3.78e+00

Pos logit contributions
isy+0.099
lf+0.095
 medal+0.093
 avail+0.092
 vows+0.091
Neg logit contributions
o-0.194
oc-0.181
c-0.179
enn-0.171
 cigarettes-0.171
Token."
Token ID526
Feature activation-3.86e-01

Pos logit contributions
lf+0.102
isy+0.102
 performance+0.099
 trophy+0.094
fulness+0.094
Neg logit contributions
 trash-0.066
 extingu-0.064
 bruised-0.062
gy-0.062
oc-0.061
Token The
Token ID383
Feature activation-4.11e-02

Pos logit contributions
isy+0.010
lf+0.010
 performance+0.009
fulness+0.009
is+0.009
Neg logit contributions
 extingu-0.007
 trash-0.007
gy-0.007
 dece-0.007
 bruised-0.007
Token boy
Token ID2933
Feature activation-5.32e-01

Pos logit contributions
lf+0.001
isy+0.001
 performance+0.001
 trophy+0.001
fulness+0.001
Neg logit contributions
 trash-0.001
 extingu-0.001
gy-0.001
 bruised-0.001
oc-0.001
Token and
Token ID290
Feature activation-1.21e+00

Pos logit contributions
isy+0.012
lf+0.012
 performance+0.011
 trophy+0.010
fulness+0.010
Neg logit contributions
 trash-0.012
 extingu-0.012
gy-0.012
 bruised-0.012
oc-0.012
Token years
Token ID812
Feature activation+2.17e+00

Pos logit contributions
lf+0.000
isy+0.000
 performance+0.000
is+0.000
 trophy+0.000
Neg logit contributions
 extingu-0.000
 trash-0.000
gy-0.000
 bruised-0.000
 dece-0.000
Token old
Token ID1468
Feature activation+1.96e+00

Pos logit contributions
 trash+0.054
 extingu+0.052
 bruised+0.051
gy+0.048
oc+0.048
Neg logit contributions
isy-0.045
lf-0.043
 performance-0.041
fulness-0.041
ves-0.039
Token and
Token ID290
Feature activation-1.23e+00

Pos logit contributions
 dece+0.041
 trash+0.041
 extingu+0.040
 bruised+0.039
fired+0.039
Neg logit contributions
lf-0.045
isy-0.044
 performance-0.042
 trophy-0.041
 couple-0.041
Token loved
Token ID6151
Feature activation-1.59e+00

Pos logit contributions
isy+0.036
 performance+0.036
is+0.035
 achievement+0.034
quet+0.034
Neg logit contributions
 trash-0.019
o-0.019
 bruised-0.019
 Wh-0.018
gy-0.018
Token to
Token ID284
Feature activation-1.86e+00

Pos logit contributions
isy+0.051
fulness+0.046
lf+0.046
ves+0.044
is+0.044
Neg logit contributions
 trash-0.026
o-0.024
 Wh-0.024
 extingu-0.023
 cigarettes-0.023
Token design
Token ID1486
Feature activation-6.58e+00

Pos logit contributions
isy+0.052
is+0.050
fulness+0.049
lf+0.048
 accomplishment+0.047
Neg logit contributions
 trash-0.033
gy-0.032
 extingu-0.031
 Wh-0.029
oc-0.029
Token.
Token ID13
Feature activation-2.10e+00

Pos logit contributions
isy+0.162
lf+0.151
 performance+0.148
fulness+0.142
 ceremony+0.141
Neg logit contributions
 trash-0.147
 extingu-0.132
oc-0.132
 dece-0.130
gy-0.127
Token Every
Token ID3887
Feature activation-1.46e+00

Pos logit contributions
isy+0.058
lf+0.057
 performance+0.056
fulness+0.053
 trophy+0.053
Neg logit contributions
 trash-0.037
 extingu-0.036
gy-0.035
 bruised-0.034
oc-0.034
Token day
Token ID1110
Feature activation-2.43e+00

Pos logit contributions
isy+0.029
lf+0.027
LC+0.026
quet+0.026
is+0.025
Neg logit contributions
 trash-0.037
 bit-0.036
oc-0.036
o-0.036
c-0.035
Token he
Token ID339
Feature activation-2.17e+00

Pos logit contributions
isy+0.057
lf+0.056
 performance+0.054
is+0.051
fulness+0.051
Neg logit contributions
 trash-0.052
 extingu-0.051
oc-0.050
gy-0.050
 bruised-0.050
Token would
Token ID561
Feature activation-2.80e+00

Pos logit contributions
isy+0.051
lf+0.050
 performance+0.049
fulness+0.048
 accomplishment+0.046
Neg logit contributions
 trash-0.046
 extingu-0.045
gy-0.045
oc-0.044
o-0.043
Token He
Token ID679
Feature activation-1.24e+00

Pos logit contributions
lf+0.009
 performance+0.008
fulness+0.008
isy+0.008
 trophy+0.008
Neg logit contributions
 trash-0.009
 bruised-0.009
 extingu-0.009
 dece-0.008
Bad-0.008
Token loved
Token ID6151
Feature activation-2.10e+00

Pos logit contributions
lf+0.030
isy+0.029
 performance+0.028
 trophy+0.027
 wedding+0.026
Neg logit contributions
 extingu-0.027
 trash-0.025
 bruised-0.025
 dece-0.024
oc-0.024
Token playing
Token ID2712
Feature activation-4.61e+00

Pos logit contributions
isy+0.058
lf+0.054
fulness+0.052
 performance+0.051
is+0.050
Neg logit contributions
 trash-0.039
 extingu-0.036
 bruised-0.036
gy-0.036
o-0.035
Token make
Token ID787
Feature activation-4.99e+00

Pos logit contributions
lf+0.104
isy+0.100
 performance+0.098
 trophy+0.094
is+0.091
Neg logit contributions
 trash-0.103
 bruised-0.102
 extingu-0.102
gy-0.100
 dece-0.099
Token-
Token ID12
Feature activation-3.24e+00

Pos logit contributions
isy+0.096
lf+0.094
 performance+0.088
fulness+0.084
pron+0.084
Neg logit contributions
 trash-0.130
 extingu-0.124
oc-0.123
 bruised-0.121
 dece-0.121
Tokenbel
Token ID6667
Feature activation-6.57e+00

Pos logit contributions
lf+0.085
isy+0.085
 performance+0.082
 accomplishment+0.079
fulness+0.079
Neg logit contributions
 trash-0.058
gy-0.057
oc-0.056
 extingu-0.056
o-0.056
Tokenieve
Token ID12311
Feature activation-3.54e+00

Pos logit contributions
isy+0.129
 couple+0.120
 wedding+0.118
 vows+0.117
mber+0.117
Neg logit contributions
 dece-0.149
Bad-0.145
oc-0.144
 trash-0.143
 Or-0.142
Token with
Token ID351
Feature activation-1.34e+00

Pos logit contributions
lf+0.078
isy+0.076
 performance+0.074
 trophy+0.070
fulness+0.069
Neg logit contributions
 trash-0.081
 extingu-0.080
 bruised-0.079
gy-0.078
oc-0.077
Token his
Token ID465
Feature activation-1.04e+00

Pos logit contributions
isy+0.031
lf+0.031
 performance+0.030
fulness+0.028
is+0.028
Neg logit contributions
 trash-0.029
 extingu-0.028
 bruised-0.028
gy-0.027
oc-0.027
Token friends
Token ID2460
Feature activation-2.31e+00

Pos logit contributions
lf+0.020
isy+0.020
 performance+0.019
 trophy+0.018
fulness+0.017
Neg logit contributions
 trash-0.026
 extingu-0.026
 bruised-0.026
gy-0.026
oc-0.025
Token.
Token ID13
Feature activation-1.93e+00

Pos logit contributions
isy+0.066
lf+0.064
 performance+0.063
 accomplishment+0.061
is+0.060
Neg logit contributions
 trash-0.037
gy-0.036
 extingu-0.036
oc-0.035
 bruised-0.035
Token imagination
Token ID13843
Feature activation-2.96e+00

Pos logit contributions
isy+0.012
lf+0.012
 performance+0.011
fulness+0.010
is+0.010
Neg logit contributions
 trash-0.016
 extingu-0.015
 bruised-0.015
gy-0.015
oc-0.015
Token.
Token ID13
Feature activation-1.81e+00

Pos logit contributions
isy+0.085
lf+0.084
 performance+0.082
 accomplishment+0.079
 trophy+0.079
Neg logit contributions
 extingu-0.044
 trash-0.044
gy-0.044
 bruised-0.042
o-0.041
Token She
Token ID1375
Feature activation-1.84e+00

Pos logit contributions
isy+0.048
lf+0.048
 performance+0.046
fulness+0.044
 trophy+0.044
Neg logit contributions
 trash-0.033
 extingu-0.032
gy-0.032
 bruised-0.031
oc-0.031
Token loved
Token ID6151
Feature activation-2.70e+00

Pos logit contributions
lf+0.048
isy+0.047
 performance+0.046
fulness+0.044
 trophy+0.043
Neg logit contributions
 trash-0.034
 extingu-0.034
 bruised-0.033
gy-0.033
oc-0.032
Token to
Token ID284
Feature activation-2.71e+00

Pos logit contributions
isy+0.084
fulness+0.075
lf+0.074
ves+0.072
quet+0.071
Neg logit contributions
 trash-0.043
 cigarettes-0.039
o-0.039
 extingu-0.039
 Wh-0.038
Token design
Token ID1486
Feature activation-6.57e+00

Pos logit contributions
isy+0.063
is+0.059
fulness+0.058
lf+0.058
 accomplishment+0.055
Neg logit contributions
gy-0.057
 trash-0.056
 extingu-0.055
oc-0.053
c-0.052
Token things
Token ID1243
Feature activation-4.06e+00

Pos logit contributions
isy+0.151
lf+0.146
 performance+0.139
fulness+0.134
 trophy+0.133
Neg logit contributions
 trash-0.149
 extingu-0.137
 dece-0.135
oc-0.134
gy-0.133
Token and
Token ID290
Feature activation-2.72e+00

Pos logit contributions
lf+0.115
isy+0.115
 performance+0.109
pron+0.105
 accomplishment+0.103
Neg logit contributions
 trash-0.067
 extingu-0.065
 bruised-0.063
gy-0.062
oc-0.060
Token one
Token ID530
Feature activation-2.32e+00

Pos logit contributions
isy+0.066
lf+0.060
is+0.058
fulness+0.058
quet+0.058
Neg logit contributions
 trash-0.058
 bit-0.054
gy-0.054
oc-0.053
 cigarettes-0.053
Token day
Token ID1110
Feature activation-9.35e-01

Pos logit contributions
isy+0.042
lf+0.040
 performance+0.037
fulness+0.036
is+0.036
Neg logit contributions
 trash-0.064
oc-0.061
 extingu-0.061
 bruised-0.060
 bit-0.059
Token she
Token ID673
Feature activation-1.85e+00

Pos logit contributions
isy+0.019
lf+0.017
 performance+0.016
 medal+0.015
 trophy+0.015
Neg logit contributions
 trash-0.024
 bruised-0.022
fired-0.022
 dece-0.022
 bit-0.022
Token of
Token ID286
Feature activation-4.00e-01

Pos logit contributions
isy+0.058
lf+0.057
fters+0.053
ves+0.053
fs+0.053
Neg logit contributions
 extingu-0.043
oc-0.043
o-0.041
 trash-0.040
 bruised-0.040
Token friends
Token ID2460
Feature activation-2.57e+00

Pos logit contributions
isy+0.011
lf+0.010
pron+0.010
fulness+0.010
mber+0.010
Neg logit contributions
 trash-0.007
 Wh-0.007
Bad-0.006
 bruised-0.006
o-0.006
Token and
Token ID290
Feature activation-3.23e+00

Pos logit contributions
lf+0.071
isy+0.071
 performance+0.069
fulness+0.065
 trophy+0.065
Neg logit contributions
 trash-0.043
 extingu-0.042
gy-0.041
oc-0.041
 bruised-0.041
Token loved
Token ID6151
Feature activation-3.29e+00

Pos logit contributions
isy+0.085
lf+0.079
is+0.079
fulness+0.075
 performance+0.075
Neg logit contributions
gy-0.064
 trash-0.062
o-0.062
 Wh-0.062
 bruised-0.061
Token to
Token ID284
Feature activation-3.32e+00

Pos logit contributions
isy+0.105
lf+0.095
fulness+0.093
fs+0.090
quet+0.089
Neg logit contributions
o-0.050
 Wh-0.049
 trash-0.047
gy-0.046
 extingu-0.043
Token create
Token ID2251
Feature activation-6.56e+00

Pos logit contributions
isy+0.086
fs+0.081
fulness+0.079
is+0.077
LC+0.077
Neg logit contributions
gy-0.067
oc-0.062
 Or-0.059
 bit-0.058
 extingu-0.057
Token beautiful
Token ID4950
Feature activation-2.31e+00

Pos logit contributions
isy+0.151
lf+0.147
 performance+0.137
fulness+0.133
pron+0.132
Neg logit contributions
 trash-0.148
 extingu-0.137
oc-0.137
 dece-0.137
gy-0.133
Token things
Token ID1243
Feature activation-3.52e+00

Pos logit contributions
isy+0.045
lf+0.042
fulness+0.040
pron+0.039
 performance+0.038
Neg logit contributions
 trash-0.060
oc-0.059
 extingu-0.056
gy-0.056
c-0.056
Token together
Token ID1978
Feature activation-2.91e+00

Pos logit contributions
lf+0.113
isy+0.111
pron+0.106
LC+0.103
 performance+0.102
Neg logit contributions
 extingu-0.043
gy-0.041
 hyd-0.040
 trash-0.040
o-0.040
Token.
Token ID13
Feature activation-1.96e+00

Pos logit contributions
isy+0.090
lf+0.089
 performance+0.086
pron+0.085
 accomplishment+0.084
Neg logit contributions
 trash-0.036
oc-0.036
 extingu-0.035
gy-0.034
 bit-0.033
Token<|endoftext|>
Token ID50256
Feature activation+1.29e+00

Pos logit contributions
isy+0.051
lf+0.050
 performance+0.049
fulness+0.049
is+0.047
Neg logit contributions
 trash-0.036
 extingu-0.035
 bruised-0.035
gy-0.033
 dece-0.033
Token to
Token ID284
Feature activation-2.88e+00

Pos logit contributions
isy+0.069
fulness+0.062
lf+0.060
quet+0.059
ves+0.058
Neg logit contributions
 trash-0.044
 Wh-0.042
o-0.040
 extingu-0.040
gy-0.039
Token use
Token ID779
Feature activation-2.29e+00

Pos logit contributions
isy+0.067
lf+0.064
is+0.062
fulness+0.060
pron+0.059
Neg logit contributions
gy-0.063
 trash-0.061
 extingu-0.061
oc-0.059
 hyd-0.058
Token his
Token ID465
Feature activation-9.35e-01

Pos logit contributions
isy+0.053
lf+0.052
 performance+0.050
fulness+0.047
is+0.047
Neg logit contributions
 trash-0.050
 extingu-0.049
 bruised-0.048
gy-0.048
oc-0.047
Token imagination
Token ID13843
Feature activation-3.30e+00

Pos logit contributions
isy+0.017
lf+0.017
 performance+0.016
fulness+0.015
 trophy+0.015
Neg logit contributions
 trash-0.025
 extingu-0.024
gy-0.024
 bruised-0.024
oc-0.023
Token to
Token ID284
Feature activation-2.50e+00

Pos logit contributions
isy+0.094
lf+0.091
 performance+0.088
 accomplishment+0.086
 trophy+0.085
Neg logit contributions
gy-0.050
 trash-0.048
 extingu-0.048
oc-0.047
c-0.046
Token create
Token ID2251
Feature activation-6.52e+00

Pos logit contributions
isy+0.060
lf+0.057
pron+0.054
fulness+0.054
is+0.053
Neg logit contributions
 trash-0.051
gy-0.050
 extingu-0.049
oc-0.048
 hyd-0.047
Token his
Token ID465
Feature activation-1.59e+00

Pos logit contributions
isy+0.142
lf+0.140
 performance+0.133
fulness+0.126
is+0.125
Neg logit contributions
 trash-0.152
 extingu-0.145
oc-0.143
 bruised-0.142
gy-0.141
Token own
Token ID898
Feature activation-1.37e+00

Pos logit contributions
lf+0.027
isy+0.026
 performance+0.026
 trophy+0.023
fulness+0.023
Neg logit contributions
 extingu-0.044
 trash-0.044
 bruised-0.043
gy-0.043
oc-0.042
Token news
Token ID1705
Feature activation-2.69e+00

Pos logit contributions
lf+0.022
isy+0.022
 performance+0.021
fulness+0.019
 trophy+0.019
Neg logit contributions
 trash-0.039
 extingu-0.039
 bruised-0.038
gy-0.038
oc-0.038
Token.
Token ID13
Feature activation-2.13e+00

Pos logit contributions
isy+0.077
lf+0.074
 performance+0.071
pron+0.071
is+0.070
Neg logit contributions
 trash-0.042
oc-0.041
 extingu-0.041
gy-0.037
 bit-0.037
Token<|endoftext|>
Token ID50256
Feature activation+1.05e+00

Pos logit contributions
lf+0.051
isy+0.051
fulness+0.050
 performance+0.049
 trophy+0.048
Neg logit contributions
 trash-0.043
 extingu-0.041
 bruised-0.041
gy-0.039
 dece-0.039
Token red
Token ID2266
Feature activation-1.54e+00

Pos logit contributions
isy+0.019
lf+0.019
 performance+0.017
fulness+0.017
is+0.017
Neg logit contributions
 trash-0.025
 extingu-0.024
gy-0.024
 bruised-0.024
oc-0.023
Token cape
Token ID36023
Feature activation-1.07e+00

Pos logit contributions
isy+0.029
lf+0.028
 performance+0.027
fulness+0.026
is+0.025
Neg logit contributions
 trash-0.040
 extingu-0.039
gy-0.039
oc-0.039
 bruised-0.038
Token and
Token ID290
Feature activation-7.26e-01

Pos logit contributions
isy+0.028
lf+0.028
 performance+0.027
 accomplishment+0.026
is+0.026
Neg logit contributions
gy-0.019
 trash-0.018
 extingu-0.018
oc-0.018
o-0.017
Token make
Token ID787
Feature activation-5.36e+00

Pos logit contributions
isy+0.016
lf+0.016
 performance+0.015
is+0.015
fulness+0.014
Neg logit contributions
 trash-0.017
 extingu-0.016
gy-0.016
 bruised-0.016
oc-0.016
Token-
Token ID12
Feature activation-2.29e+00

Pos logit contributions
isy+0.127
lf+0.117
pron+0.115
quet+0.115
 ceremony+0.114
Neg logit contributions
 trash-0.113
 Wh-0.108
oc-0.107
 dece-0.105
c-0.102
Tokenbel
Token ID6667
Feature activation-6.41e+00

Pos logit contributions
lf+0.065
isy+0.064
 performance+0.062
 accomplishment+0.061
 achievement+0.060
Neg logit contributions
 trash-0.036
gy-0.036
oc-0.036
o-0.036
 bruised-0.035
Tokenieve
Token ID12311
Feature activation-3.72e+00

Pos logit contributions
isy+0.127
 couple+0.124
mber+0.123
 ceremony+0.118
 wedding+0.117
Neg logit contributions
Bad-0.138
 dece-0.135
 trash-0.132
oc-0.132
 freed-0.132
Token he
Token ID339
Feature activation-1.24e+00

Pos logit contributions
isy+0.101
lf+0.094
is+0.091
 performance+0.091
pron+0.090
Neg logit contributions
 trash-0.066
oc-0.065
gy-0.063
 extingu-0.061
 bruised-0.060
Token had
Token ID550
Feature activation-5.94e-01

Pos logit contributions
isy+0.033
lf+0.033
 performance+0.031
is+0.030
fulness+0.030
Neg logit contributions
 trash-0.022
gy-0.022
oc-0.021
 bruised-0.021
 extingu-0.021
Token super
Token ID2208
Feature activation-1.95e+00

Pos logit contributions
isy+0.016
lf+0.016
 performance+0.015
 trophy+0.015
fulness+0.015
Neg logit contributions
 trash-0.010
gy-0.010
 extingu-0.010
 bruised-0.010
oc-0.010
Tokenpowers
Token ID30132
Feature activation-1.62e+00

Pos logit contributions
lf+0.044
isy+0.043
 performance+0.038
is+0.038
fulness+0.038
Neg logit contributions
 trash-0.045
oc-0.042
 dece-0.041
 bruised-0.041
gy-0.041
Tokenel
Token ID417
Feature activation-6.28e-01

Pos logit contributions
isy+0.039
lf+0.038
 performance+0.037
 trophy+0.035
fulness+0.035
Neg logit contributions
 trash-0.032
 extingu-0.031
gy-0.030
oc-0.030
 bruised-0.030
Token cr
Token ID1067
Feature activation-2.49e+00

Pos logit contributions
isy+0.010
lf+0.010
 performance+0.009
is+0.009
fulness+0.009
Neg logit contributions
 extingu-0.018
 trash-0.018
 bruised-0.018
Bad-0.017
oc-0.017
Tokenay
Token ID323
Feature activation-3.27e+00

Pos logit contributions
lf+0.042
isy+0.041
 performance+0.040
 trophy+0.036
fulness+0.036
Neg logit contributions
 trash-0.069
 extingu-0.068
gy-0.067
oc-0.067
 bruised-0.066
Tokenons
Token ID684
Feature activation-2.24e+00

Pos logit contributions
isy+0.056
lf+0.054
 performance+0.053
 trophy+0.050
 accomplishment+0.049
Neg logit contributions
 trash-0.088
oc-0.086
o-0.085
c-0.084
 extingu-0.084
Token to
Token ID284
Feature activation-1.82e+00

Pos logit contributions
lf+0.069
isy+0.067
 performance+0.066
 accomplishment+0.064
 achievement+0.063
Neg logit contributions
 trash-0.031
gy-0.030
 extingu-0.030
o-0.030
c-0.029
Token create
Token ID2251
Feature activation-6.39e+00

Pos logit contributions
isy+0.044
lf+0.043
 performance+0.041
fulness+0.040
 accomplishment+0.040
Neg logit contributions
 trash-0.037
gy-0.035
 extingu-0.035
c-0.035
oc-0.035
Token beautiful
Token ID4950
Feature activation-2.15e+00

Pos logit contributions
isy+0.135
lf+0.133
 performance+0.126
 trophy+0.120
fulness+0.119
Neg logit contributions
 trash-0.155
 extingu-0.144
 dece-0.144
oc-0.142
c-0.140
Token pictures
Token ID5986
Feature activation-4.05e+00

Pos logit contributions
isy+0.036
lf+0.035
 performance+0.033
fulness+0.032
 trophy+0.031
Neg logit contributions
 trash-0.060
oc-0.059
 extingu-0.058
gy-0.058
 dece-0.057
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
isy+0.128
lf+0.125
 accomplishment+0.124
 performance+0.123
 achievement+0.122
Neg logit contributions
o-0.047
c-0.046
 extingu-0.043
 trash-0.043
 Or-0.042
Token<|endoftext|>
Token ID50256
Feature activation+1.57e+00

Pos logit contributions
isy+0.038
lf+0.038
 performance+0.036
fulness+0.035
 trophy+0.035
Neg logit contributions
 trash-0.021
 extingu-0.021
 bruised-0.020
gy-0.020
oc-0.020
TokenOnce
Token ID7454
Feature activation+5.31e-01

Pos logit contributions
 extingu+0.028
 trash+0.028
 bruised+0.027
gy+0.026
 dece+0.026
Neg logit contributions
lf-0.042
isy-0.041
 performance-0.040
fulness-0.038
is-0.038
Token things
Token ID1243
Feature activation-3.91e+00

Pos logit contributions
isy+0.156
lf+0.144
 performance+0.143
fulness+0.140
 ceremony+0.137
Neg logit contributions
 trash-0.128
oc-0.111
 dece-0.111
 cages-0.109
 extingu-0.109
Token.
Token ID13
Feature activation-1.52e+00

Pos logit contributions
isy+0.137
lf+0.136
pron+0.129
 performance+0.129
 accomplishment+0.127
Neg logit contributions
 trash-0.040
 extingu-0.035
o-0.035
 hyd-0.032
gy-0.032
Token She
Token ID1375
Feature activation-2.13e+00

Pos logit contributions
lf+0.040
isy+0.040
 performance+0.038
fulness+0.037
 trophy+0.036
Neg logit contributions
 trash-0.028
 extingu-0.028
gy-0.027
 bruised-0.027
oc-0.027
Token wanted
Token ID2227
Feature activation-2.81e+00

Pos logit contributions
isy+0.062
 performance+0.060
fulness+0.059
 accomplishment+0.058
 achievement+0.058
Neg logit contributions
 trash-0.033
gy-0.033
oc-0.033
o-0.032
 bit-0.031
Token to
Token ID284
Feature activation-2.38e+00

Pos logit contributions
isy+0.086
lf+0.082
 performance+0.077
 accomplishment+0.076
fulness+0.076
Neg logit contributions
 trash-0.047
 extingu-0.040
 cigarettes-0.040
o-0.039
 bruised-0.038
Token design
Token ID1486
Feature activation-6.36e+00

Pos logit contributions
isy+0.063
fulness+0.059
mber+0.056
fs+0.055
LC+0.055
Neg logit contributions
 trash-0.044
 bit-0.040
 Help-0.039
 extingu-0.039
 hyd-0.039
Token something
Token ID1223
Feature activation-3.43e+00

Pos logit contributions
isy+0.174
lf+0.171
 performance+0.164
fulness+0.158
 trophy+0.157
Neg logit contributions
 trash-0.118
 dece-0.103
 extingu-0.103
 bruised-0.102
 Wh-0.099
Token new
Token ID649
Feature activation-1.20e+00

Pos logit contributions
lf+0.077
isy+0.075
 performance+0.069
fulness+0.068
 accomplishment+0.067
Neg logit contributions
 trash-0.082
 extingu-0.072
 bit-0.072
 dece-0.071
 cigarettes-0.070
Token and
Token ID290
Feature activation-2.54e+00

Pos logit contributions
lf+0.033
isy+0.032
 performance+0.031
fulness+0.030
 trophy+0.030
Neg logit contributions
 trash-0.021
 extingu-0.021
gy-0.020
 bruised-0.020
oc-0.020
Token fun
Token ID1257
Feature activation-4.62e+00

Pos logit contributions
isy+0.060
lf+0.057
fulness+0.053
 performance+0.053
is+0.052
Neg logit contributions
 trash-0.061
 bit-0.057
 dece-0.053
 bruised-0.052
 cigarettes-0.052
Token,
Token ID11
Feature activation-2.88e+00

Pos logit contributions
isy+0.140
isin+0.123
becca+0.120
mber+0.119
LC+0.119
Neg logit contributions
 trash-0.075
 cigarettes-0.067
packs-0.065
gy-0.064
 extingu-0.063
Token her
Token ID607
Feature activation+6.74e-01

Pos logit contributions
lf+0.043
isy+0.041
 performance+0.038
pron+0.038
 trophy+0.037
Neg logit contributions
 trash-0.041
o-0.037
 Wh-0.037
c-0.037
 dece-0.036
Token even
Token ID772
Feature activation+1.43e-02

Pos logit contributions
 trash+0.013
 extingu+0.013
gy+0.013
 bruised+0.012
oc+0.012
Neg logit contributions
lf-0.017
isy-0.017
 performance-0.016
fulness-0.016
is-0.015
Token more
Token ID517
Feature activation-9.05e-01

Pos logit contributions
 trash+0.000
 extingu+0.000
 bruised+0.000
gy+0.000
oc+0.000
Neg logit contributions
lf-0.000
isy-0.000
 performance-0.000
fulness-0.000
 trophy-0.000
Token things
Token ID1243
Feature activation-2.19e+00

Pos logit contributions
lf+0.019
isy+0.018
 performance+0.017
fulness+0.016
 achievement+0.016
Neg logit contributions
 trash-0.023
 extingu-0.021
c-0.020
 bruised-0.020
 dece-0.020
Token to
Token ID284
Feature activation-1.72e+00

Pos logit contributions
lf+0.060
isy+0.058
 performance+0.055
is+0.052
pron+0.052
Neg logit contributions
 trash-0.040
 extingu-0.039
 bruised-0.038
gy-0.036
o-0.036
Token design
Token ID1486
Feature activation-6.32e+00

Pos logit contributions
isy+0.041
lf+0.039
 performance+0.036
pron+0.036
fulness+0.036
Neg logit contributions
 trash-0.035
 extingu-0.034
gy-0.033
oc-0.032
 dece-0.032
Token.
Token ID13
Feature activation-1.11e+00

Pos logit contributions
isy+0.161
lf+0.160
 performance+0.153
 trophy+0.145
fulness+0.144
Neg logit contributions
 trash-0.124
 extingu-0.116
gy-0.113
 bruised-0.113
 dece-0.112
Token She
Token ID1375
Feature activation-1.27e+00

Pos logit contributions
isy+0.025
lf+0.024
 performance+0.024
fulness+0.023
 accomplishment+0.023
Neg logit contributions
 trash-0.024
 extingu-0.024
 bruised-0.023
gy-0.023
 dece-0.023
Token brought
Token ID3181
Feature activation-2.38e+00

Pos logit contributions
isy+0.033
lf+0.033
 performance+0.032
fulness+0.032
 trophy+0.030
Neg logit contributions
 trash-0.022
 extingu-0.022
oc-0.022
gy-0.022
o-0.021
Token out
Token ID503
Feature activation+1.73e+00

Pos logit contributions
lf+0.056
isy+0.055
 performance+0.051
pron+0.049
fulness+0.049
Neg logit contributions
 trash-0.054
 extingu-0.050
gy-0.049
 bruised-0.048
 dece-0.048
Token some
Token ID617
Feature activation-8.72e-02

Pos logit contributions
 trash+0.036
 extingu+0.036
oc+0.035
gy+0.035
 bruised+0.035
Neg logit contributions
lf-0.040
isy-0.040
 performance-0.039
 trophy-0.037
fulness-0.037
Token Lily
Token ID20037
Feature activation+2.39e-01

Pos logit contributions
isy+0.001
lf+0.001
 performance+0.000
fulness+0.000
is+0.000
Neg logit contributions
 extingu-0.000
oc-0.000
 trash-0.000
 bruised-0.000
 hyd-0.000
Token.
Token ID13
Feature activation-2.60e-01

Pos logit contributions
 extingu+0.006
 trash+0.006
Bad+0.006
 dece+0.006
 bruised+0.006
Neg logit contributions
isy-0.005
lf-0.005
is-0.004
 performance-0.004
fulness-0.004
Token She
Token ID1375
Feature activation-1.23e+00

Pos logit contributions
lf+0.006
isy+0.006
 performance+0.006
fulness+0.006
 trophy+0.006
Neg logit contributions
 extingu-0.005
 trash-0.005
oc-0.005
 bruised-0.005
gy-0.005
Token loved
Token ID6151
Feature activation-1.96e+00

Pos logit contributions
lf+0.029
isy+0.029
 performance+0.027
is+0.026
 trophy+0.026
Neg logit contributions
 extingu-0.027
 trash-0.026
 bruised-0.025
oc-0.025
gy-0.024
Token to
Token ID284
Feature activation-2.49e+00

Pos logit contributions
isy+0.060
fulness+0.057
lf+0.056
ves+0.054
 performance+0.053
Neg logit contributions
 trash-0.032
 Wh-0.030
o-0.029
 cigarettes-0.028
 bruised-0.028
Token create
Token ID2251
Feature activation-6.31e+00

Pos logit contributions
fulness+0.067
isy+0.067
is+0.065
lf+0.063
 accomplishment+0.063
Neg logit contributions
 trash-0.043
gy-0.043
 extingu-0.040
 Wh-0.038
oc-0.038
Token things
Token ID1243
Feature activation-3.84e+00

Pos logit contributions
isy+0.149
lf+0.144
fulness+0.138
 performance+0.137
 ceremony+0.133
Neg logit contributions
 trash-0.143
 dece-0.126
c-0.125
 extingu-0.122
oc-0.120
Token with
Token ID351
Feature activation+1.82e-01

Pos logit contributions
lf+0.124
isy+0.122
 performance+0.117
pron+0.116
 vows+0.116
Neg logit contributions
 trash-0.050
 extingu-0.045
c-0.044
 bruised-0.042
gy-0.041
Token her
Token ID607
Feature activation+1.94e-01

Pos logit contributions
 trash+0.005
 extingu+0.004
 bruised+0.004
gy+0.004
oc+0.004
Neg logit contributions
isy-0.004
lf-0.004
 performance-0.003
fulness-0.003
 trophy-0.003
Token toys
Token ID14958
Feature activation-1.49e+00

Pos logit contributions
 trash+0.004
 extingu+0.004
 bruised+0.004
gy+0.004
oc+0.004
Neg logit contributions
lf-0.004
isy-0.004
 performance-0.004
 trophy-0.004
fulness-0.004
Token.
Token ID13
Feature activation-2.22e+00

Pos logit contributions
isy+0.043
lf+0.043
 performance+0.042
fulness+0.040
 accomplishment+0.040
Neg logit contributions
 trash-0.024
 extingu-0.022
gy-0.022
 bruised-0.022
oc-0.021
Token things
Token ID1243
Feature activation-3.83e+00

Pos logit contributions
isy+0.143
lf+0.138
 performance+0.134
fulness+0.132
 trophy+0.127
Neg logit contributions
 trash-0.123
 extingu-0.112
 dece-0.110
oc-0.109
gy-0.108
Token.
Token ID13
Feature activation-1.41e+00

Pos logit contributions
isy+0.135
lf+0.134
pron+0.128
mber+0.128
 vows+0.127
Neg logit contributions
 trash-0.040
 extingu-0.035
 hyd-0.032
o-0.032
c-0.031
Token She
Token ID1375
Feature activation-2.12e+00

Pos logit contributions
lf+0.038
isy+0.038
 performance+0.036
fulness+0.035
 trophy+0.034
Neg logit contributions
 trash-0.026
 extingu-0.025
gy-0.025
 bruised-0.024
oc-0.024
Token liked
Token ID8288
Feature activation-2.71e+00

Pos logit contributions
isy+0.061
 performance+0.060
fulness+0.059
 accomplishment+0.058
lf+0.058
Neg logit contributions
 trash-0.034
gy-0.033
oc-0.033
o-0.032
 bit-0.031
Token to
Token ID284
Feature activation-2.89e+00

Pos logit contributions
isy+0.094
fulness+0.087
lf+0.085
 accomplishment+0.083
 avail+0.083
Neg logit contributions
 trash-0.035
o-0.031
 Wh-0.030
 cigarettes-0.029
 extingu-0.028
Token create
Token ID2251
Feature activation-6.31e+00

Pos logit contributions
isy+0.075
fulness+0.072
mber+0.068
fs+0.066
 couple+0.066
Neg logit contributions
 trash-0.054
gy-0.051
 extingu-0.051
 bit-0.050
 hyd-0.049
Token things
Token ID1243
Feature activation-3.91e+00

Pos logit contributions
isy+0.143
lf+0.139
 performance+0.133
fulness+0.131
 trophy+0.127
Neg logit contributions
 trash-0.148
 dece-0.134
 extingu-0.133
oc-0.131
gy-0.129
Token with
Token ID351
Feature activation+3.59e-01

Pos logit contributions
lf+0.124
isy+0.123
pron+0.116
 performance+0.116
 vows+0.114
Neg logit contributions
 trash-0.054
 extingu-0.051
 bruised-0.047
gy-0.046
c-0.046
Token her
Token ID607
Feature activation+8.52e-03

Pos logit contributions
 trash+0.009
 extingu+0.009
gy+0.009
 bruised+0.009
oc+0.009
Neg logit contributions
lf-0.007
isy-0.007
 performance-0.007
fulness-0.006
 trophy-0.006
Token friends
Token ID2460
Feature activation-2.32e+00

Pos logit contributions
 trash+0.000
 extingu+0.000
gy+0.000
 bruised+0.000
oc+0.000
Neg logit contributions
isy-0.000
lf-0.000
 performance-0.000
fulness-0.000
is-0.000
Token and
Token ID290
Feature activation-2.20e+00

Pos logit contributions
isy+0.072
lf+0.071
 performance+0.069
 accomplishment+0.069
fulness+0.068
Neg logit contributions
 trash-0.032
gy-0.031
 extingu-0.030
o-0.030
c-0.029
Token special
Token ID2041
Feature activation-1.75e+00

Pos logit contributions
lf+0.074
isy+0.071
fulness+0.065
 performance+0.063
pron+0.063
Neg logit contributions
 trash-0.088
 extingu-0.080
 bit-0.079
 dece-0.078
 bruised-0.077
Token.
Token ID13
Feature activation-1.51e+00

Pos logit contributions
isy+0.052
lf+0.052
 performance+0.049
is+0.048
pron+0.048
Neg logit contributions
 extingu-0.026
 trash-0.026
gy-0.024
oc-0.023
 bruised-0.023
Token She
Token ID1375
Feature activation-1.50e+00

Pos logit contributions
lf+0.038
isy+0.038
 performance+0.036
fulness+0.035
 trophy+0.034
Neg logit contributions
 trash-0.029
 extingu-0.029
 bruised-0.028
gy-0.028
oc-0.028
Token wanted
Token ID2227
Feature activation-2.76e+00

Pos logit contributions
isy+0.043
lf+0.042
 performance+0.041
fulness+0.040
 accomplishment+0.039
Neg logit contributions
 trash-0.024
gy-0.024
 extingu-0.023
oc-0.023
 bruised-0.023
Token to
Token ID284
Feature activation-2.12e+00

Pos logit contributions
isy+0.079
lf+0.077
 performance+0.072
fulness+0.071
 accomplishment+0.070
Neg logit contributions
 trash-0.049
 extingu-0.044
 bruised-0.043
 cigarettes-0.043
o-0.042
Token design
Token ID1486
Feature activation-6.30e+00

Pos logit contributions
isy+0.056
fulness+0.053
mber+0.052
fs+0.051
LC+0.050
Neg logit contributions
 trash-0.035
 extingu-0.035
 bit-0.034
 Or-0.033
 Help-0.033
Token a
Token ID257
Feature activation-3.25e+00

Pos logit contributions
isy+0.184
lf+0.183
 performance+0.175
fulness+0.169
pron+0.169
Neg logit contributions
 trash-0.102
 extingu-0.090
 dece-0.090
 bruised-0.089
oc-0.086
Token big
Token ID1263
Feature activation-9.63e-01

Pos logit contributions
isy+0.063
lf+0.061
fulness+0.061
 performance+0.055
 accomplishment+0.053
Neg logit contributions
 trash-0.085
 extingu-0.079
oc-0.078
 bit-0.078
 bruised-0.076
Token,
Token ID11
Feature activation-2.08e+00

Pos logit contributions
isy+0.021
lf+0.020
 performance+0.019
fulness+0.019
is+0.018
Neg logit contributions
 trash-0.023
 extingu-0.022
oc-0.022
 bruised-0.022
gy-0.021
Token black
Token ID2042
Feature activation-5.59e-01

Pos logit contributions
isy+0.042
lf+0.042
 performance+0.039
fulness+0.038
 achievement+0.037
Neg logit contributions
 trash-0.053
 extingu-0.050
 bruised-0.050
 dece-0.048
oc-0.048
Token anchor
Token ID18021
Feature activation-7.48e-01

Pos logit contributions
lf+0.011
isy+0.011
 performance+0.010
 trophy+0.010
is+0.010
Neg logit contributions
 trash-0.014
 extingu-0.014
 bruised-0.014
gy-0.014
 dece-0.013
Token always
Token ID1464
Feature activation-3.65e+00

Pos logit contributions
lf+0.086
isy+0.085
 performance+0.077
LC+0.076
ves+0.076
Neg logit contributions
gy-0.076
 trash-0.075
 extingu-0.074
 hyd-0.073
 bruised-0.073
Token be
Token ID307
Feature activation-1.63e+00

Pos logit contributions
isy+0.092
lf+0.091
ves+0.084
fulness+0.084
fs+0.082
Neg logit contributions
 trash-0.070
 bit-0.068
 bruised-0.068
 dece-0.067
gy-0.067
Token a
Token ID257
Feature activation-2.62e+00

Pos logit contributions
isy+0.033
lf+0.033
 performance+0.030
fulness+0.029
is+0.028
Neg logit contributions
 trash-0.041
 extingu-0.040
 bruised-0.040
gy-0.039
 dece-0.039
Token team
Token ID1074
Feature activation-1.57e+00

Pos logit contributions
lf+0.045
isy+0.045
 performance+0.043
fulness+0.039
 trophy+0.039
Neg logit contributions
 trash-0.072
 extingu-0.071
gy-0.069
 bruised-0.069
oc-0.069
Token and
Token ID290
Feature activation-1.50e+00

Pos logit contributions
isy+0.040
lf+0.040
 performance+0.037
fulness+0.036
is+0.036
Neg logit contributions
 trash-0.029
 extingu-0.029
oc-0.029
gy-0.028
 bruised-0.028
Token create
Token ID2251
Feature activation-6.30e+00

Pos logit contributions
isy+0.035
lf+0.034
is+0.032
fulness+0.031
 performance+0.031
Neg logit contributions
 trash-0.033
 extingu-0.032
 bruised-0.031
gy-0.031
 dece-0.031
Token amazing
Token ID4998
Feature activation-2.77e+00

Pos logit contributions
lf+0.144
isy+0.144
 performance+0.139
fulness+0.131
 trophy+0.131
Neg logit contributions
 trash-0.136
 extingu-0.134
gy-0.131
 bruised-0.131
oc-0.130
Token things
Token ID1243
Feature activation-3.26e+00

Pos logit contributions
isy+0.061
lf+0.057
pron+0.054
fulness+0.052
 performance+0.050
Neg logit contributions
 trash-0.066
oc-0.064
 extingu-0.062
 dece-0.061
 hyd-0.059
Token together
Token ID1978
Feature activation-2.73e+00

Pos logit contributions
lf+0.099
isy+0.098
 performance+0.091
pron+0.090
is+0.088
Neg logit contributions
 trash-0.047
 extingu-0.047
 hyd-0.044
 bruised-0.043
gy-0.043
Token.
Token ID13
Feature activation-1.48e+00

Pos logit contributions
isy+0.078
lf+0.078
 performance+0.075
is+0.071
pron+0.071
Neg logit contributions
 trash-0.044
 extingu-0.042
oc-0.041
gy-0.041
 bruised-0.040
Token The
Token ID383
Feature activation-9.74e-01

Pos logit contributions
isy+0.039
lf+0.038
 performance+0.037
fulness+0.037
 accomplishment+0.035
Neg logit contributions
 extingu-0.027
 trash-0.027
 bruised-0.026
gy-0.026
 dece-0.025
Token using
Token ID1262
Feature activation-1.48e+00

Pos logit contributions
isy+0.019
lf+0.017
 performance+0.017
 vows+0.016
pron+0.016
Neg logit contributions
 bruised-0.014
 Wh-0.014
 extingu-0.014
Bad-0.013
 trash-0.013
Token his
Token ID465
Feature activation-6.77e-01

Pos logit contributions
isy+0.038
lf+0.036
 performance+0.035
fulness+0.033
is+0.033
Neg logit contributions
 trash-0.030
 extingu-0.029
 bruised-0.028
gy-0.028
oc-0.027
Token imag
Token ID3590
Feature activation-5.99e+00

Pos logit contributions
isy+0.013
lf+0.013
 performance+0.013
fulness+0.012
is+0.012
Neg logit contributions
 trash-0.017
 extingu-0.017
 bruised-0.016
gy-0.016
oc-0.016
Tokeninations
Token ID7352
Feature activation-3.81e+00

Pos logit contributions
isy+0.095
 vows+0.090
lf+0.090
 avail+0.089
 medal+0.084
Neg logit contributions
o-0.161
oc-0.157
c-0.155
 extingu-0.150
 cigarettes-0.148
Token to
Token ID284
Feature activation-2.21e+00

Pos logit contributions
isy+0.107
lf+0.105
 performance+0.101
is+0.097
fulness+0.096
Neg logit contributions
 trash-0.064
 extingu-0.062
gy-0.060
 bruised-0.060
oc-0.058
Token create
Token ID2251
Feature activation-6.29e+00

Pos logit contributions
isy+0.055
lf+0.051
fulness+0.048
 poems+0.047
pron+0.047
Neg logit contributions
 extingu-0.044
gy-0.044
 trash-0.043
 hyd-0.041
 bruised-0.041
Token something
Token ID1223
Feature activation-3.19e+00

Pos logit contributions
isy+0.160
lf+0.157
 performance+0.150
fulness+0.143
is+0.142
Neg logit contributions
 trash-0.124
 extingu-0.118
oc-0.115
gy-0.115
 bruised-0.115
Token fun
Token ID1257
Feature activation-4.42e+00

Pos logit contributions
lf+0.065
isy+0.064
 performance+0.058
pron+0.056
fulness+0.055
Neg logit contributions
 trash-0.080
 extingu-0.076
 dece-0.075
 bruised-0.074
oc-0.073
Token.
Token ID13
Feature activation-1.34e+00

Pos logit contributions
isy+0.130
lf+0.125
 performance+0.119
pron+0.117
is+0.116
Neg logit contributions
 trash-0.068
 extingu-0.067
gy-0.066
oc-0.064
o-0.063
Token Joe
Token ID5689
Feature activation-2.36e+00

Pos logit contributions
lf+0.027
isy+0.026
 performance+0.026
fulness+0.026
 accomplishment+0.025
Neg logit contributions
 trash-0.032
 bruised-0.032
 extingu-0.031
Bad-0.030
gy-0.030
Token and
Token ID290
Feature activation-2.78e+00

Pos logit contributions
isy+0.063
lf+0.063
 performance+0.061
fulness+0.058
 trophy+0.058
Neg logit contributions
 trash-0.042
 extingu-0.041
gy-0.040
oc-0.040
 bruised-0.040
Token to
Token ID284
Feature activation+2.23e+00

Pos logit contributions
oc+0.046
 extingu+0.046
 trash+0.045
gy+0.045
 bruised+0.043
Neg logit contributions
isy-0.039
 performance-0.038
fulness-0.038
lf-0.037
 trophy-0.036
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
 extingu+0.047
oc+0.046
 trash+0.046
 bruised+0.045
gy+0.045
Neg logit contributions
 performance-0.051
isy-0.051
lf-0.050
 accomplishment-0.047
fulness-0.047
Token green
Token ID4077
Feature activation+8.32e-01

Pos logit contributions
 trash+0.029
 extingu+0.028
 bruised+0.027
gy+0.027
oc+0.027
Neg logit contributions
lf-0.033
isy-0.032
 performance-0.031
fulness-0.030
 trophy-0.029
Token toy
Token ID13373
Feature activation+1.89e+00

Pos logit contributions
 extingu+0.019
 trash+0.019
 bruised+0.019
oc+0.019
 dece+0.019
Neg logit contributions
isy-0.018
lf-0.017
 performance-0.017
 trophy-0.016
is-0.016
Token.
Token ID13
Feature activation+1.39e+00

Pos logit contributions
 trash+0.035
 extingu+0.034
gy+0.033
 bruised+0.033
oc+0.032
Neg logit contributions
lf-0.050
isy-0.050
 performance-0.048
fulness-0.046
is-0.045
Token "
Token ID366
Feature activation+4.95e+00

Pos logit contributions
 trash+0.032
 extingu+0.032
oc+0.032
gy+0.032
 bruised+0.031
Neg logit contributions
isy-0.029
lf-0.029
 performance-0.027
fulness-0.026
 trophy-0.026
TokenGrab
Token ID48400
Feature activation+9.46e-01

Pos logit contributions
gy+0.126
 bruised+0.124
 extingu+0.123
 trash+0.122
fired+0.121
Neg logit contributions
isy-0.087
lf-0.084
 trophy-0.083
 chords-0.081
fulness-0.080
Token it
Token ID340
Feature activation+3.09e+00

Pos logit contributions
 trash+0.026
 extingu+0.026
gy+0.026
 bruised+0.026
oc+0.026
Neg logit contributions
lf-0.015
isy-0.015
 performance-0.014
 accomplishment-0.013
is-0.013
Token,
Token ID11
Feature activation+1.28e+00

Pos logit contributions
 trash+0.058
 extingu+0.056
 bruised+0.055
gy+0.054
oc+0.054
Neg logit contributions
isy-0.080
lf-0.080
 performance-0.077
fulness-0.074
 trophy-0.073
Token Ben
Token ID3932
Feature activation+1.43e+00

Pos logit contributions
 trash+0.026
 extingu+0.026
gy+0.025
 bruised+0.025
oc+0.025
Neg logit contributions
isy-0.031
lf-0.031
 performance-0.030
 trophy-0.028
fulness-0.028
Token!"
Token ID2474
Feature activation+1.61e-02

Pos logit contributions
 trash+0.030
 extingu+0.030
 bruised+0.029
 dece+0.028
Bad+0.028
Neg logit contributions
isy-0.033
lf-0.033
 performance-0.030
is-0.029
fulness-0.029
Token OK
Token ID7477
Feature activation+3.14e+00

Pos logit contributions
 trash+0.096
 extingu+0.096
oc+0.093
gy+0.091
 bruised+0.089
Neg logit contributions
isy-0.150
lf-0.150
 performance-0.145
is-0.137
 trophy-0.137
Token?"
Token ID1701
Feature activation+3.97e-02

Pos logit contributions
 trash+0.070
oc+0.069
 extingu+0.068
 dece+0.067
 bruised+0.064
Neg logit contributions
lf-0.073
isy-0.068
 performance-0.068
 trophy-0.063
is-0.060
Token Sam
Token ID3409
Feature activation+1.28e+00

Pos logit contributions
 extingu+0.001
oc+0.001
gy+0.001
 trash+0.001
tr+0.001
Neg logit contributions
lf-0.001
isy-0.001
 performance-0.001
 accomplishment-0.001
 trophy-0.001
Token asked
Token ID1965
Feature activation+4.53e-01

Pos logit contributions
 trash+0.030
 extingu+0.030
oc+0.029
 bruised+0.029
gy+0.029
Neg logit contributions
lf-0.027
isy-0.027
 performance-0.025
is-0.024
 trophy-0.023
Token.
Token ID13
Feature activation+2.15e+00

Pos logit contributions
 trash+0.011
oc+0.011
 extingu+0.010
Bad+0.010
 dece+0.010
Neg logit contributions
isy-0.009
lf-0.009
fulness-0.009
 performance-0.008
 accomplishment-0.008
Token "
Token ID366
Feature activation+5.15e+00

Pos logit contributions
 dece+0.061
c+0.060
 trash+0.060
 bruised+0.058
oc+0.058
Neg logit contributions
lf-0.034
isy-0.031
 hardly-0.030
fulness-0.028
 trophy-0.028
TokenYou
Token ID1639
Feature activation+4.19e+00

Pos logit contributions
gy+0.097
 trash+0.095
 extingu+0.093
 bruised+0.091
fired+0.090
Neg logit contributions
lf-0.135
isy-0.132
fulness-0.123
 performance-0.123
 trophy-0.122
Token are
Token ID389
Feature activation+1.86e+00

Pos logit contributions
 extingu+0.094
oc+0.085
 cages+0.085
fired+0.083
oky+0.083
Neg logit contributions
isy-0.090
 hardly-0.089
 trophy-0.086
 performance-0.086
lf-0.083
Token hurt
Token ID5938
Feature activation+2.42e+00

Pos logit contributions
oc+0.046
 extingu+0.043
fired+0.041
packs+0.040
gy+0.039
Neg logit contributions
isy-0.042
lf-0.040
 performance-0.038
 trophy-0.037
 medal-0.035
Token!"
Token ID2474
Feature activation-1.36e-01

Pos logit contributions
 extingu+0.063
 dece+0.062
ric+0.061
c+0.061
oc+0.060
Neg logit contributions
lf-0.044
isy-0.040
is-0.039
fulness-0.036
fully-0.036
Token
Token ID198
Feature activation+1.30e+00

Pos logit contributions
lf+0.003
isy+0.003
fulness+0.003
 performance+0.003
 accomplishment+0.003
Neg logit contributions
 extingu-0.003
 trash-0.003
gy-0.003
 dece-0.003
 bruised-0.003
Token spraying
Token ID40170
Feature activation-2.26e+00

Pos logit contributions
 trash+0.007
 extingu+0.007
gy+0.007
 bruised+0.007
 dece+0.007
Neg logit contributions
lf-0.007
isy-0.007
 performance-0.007
fulness-0.007
 trophy-0.007
Token,
Token ID11
Feature activation-5.25e-01

Pos logit contributions
 performance+0.039
 trophy+0.039
fulness+0.038
isy+0.037
lf+0.037
Neg logit contributions
oc-0.061
 extingu-0.058
gy-0.058
enn-0.057
tr-0.055
Token a
Token ID257
Feature activation-8.84e-01

Pos logit contributions
lf+0.010
isy+0.008
 trophy+0.008
 performance+0.008
 medal+0.008
Neg logit contributions
 extingu-0.015
oc-0.014
 trash-0.014
 bruised-0.014
gy-0.014
Token man
Token ID582
Feature activation+1.16e+00

Pos logit contributions
lf+0.018
isy+0.018
 performance+0.017
 trophy+0.016
fulness+0.016
Neg logit contributions
 trash-0.021
 extingu-0.021
gy-0.020
 bruised-0.020
oc-0.020
Token came
Token ID1625
Feature activation+3.32e+00

Pos logit contributions
 trash+0.023
 extingu+0.022
 dece+0.022
 bruised+0.022
gy+0.021
Neg logit contributions
lf-0.030
isy-0.027
 performance-0.027
is-0.026
 couple-0.025
Token up
Token ID510
Feature activation+4.75e+00

Pos logit contributions
 trash+0.082
oc+0.078
 dece+0.077
 bruised+0.077
 extingu+0.077
Neg logit contributions
 performance-0.063
lf-0.062
isy-0.062
is-0.060
 couple-0.055
Token to
Token ID284
Feature activation+2.07e+00

Pos logit contributions
 trash+0.122
 bruised+0.116
 dece+0.115
 cigarettes+0.112
oc+0.111
Neg logit contributions
lf-0.091
 performance-0.091
isy-0.085
is-0.083
 couple-0.083
Token him
Token ID683
Feature activation+3.45e+00

Pos logit contributions
 trash+0.052
 bruised+0.052
oky+0.051
 extingu+0.051
tr+0.051
Neg logit contributions
lf-0.039
isy-0.035
 performance-0.034
 trophy-0.033
fulness-0.033
Token and
Token ID290
Feature activation+1.70e+00

Pos logit contributions
 trash+0.068
 dece+0.065
 extingu+0.064
 bruised+0.063
Bad+0.063
Neg logit contributions
lf-0.086
isy-0.086
 performance-0.082
 trophy-0.078
fulness-0.077
Token asked
Token ID1965
Feature activation+1.03e+00

Pos logit contributions
 extingu+0.045
 trash+0.043
gy+0.043
 bruised+0.042
oc+0.042
Neg logit contributions
lf-0.031
isy-0.030
 performance-0.027
 trophy-0.026
pron-0.026
Token,
Token ID11
Feature activation+2.93e+00

Pos logit contributions
 extingu+0.026
 trash+0.025
 hyd+0.025
 bruised+0.025
gy+0.025
Neg logit contributions
lf-0.019
isy-0.019
fulness-0.018
is-0.017
 accomplishment-0.016
Token opened
Token ID4721
Feature activation+1.03e+00

Pos logit contributions
lf+0.026
isy+0.025
 performance+0.024
 trophy+0.023
is+0.023
Neg logit contributions
 trash-0.021
 bruised-0.021
 extingu-0.021
oc-0.020
gy-0.020
Token the
Token ID262
Feature activation+2.79e+00

Pos logit contributions
 trash+0.028
 extingu+0.027
 bruised+0.027
gy+0.027
oc+0.027
Neg logit contributions
lf-0.018
isy-0.018
 performance-0.017
fulness-0.016
 trophy-0.016
Token door
Token ID3420
Feature activation+3.94e+00

Pos logit contributions
Bad+0.080
oc+0.079
o+0.079
 bruised+0.078
 dece+0.078
Neg logit contributions
 trophy-0.040
lf-0.039
 performance-0.036
isy-0.035
 medal-0.035
Token and
Token ID290
Feature activation+1.65e+00

Pos logit contributions
 extingu+0.058
 trash+0.054
gy+0.052
 bruised+0.051
oc+0.050
Neg logit contributions
isy-0.122
lf-0.120
 performance-0.117
pron-0.113
 trophy-0.111
Token climbed
Token ID19952
Feature activation+8.21e-01

Pos logit contributions
oc+0.033
 bruised+0.033
 extingu+0.032
 dece+0.032
gy+0.031
Neg logit contributions
lf-0.040
 performance-0.036
 trophy-0.036
isy-0.036
 couple-0.036
Token in
Token ID287
Feature activation+4.69e+00

Pos logit contributions
 trash+0.017
 extingu+0.017
 bruised+0.017
oc+0.017
 dece+0.016
Neg logit contributions
lf-0.019
isy-0.019
 performance-0.018
 trophy-0.017
fulness-0.017
Token.
Token ID13
Feature activation+4.03e-01

Pos logit contributions
 trash+0.088
 extingu+0.085
 bruised+0.084
gy+0.083
oc+0.083
Neg logit contributions
lf-0.122
isy-0.121
 performance-0.117
fulness-0.112
 trophy-0.111
Token
Token ID198
Feature activation+1.44e+00

Pos logit contributions
 extingu+0.007
 bruised+0.007
 trash+0.007
gy+0.007
oc+0.007
Neg logit contributions
lf-0.011
isy-0.010
 performance-0.010
 trophy-0.010
fulness-0.010
Token
Token ID198
Feature activation+1.11e+00

Pos logit contributions
 trash+0.023
 extingu+0.022
 bruised+0.022
gy+0.022
oc+0.021
Neg logit contributions
lf-0.042
isy-0.041
 performance-0.040
fulness-0.039
is-0.038
Token"
Token ID1
Feature activation+2.30e+00

Pos logit contributions
 extingu+0.026
 bruised+0.026
gy+0.025
 trash+0.025
oc+0.024
Neg logit contributions
lf-0.025
isy-0.023
is-0.022
 performance-0.022
ves-0.021
TokenWow
Token ID22017
Feature activation+1.60e+00

Pos logit contributions
 bruised+0.048
gy+0.047
oc+0.046
fired+0.045
 trash+0.045
Neg logit contributions
lf-0.055
isy-0.053
 couple-0.053
pron-0.050
is-0.050
Token is
Token ID318
Feature activation+1.18e+00

Pos logit contributions
 extingu+0.023
fired+0.022
packs+0.021
 dece+0.020
oky+0.020
Neg logit contributions
isy-0.023
lf-0.021
 happen-0.021
 trophy-0.020
 hardly-0.019
Token dangerous
Token ID4923
Feature activation+2.20e+00

Pos logit contributions
oc+0.034
 extingu+0.032
gy+0.032
fired+0.032
ASH+0.031
Neg logit contributions
isy-0.020
lf-0.018
 poems-0.018
 accomplishment-0.017
pron-0.017
Token and
Token ID290
Feature activation+3.03e-01

Pos logit contributions
 trash+0.040
 extingu+0.039
gy+0.038
 bruised+0.038
oc+0.037
Neg logit contributions
lf-0.059
isy-0.059
 performance-0.057
fulness-0.054
 trophy-0.054
Token not
Token ID407
Feature activation-8.08e-01

Pos logit contributions
 extingu+0.006
gy+0.006
oc+0.006
 dece+0.005
 trash+0.005
Neg logit contributions
isy-0.007
lf-0.007
 performance-0.007
 trophy-0.007
fulness-0.007
Token for
Token ID329
Feature activation+1.87e+00

Pos logit contributions
isy+0.017
lf+0.016
 trophy+0.016
 performance+0.015
 medal+0.015
Neg logit contributions
oc-0.019
 extingu-0.019
gy-0.018
 trash-0.017
fired-0.017
Token you
Token ID345
Feature activation+4.77e+00

Pos logit contributions
 trash+0.042
 bruised+0.040
 extingu+0.040
gy+0.039
 dece+0.038
Neg logit contributions
isy-0.043
lf-0.042
 performance-0.041
fulness-0.039
 trophy-0.038
Token.
Token ID13
Feature activation+1.80e+00

Pos logit contributions
 extingu+0.112
gy+0.106
oc+0.105
 trash+0.101
 dece+0.101
Neg logit contributions
isy-0.104
lf-0.099
 performance-0.097
fulness-0.096
 trophy-0.092
Token You
Token ID921
Feature activation+3.15e+00

Pos logit contributions
 extingu+0.042
gy+0.042
 trash+0.042
 bit+0.042
 dece+0.042
Neg logit contributions
fulness-0.032
isy-0.031
lf-0.030
 poems-0.029
LC-0.029
Token could
Token ID714
Feature activation-1.84e+00

Pos logit contributions
 extingu+0.076
ASH+0.070
 dece+0.069
 trash+0.069
fired+0.069
Neg logit contributions
isy-0.062
lf-0.061
 trophy-0.060
 hardly-0.058
 performance-0.057
Token have
Token ID423
Feature activation+1.03e+00

Pos logit contributions
isy+0.040
lf+0.040
 performance+0.038
 trophy+0.036
is+0.036
Neg logit contributions
 extingu-0.042
 trash-0.041
oc-0.041
 bruised-0.040
gy-0.039
Token hurt
Token ID5938
Feature activation+6.74e-02

Pos logit contributions
 extingu+0.021
oc+0.021
gy+0.019
oky+0.019
o+0.018
Neg logit contributions
lf-0.025
 happen-0.023
isy-0.023
 performance-0.023
 trophy-0.023
Token look
Token ID804
Feature activation-3.15e-01

Pos logit contributions
isy+0.035
lf+0.035
 performance+0.033
fulness+0.031
is+0.031
Neg logit contributions
 trash-0.035
 extingu-0.035
gy-0.034
 bruised-0.034
oc-0.034
Token for
Token ID329
Feature activation+7.48e-01

Pos logit contributions
isy+0.006
lf+0.006
 performance+0.006
fulness+0.006
 trophy+0.006
Neg logit contributions
gy-0.007
 extingu-0.007
 trash-0.007
oc-0.007
 bruised-0.007
Token another
Token ID1194
Feature activation-1.21e+00

Pos logit contributions
o+0.017
gy+0.017
oc+0.017
tr+0.016
 bruised+0.016
Neg logit contributions
lf-0.016
 performance-0.015
isy-0.015
 accomplishment-0.015
 trophy-0.014
Token treasure
Token ID14068
Feature activation-8.91e-01

Pos logit contributions
lf+0.026
isy+0.025
 performance+0.025
 trophy+0.023
is+0.023
Neg logit contributions
 trash-0.028
 extingu-0.028
 bruised-0.028
gy-0.027
oc-0.027
Token tomorrow
Token ID9439
Feature activation+8.03e-01

Pos logit contributions
isy+0.023
lf+0.023
 performance+0.023
fulness+0.022
is+0.021
Neg logit contributions
 trash-0.016
 extingu-0.016
gy-0.016
oc-0.015
 bruised-0.015
Token,
Token ID11
Feature activation+8.64e-01

Pos logit contributions
 trash+0.013
 extingu+0.012
gy+0.012
oc+0.012
 bruised+0.012
Neg logit contributions
isy-0.023
lf-0.023
 performance-0.022
 trophy-0.021
is-0.021
Token in
Token ID287
Feature activation+4.23e+00

Pos logit contributions
oc+0.018
 trash+0.017
gy+0.017
 extingu+0.017
 bruised+0.016
Neg logit contributions
lf-0.020
 performance-0.020
isy-0.020
 trophy-0.019
 accomplishment-0.019
Token a
Token ID257
Feature activation+2.33e-01

Pos logit contributions
oc+0.096
o+0.095
gy+0.095
 extingu+0.093
 trash+0.092
Neg logit contributions
lf-0.092
 performance-0.090
 accomplishment-0.087
 achievement-0.084
isy-0.084
Token different
Token ID1180
Feature activation+3.56e-01

Pos logit contributions
 extingu+0.005
gy+0.005
 bruised+0.005
o+0.005
 trash+0.005
Neg logit contributions
lf-0.005
isy-0.005
 performance-0.005
pron-0.005
 trophy-0.005
Token place
Token ID1295
Feature activation+5.92e-01

Pos logit contributions
 extingu+0.008
 bruised+0.008
o+0.008
 Wh+0.008
 Or+0.008
Neg logit contributions
lf-0.008
 performance-0.007
isy-0.007
 trophy-0.007
 ceremony-0.007
Token.
Token ID13
Feature activation+9.79e-02

Pos logit contributions
 trash+0.012
oc+0.011
 extingu+0.011
 bruised+0.011
gy+0.011
Neg logit contributions
lf-0.015
isy-0.014
 performance-0.014
fulness-0.014
 accomplishment-0.013
Token dad
Token ID9955
Feature activation+8.36e-01

Pos logit contributions
isy+0.019
lf+0.018
 performance+0.017
fulness+0.017
is+0.016
Neg logit contributions
 trash-0.018
 extingu-0.017
 bruised-0.017
gy-0.017
oc-0.016
Token's
Token ID338
Feature activation-8.74e-01

Pos logit contributions
oc+0.011
 trash+0.011
 bruised+0.011
gy+0.010
c+0.010
Neg logit contributions
isy-0.026
lf-0.025
 performance-0.025
 accomplishment-0.024
 achievement-0.024
Token suit
Token ID6050
Feature activation-3.58e-01

Pos logit contributions
isy+0.021
lf+0.020
 performance+0.018
fulness+0.018
quet+0.018
Neg logit contributions
 trash-0.020
 extingu-0.019
gy-0.018
 bruised-0.018
oc-0.018
Token anymore
Token ID7471
Feature activation-1.28e-01

Pos logit contributions
isy+0.011
lf+0.010
 performance+0.010
 accomplishment+0.010
 achievement+0.010
Neg logit contributions
gy-0.005
 trash-0.005
 bruised-0.005
oc-0.005
 extingu-0.005
Token.
Token ID13
Feature activation+5.07e-01

Pos logit contributions
isy+0.004
lf+0.004
 performance+0.004
is+0.003
 trophy+0.003
Neg logit contributions
 trash-0.002
oc-0.002
 extingu-0.002
gy-0.002
 bruised-0.002
Token He
Token ID679
Feature activation+6.59e-01

Pos logit contributions
 extingu+0.012
gy+0.012
 bruised+0.012
 bit+0.012
 trash+0.011
Neg logit contributions
lf-0.010
fulness-0.009
 trophy-0.009
 hardly-0.009
isy-0.009
Token only
Token ID691
Feature activation-6.96e-02

Pos logit contributions
 extingu+0.014
 trash+0.013
 bruised+0.013
gy+0.013
 dece+0.013
Neg logit contributions
lf-0.016
isy-0.015
 performance-0.015
 trophy-0.014
 medal-0.014
Token cared
Token ID19951
Feature activation-2.85e+00

Pos logit contributions
lf+0.002
isy+0.002
 performance+0.002
 trophy+0.002
fulness+0.002
Neg logit contributions
 extingu-0.001
 trash-0.001
gy-0.001
 bruised-0.001
oc-0.001
Token about
Token ID546
Feature activation-4.88e-01

Pos logit contributions
lf+0.054
isy+0.053
 performance+0.051
pron+0.047
 ceremony+0.046
Neg logit contributions
 trash-0.075
 extingu-0.072
 bruised-0.072
oc-0.069
 dece-0.068
Token having
Token ID1719
Feature activation-8.43e-01

Pos logit contributions
isy+0.011
lf+0.011
 performance+0.010
fulness+0.010
 trophy+0.010
Neg logit contributions
 trash-0.011
 extingu-0.011
gy-0.011
 bruised-0.011
oc-0.011
Token fun
Token ID1257
Feature activation-3.30e+00

Pos logit contributions
isy+0.017
lf+0.017
 performance+0.016
fulness+0.015
 trophy+0.015
Neg logit contributions
 trash-0.021
 extingu-0.020
 bruised-0.020
gy-0.020
oc-0.020
Token tree
Token ID5509
Feature activation+2.87e+00

Pos logit contributions
 extingu+0.028
 bruised+0.028
 trash+0.028
 dece+0.027
gy+0.027
Neg logit contributions
lf-0.020
isy-0.020
 performance-0.019
 trophy-0.018
is-0.017
Token,
Token ID11
Feature activation+1.02e+00

Pos logit contributions
 trash+0.061
 extingu+0.061
 bruised+0.059
 dece+0.058
Bad+0.057
Neg logit contributions
lf-0.067
isy-0.067
 performance-0.064
 trophy-0.061
is-0.061
Token but
Token ID475
Feature activation+3.65e-01

Pos logit contributions
 trash+0.020
 extingu+0.020
gy+0.020
oc+0.020
 bruised+0.019
Neg logit contributions
isy-0.025
lf-0.025
 performance-0.024
 trophy-0.023
fulness-0.023
Token I
Token ID314
Feature activation+1.71e+00

Pos logit contributions
 trash+0.009
 bruised+0.008
 extingu+0.008
gy+0.008
oc+0.008
Neg logit contributions
isy-0.008
lf-0.008
 performance-0.008
is-0.007
fulness-0.007
Token'm
Token ID1101
Feature activation+1.06e+00

Pos logit contributions
 extingu+0.040
 cages+0.036
Bad+0.036
 trash+0.036
ASH+0.035
Neg logit contributions
 hardly-0.037
 performance-0.035
isy-0.035
 medal-0.033
 trophy-0.033
Token scared
Token ID12008
Feature activation+7.88e-01

Pos logit contributions
 trash+0.018
 extingu+0.018
oc+0.018
gy+0.017
 bruised+0.017
Neg logit contributions
isy-0.029
lf-0.029
 performance-0.028
 trophy-0.027
is-0.027
Token."
Token ID526
Feature activation-1.84e+00

Pos logit contributions
 trash+0.015
 bruised+0.014
 extingu+0.014
gy+0.014
oc+0.013
Neg logit contributions
lf-0.021
isy-0.021
 performance-0.020
 trophy-0.019
 achievement-0.019
Token Her
Token ID2332
Feature activation-2.11e-01

Pos logit contributions
lf+0.037
isy+0.036
 performance+0.035
fulness+0.032
 trophy+0.032
Neg logit contributions
 extingu-0.046
 trash-0.045
 bruised-0.044
oc-0.044
 dece-0.043
Token mom
Token ID1995
Feature activation+8.82e-01

Pos logit contributions
isy+0.005
fulness+0.005
lf+0.005
 performance+0.005
is+0.004
Neg logit contributions
 trash-0.005
 bruised-0.005
gy-0.005
 extingu-0.005
 Wh-0.004
Token said
Token ID531
Feature activation+1.70e-01

Pos logit contributions
 trash+0.020
 extingu+0.019
gy+0.019
 bruised+0.019
oc+0.019
Neg logit contributions
lf-0.020
isy-0.020
 performance-0.019
fulness-0.018
 trophy-0.018
Token,
Token ID11
Feature activation+2.73e+00

Pos logit contributions
 bruised+0.003
 trash+0.003
 extingu+0.002
gy+0.002
 Wh+0.002
Neg logit contributions
lf-0.005
 performance-0.005
isy-0.005
 trophy-0.005
 achievement-0.005
TokenOnce
Token ID7454
Feature activation+6.82e-01

Pos logit contributions
 extingu+0.021
 trash+0.021
 bruised+0.021
 dece+0.020
gy+0.020
Neg logit contributions
lf-0.034
isy-0.033
 performance-0.032
fulness-0.031
 trophy-0.030
Token upon
Token ID2402
Feature activation+2.68e+00

Pos logit contributions
 trash+0.005
o+0.005
gy+0.005
 bruised+0.004
 extingu+0.004
Neg logit contributions
isy-0.025
lf-0.025
 performance-0.025
 chords-0.024
is-0.023
Token a
Token ID257
Feature activation+8.74e-01

Pos logit contributions
 trash+0.040
 extingu+0.038
gy+0.037
 bruised+0.037
oc+0.037
Neg logit contributions
lf-0.080
isy-0.080
 performance-0.077
fulness-0.074
 trophy-0.074
Token time
Token ID640
Feature activation+2.88e-01

Pos logit contributions
 extingu+0.026
 bruised+0.026
 trash+0.025
gy+0.025
fired+0.024
Neg logit contributions
isy-0.014
lf-0.013
 performance-0.012
is-0.012
pron-0.012
Token there
Token ID612
Feature activation-1.54e+00

Pos logit contributions
 trash+0.008
 extingu+0.008
 bruised+0.008
 hyd+0.007
oc+0.007
Neg logit contributions
lf-0.006
isy-0.005
 performance-0.005
 trophy-0.005
fulness-0.005
Token was
Token ID373
Feature activation+1.68e+00

Pos logit contributions
lf+0.040
isy+0.037
 performance+0.036
 trophy+0.035
fulness+0.034
Neg logit contributions
 extingu-0.031
 trash-0.030
 bruised-0.029
 dece-0.028
gy-0.028
Token a
Token ID257
Feature activation-6.13e-01

Pos logit contributions
 extingu+0.030
 trash+0.030
 bruised+0.029
oc+0.029
gy+0.028
Neg logit contributions
lf-0.045
isy-0.044
 performance-0.043
 trophy-0.041
fulness-0.040
Token beautiful
Token ID4950
Feature activation-9.28e-01

Pos logit contributions
isy+0.014
lf+0.014
fulness+0.014
 performance+0.014
 achievement+0.013
Neg logit contributions
 trash-0.014
oc-0.013
 extingu-0.013
 bruised-0.012
gy-0.012
Token flower
Token ID15061
Feature activation+5.14e-02

Pos logit contributions
fulness+0.020
isy+0.020
lf+0.020
 performance+0.019
ves+0.019
Neg logit contributions
 trash-0.021
oc-0.020
gy-0.020
 extingu-0.019
 bit-0.019
Token in
Token ID287
Feature activation+4.08e+00

Pos logit contributions
 trash+0.001
gy+0.001
oc+0.001
 extingu+0.001
o+0.001
Neg logit contributions
lf-0.001
isy-0.001
 performance-0.001
fulness-0.001
 accomplishment-0.001
Token a
Token ID257
Feature activation-8.33e-02

Pos logit contributions
 trash+0.080
 extingu+0.078
gy+0.076
 bruised+0.076
oc+0.075
Neg logit contributions
isy-0.103
lf-0.103
 performance-0.100
fulness-0.095
 trophy-0.094
Token when
Token ID618
Feature activation+2.21e-01

Pos logit contributions
lf+0.017
isy+0.017
 performance+0.017
fulness+0.016
 trophy+0.016
Neg logit contributions
 trash-0.012
 extingu-0.012
 bruised-0.012
gy-0.012
oc-0.011
Token he
Token ID339
Feature activation-2.92e-01

Pos logit contributions
 trash+0.006
gy+0.006
 bruised+0.006
 extingu+0.006
 dece+0.006
Neg logit contributions
isy-0.004
lf-0.004
 performance-0.004
is-0.003
fulness-0.003
Token heard
Token ID2982
Feature activation+3.18e-01

Pos logit contributions
lf+0.008
 performance+0.008
isy+0.007
 wedding+0.007
is+0.007
Neg logit contributions
 extingu-0.006
 bruised-0.005
 trash-0.005
 cigarettes-0.005
oc-0.005
Token a
Token ID257
Feature activation-1.14e+00

Pos logit contributions
 trash+0.005
 extingu+0.005
gy+0.005
 bruised+0.005
oc+0.005
Neg logit contributions
lf-0.009
isy-0.009
 performance-0.009
fulness-0.008
 trophy-0.008
Token noise
Token ID7838
Feature activation-1.86e-01

Pos logit contributions
lf+0.023
isy+0.023
 performance+0.022
fulness+0.021
 accomplishment+0.020
Neg logit contributions
 trash-0.028
 extingu-0.027
oc-0.027
 bruised-0.026
gy-0.026
Token coming
Token ID2406
Feature activation+2.12e+00

Pos logit contributions
lf+0.005
isy+0.005
 performance+0.005
fulness+0.005
 trophy+0.005
Neg logit contributions
 trash-0.003
 extingu-0.003
gy-0.003
 bruised-0.003
oc-0.003
Token from
Token ID422
Feature activation+4.63e+00

Pos logit contributions
 bruised+0.043
 trash+0.042
 dece+0.042
oc+0.042
c+0.041
Neg logit contributions
 performance-0.049
isy-0.048
lf-0.047
fulness-0.046
 trophy-0.045
Token the
Token ID262
Feature activation+2.47e+00

Pos logit contributions
oc+0.111
 dece+0.109
 bruised+0.107
o+0.107
 extingu+0.106
Neg logit contributions
lf-0.092
 performance-0.088
 accomplishment-0.083
 trophy-0.083
 medal-0.081
Token forest
Token ID8222
Feature activation+1.51e+00

Pos logit contributions
oc+0.063
 dece+0.063
 extingu+0.062
gy+0.061
 bruised+0.061
Neg logit contributions
lf-0.048
 performance-0.047
 trophy-0.045
isy-0.044
 medal-0.042
Token nearby
Token ID6716
Feature activation+1.51e+00

Pos logit contributions
 trash+0.031
 extingu+0.030
 bruised+0.030
oc+0.029
gy+0.029
Neg logit contributions
lf-0.036
isy-0.036
 performance-0.035
fulness-0.033
 trophy-0.033
Token.
Token ID13
Feature activation-1.08e+00

Pos logit contributions
 extingu+0.030
 trash+0.030
 bruised+0.029
gy+0.029
oc+0.029
Neg logit contributions
lf-0.037
isy-0.036
 performance-0.035
fulness-0.034
 trophy-0.033
Token was
Token ID373
Feature activation-1.60e-01

Pos logit contributions
 trash+0.032
 extingu+0.031
 bruised+0.031
gy+0.030
oc+0.030
Neg logit contributions
lf-0.040
isy-0.040
 performance-0.038
fulness-0.037
 trophy-0.036
Token proud
Token ID6613
Feature activation+1.11e-01

Pos logit contributions
isy+0.003
lf+0.003
 performance+0.003
fulness+0.003
 trophy+0.003
Neg logit contributions
 trash-0.004
 bruised-0.004
 extingu-0.004
gy-0.004
 dece-0.004
Token of
Token ID286
Feature activation+1.77e-01

Pos logit contributions
 trash+0.002
 bruised+0.002
 extingu+0.002
 bit+0.002
o+0.002
Neg logit contributions
lf-0.003
isy-0.003
 performance-0.003
pron-0.003
 trophy-0.003
Token them
Token ID606
Feature activation+7.62e-01

Pos logit contributions
 trash+0.004
 extingu+0.004
gy+0.004
 bruised+0.004
oc+0.004
Neg logit contributions
isy-0.004
lf-0.004
 performance-0.004
pron-0.004
 trophy-0.003
Token.
Token ID13
Feature activation+6.58e-01

Pos logit contributions
 trash+0.011
 bruised+0.011
gy+0.011
 extingu+0.010
o+0.010
Neg logit contributions
lf-0.024
isy-0.023
 performance-0.022
pron-0.022
 trophy-0.021
Token She
Token ID1375
Feature activation+3.30e-01

Pos logit contributions
 extingu+0.016
gy+0.015
 bruised+0.015
oc+0.015
 trash+0.015
Neg logit contributions
lf-0.013
isy-0.013
fulness-0.012
 performance-0.012
is-0.011
Token knew
Token ID2993
Feature activation-1.37e+00

Pos logit contributions
 trash+0.007
 extingu+0.007
gy+0.007
 bruised+0.007
oc+0.007
Neg logit contributions
isy-0.008
lf-0.008
 performance-0.007
is-0.007
 trophy-0.007
Token they
Token ID484
Feature activation-4.96e-01

Pos logit contributions
isy+0.027
lf+0.027
 performance+0.026
pron+0.024
 trophy+0.024
Neg logit contributions
 trash-0.034
 extingu-0.033
 bruised-0.033
 Wh-0.033
gy-0.032
Token learned
Token ID4499
Feature activation-2.18e+00

Pos logit contributions
lf+0.013
isy+0.013
 performance+0.012
fulness+0.012
 trophy+0.012
Neg logit contributions
 trash-0.009
 extingu-0.009
gy-0.009
 bruised-0.009
oc-0.009
Token a
Token ID257
Feature activation-3.58e+00

Pos logit contributions
isy+0.052
lf+0.052
 performance+0.051
 trophy+0.049
fulness+0.049
Neg logit contributions
oc-0.044
gy-0.043
 extingu-0.043
 bruised-0.043
 trash-0.042
Token lesson
Token ID11483
Feature activation+8.00e-01

Pos logit contributions
lf+0.062
isy+0.057
 performance+0.054
fulness+0.051
 ceremony+0.049
Neg logit contributions
 trash-0.104
 extingu-0.098
oc-0.096
 dece-0.096
gy-0.095
Token You
Token ID921
Feature activation+1.73e+00

Pos logit contributions
 extingu+0.033
 trash+0.032
fired+0.030
oc+0.030
 dece+0.030
Neg logit contributions
isy-0.035
 performance-0.034
lf-0.033
fulness-0.033
is-0.032
Token have
Token ID423
Feature activation+1.72e+00

Pos logit contributions
 extingu+0.035
 trash+0.033
oc+0.032
 dece+0.031
 bruised+0.031
Neg logit contributions
isy-0.042
lf-0.042
 performance-0.042
 trophy-0.041
 hardly-0.039
Token to
Token ID284
Feature activation-3.00e-01

Pos logit contributions
oc+0.048
 extingu+0.047
gy+0.044
 bruised+0.042
 trash+0.042
Neg logit contributions
 performance-0.031
lf-0.029
 poems-0.029
isy-0.028
 wedding-0.028
Token go
Token ID467
Feature activation-1.03e+00

Pos logit contributions
lf+0.007
isy+0.007
 performance+0.006
fulness+0.006
 trophy+0.006
Neg logit contributions
 trash-0.007
 extingu-0.007
gy-0.006
 bruised-0.006
oc-0.006
Token to
Token ID284
Feature activation+1.09e+00

Pos logit contributions
isy+0.028
lf+0.027
 performance+0.025
fulness+0.025
 trophy+0.025
Neg logit contributions
 trash-0.019
gy-0.019
 extingu-0.018
 bruised-0.018
o-0.018
Token school
Token ID1524
Feature activation-1.49e+00

Pos logit contributions
 trash+0.027
 extingu+0.026
gy+0.026
 bruised+0.026
oc+0.025
Neg logit contributions
isy-0.022
lf-0.022
 performance-0.020
fulness-0.019
 trophy-0.019
Token and
Token ID290
Feature activation-8.65e-01

Pos logit contributions
isy+0.042
lf+0.040
 performance+0.038
fulness+0.038
 trophy+0.037
Neg logit contributions
 trash-0.025
gy-0.024
oc-0.024
 extingu-0.023
 bruised-0.023
Token learn
Token ID2193
Feature activation-2.96e+00

Pos logit contributions
isy+0.020
lf+0.019
 performance+0.018
fulness+0.018
is+0.018
Neg logit contributions
 trash-0.020
 bruised-0.018
 extingu-0.018
gy-0.018
 dece-0.018
Token new
Token ID649
Feature activation-2.05e+00

Pos logit contributions
lf+0.050
isy+0.050
 performance+0.048
fulness+0.046
 trophy+0.045
Neg logit contributions
gy-0.081
 extingu-0.081
oc-0.080
 trash-0.080
 bruised-0.079
Token things
Token ID1243
Feature activation-2.33e+00

Pos logit contributions
isy+0.046
lf+0.044
pron+0.041
 performance+0.040
 trophy+0.039
Neg logit contributions
 trash-0.049
oc-0.045
 extingu-0.044
 dece-0.044
 Or-0.044
Token."
Token ID526
Feature activation-1.94e+00

Pos logit contributions
lf+0.070
isy+0.070
 performance+0.067
pron+0.065
 accomplishment+0.065
Neg logit contributions
 trash-0.036
 extingu-0.033
o-0.031
 bruised-0.031
 Or-0.031
Token fl
Token ID781
Feature activation-1.83e+00

Pos logit contributions
lf+0.062
isy+0.062
 performance+0.060
fulness+0.057
 trophy+0.057
Neg logit contributions
 trash-0.039
 extingu-0.039
 bruised-0.037
gy-0.037
oc-0.037
Tokenapped
Token ID6320
Feature activation-2.20e+00

Pos logit contributions
isy+0.036
lf+0.035
 performance+0.034
fulness+0.032
 trophy+0.032
Neg logit contributions
 trash-0.046
 extingu-0.045
oc-0.044
 bruised-0.044
gy-0.044
Token their
Token ID511
Feature activation+2.01e+00

Pos logit contributions
lf+0.051
isy+0.050
 performance+0.049
fulness+0.046
 trophy+0.046
Neg logit contributions
 trash-0.048
 extingu-0.047
gy-0.046
 bruised-0.046
oc-0.045
Token wings
Token ID12098
Feature activation-2.16e-01

Pos logit contributions
 trash+0.047
 extingu+0.047
 bruised+0.046
gy+0.046
oc+0.046
Neg logit contributions
isy-0.042
lf-0.042
 performance-0.040
 trophy-0.038
fulness-0.038
Token with
Token ID351
Feature activation+2.00e+00

Pos logit contributions
lf+0.007
isy+0.006
 performance+0.006
fulness+0.006
pron+0.006
Neg logit contributions
gy-0.003
 extingu-0.003
 trash-0.003
 bruised-0.003
oc-0.003
Token all
Token ID477
Feature activation-1.79e-01

Pos logit contributions
 trash+0.054
 extingu+0.053
 bruised+0.052
gy+0.052
oc+0.052
Neg logit contributions
lf-0.036
isy-0.035
 performance-0.034
fulness-0.031
 trophy-0.031
Token their
Token ID511
Feature activation+1.22e+00

Pos logit contributions
lf+0.004
isy+0.004
 performance+0.004
fulness+0.004
 trophy+0.004
Neg logit contributions
 trash-0.004
 extingu-0.004
gy-0.004
 bruised-0.004
oc-0.004
Token might
Token ID1244
Feature activation-2.00e+00

Pos logit contributions
 trash+0.028
 extingu+0.027
 bruised+0.027
gy+0.026
oc+0.026
Neg logit contributions
lf-0.027
isy-0.027
 performance-0.026
fulness-0.024
 trophy-0.024
Token and
Token ID290
Feature activation-5.10e-01

Pos logit contributions
lf+0.053
isy+0.053
 performance+0.051
fulness+0.049
 trophy+0.048
Neg logit contributions
 trash-0.037
 extingu-0.036
gy-0.035
 bruised-0.035
oc-0.034
Token suddenly
Token ID6451
Feature activation-1.34e-01

Pos logit contributions
isy+0.012
lf+0.012
 performance+0.011
fulness+0.011
is+0.011
Neg logit contributions
 trash-0.011
 extingu-0.011
gy-0.011
 bruised-0.011
oc-0.011
Token,
Token ID11
Feature activation+2.55e-02

Pos logit contributions
lf+0.003
isy+0.003
 performance+0.003
 trophy+0.003
fulness+0.003
Neg logit contributions
 extingu-0.003
oc-0.003
 trash-0.003
 bruised-0.003
 cigarettes-0.003
Token and
Token ID290
Feature activation+1.61e-01

Pos logit contributions
 trash+0.010
 extingu+0.009
oc+0.009
 bruised+0.009
gy+0.009
Neg logit contributions
lf-0.014
isy-0.014
 performance-0.014
 trophy-0.013
is-0.013
Token it
Token ID340
Feature activation-1.48e+00

Pos logit contributions
 trash+0.004
o+0.003
 bruised+0.003
 Wh+0.003
gy+0.003
Neg logit contributions
isy-0.004
 performance-0.004
lf-0.003
 achievement-0.003
fulness-0.003
Token looked
Token ID3114
Feature activation-1.72e+00

Pos logit contributions
lf+0.038
isy+0.038
 performance+0.036
 trophy+0.035
fulness+0.035
Neg logit contributions
 trash-0.028
 extingu-0.028
 bruised-0.027
oc-0.027
gy-0.026
Token like
Token ID588
Feature activation+5.69e-01

Pos logit contributions
isy+0.046
lf+0.045
 performance+0.045
fulness+0.043
 trophy+0.043
Neg logit contributions
 extingu-0.030
 trash-0.030
gy-0.030
oc-0.029
 bruised-0.029
Token the
Token ID262
Feature activation-1.91e-01

Pos logit contributions
 trash+0.010
 extingu+0.009
 bruised+0.009
 dece+0.009
gy+0.009
Neg logit contributions
isy-0.016
lf-0.016
 performance-0.015
is-0.014
fulness-0.014
Token shape
Token ID5485
Feature activation-1.70e+00

Pos logit contributions
lf+0.004
isy+0.004
 performance+0.004
fulness+0.004
is+0.004
Neg logit contributions
 trash-0.005
 extingu-0.004
 bruised-0.004
 dece-0.004
 bit-0.004
Token that
Token ID326
Feature activation-1.94e+00

Pos logit contributions
isy+0.040
lf+0.040
 performance+0.039
 accomplishment+0.038
 achievement+0.037
Neg logit contributions
 trash-0.035
 bruised-0.033
 extingu-0.033
gy-0.033
o-0.032
Token had
Token ID550
Feature activation-6.46e-03

Pos logit contributions
isy+0.045
lf+0.045
 performance+0.043
fulness+0.040
is+0.040
Neg logit contributions
 trash-0.042
 extingu-0.041
gy-0.040
 bruised-0.040
oc-0.040
Token passed
Token ID3804
Feature activation-4.46e-01

Pos logit contributions
lf+0.000
isy+0.000
 performance+0.000
fulness+0.000
 trophy+0.000
Neg logit contributions
 trash-0.000
 extingu-0.000
oc-0.000
gy-0.000
 bruised-0.000
Token him
Token ID683
Feature activation+8.94e-01

Pos logit contributions
lf+0.009
fulness+0.009
isy+0.009
is+0.009
 performance+0.009
Neg logit contributions
 extingu-0.010
oc-0.010
 Or-0.010
 bruised-0.010
 trash-0.009
Token by
Token ID416
Feature activation+2.47e+00

Pos logit contributions
 extingu+0.019
 trash+0.018
oc+0.018
 bruised+0.018
 dece+0.017
Neg logit contributions
isy-0.021
lf-0.021
 performance-0.020
 trophy-0.019
fulness-0.019
Token finally
Token ID3443
Feature activation-9.76e-01

Pos logit contributions
lf+0.022
isy+0.022
 performance+0.021
fulness+0.021
 trophy+0.020
Neg logit contributions
 trash-0.016
 extingu-0.015
gy-0.015
 bruised-0.015
oc-0.015
Token said
Token ID531
Feature activation-5.18e-01

Pos logit contributions
isy+0.024
lf+0.024
 performance+0.023
is+0.022
fulness+0.022
Neg logit contributions
 extingu-0.020
 trash-0.020
gy-0.019
 bruised-0.019
oc-0.019
Token yes
Token ID3763
Feature activation+2.87e-02

Pos logit contributions
lf+0.011
isy+0.011
 performance+0.010
is+0.010
 achievement+0.010
Neg logit contributions
 bruised-0.012
 trash-0.012
 dece-0.011
 Help-0.011
 Wh-0.011
Token.
Token ID13
Feature activation-9.50e-01

Pos logit contributions
 trash+0.000
gy+0.000
oc+0.000
o+0.000
 bit+0.000
Neg logit contributions
lf-0.001
isy-0.001
 performance-0.001
pron-0.001
 accomplishment-0.001
Token They
Token ID1119
Feature activation-2.00e+00

Pos logit contributions
lf+0.024
isy+0.024
 performance+0.023
 trophy+0.022
fulness+0.022
Neg logit contributions
 trash-0.018
 extingu-0.018
 bruised-0.017
 dece-0.017
gy-0.017
Token went
Token ID1816
Feature activation-5.35e-01

Pos logit contributions
lf+0.052
isy+0.052
 performance+0.050
fulness+0.049
is+0.048
Neg logit contributions
 trash-0.038
gy-0.036
 extingu-0.036
 bruised-0.035
o-0.035
Token to
Token ID284
Feature activation+7.45e-01

Pos logit contributions
isy+0.016
lf+0.015
fulness+0.015
 performance+0.014
pron+0.014
Neg logit contributions
gy-0.009
 trash-0.009
 extingu-0.009
o-0.009
fired-0.008
Token the
Token ID262
Feature activation-1.21e-01

Pos logit contributions
 trash+0.016
 extingu+0.015
 bruised+0.015
oc+0.015
gy+0.015
Neg logit contributions
lf-0.017
isy-0.017
 performance-0.017
 trophy-0.016
fulness-0.016
Token garden
Token ID11376
Feature activation-2.31e-01

Pos logit contributions
lf+0.003
isy+0.002
 performance+0.002
 wedding+0.002
is+0.002
Neg logit contributions
 extingu-0.003
oc-0.003
gy-0.003
 bruised-0.003
o-0.003
Token and
Token ID290
Feature activation-4.96e-01

Pos logit contributions
lf+0.006
isy+0.006
 performance+0.006
fulness+0.006
 trophy+0.006
Neg logit contributions
 trash-0.004
 extingu-0.004
 bruised-0.004
oc-0.004
gy-0.004
Token the
Token ID262
Feature activation-5.83e-01

Pos logit contributions
lf+0.014
isy+0.013
 performance+0.013
 trophy+0.012
fulness+0.012
Neg logit contributions
 trash-0.009
 extingu-0.008
oc-0.008
 bruised-0.008
gy-0.008
Token and
Token ID290
Feature activation-1.84e+00

Pos logit contributions
isy+0.020
lf+0.020
 performance+0.019
fulness+0.018
 trophy+0.018
Neg logit contributions
 trash-0.015
 extingu-0.014
gy-0.014
 bruised-0.014
oc-0.014
Token celebrated
Token ID13943
Feature activation-3.48e+00

Pos logit contributions
isy+0.045
lf+0.044
is+0.041
 performance+0.041
pron+0.040
Neg logit contributions
 trash-0.038
 bruised-0.038
 bit-0.037
o-0.037
gy-0.036
Token every
Token ID790
Feature activation-5.01e-01

Pos logit contributions
lf+0.088
isy+0.088
 performance+0.084
fulness+0.080
 trophy+0.080
Neg logit contributions
 trash-0.067
 extingu-0.066
gy-0.064
 bruised-0.064
oc-0.064
Token time
Token ID640
Feature activation-1.39e+00

Pos logit contributions
isy+0.008
lf+0.008
fulness+0.007
 performance+0.007
is+0.007
Neg logit contributions
 trash-0.015
 bit-0.014
 extingu-0.014
 bruised-0.014
oc-0.014
Token they
Token ID484
Feature activation-1.21e+00

Pos logit contributions
isy+0.031
lf+0.031
 performance+0.030
 trophy+0.028
fulness+0.028
Neg logit contributions
 trash-0.031
 extingu-0.030
 bruised-0.029
gy-0.029
oc-0.029
Token made
Token ID925
Feature activation-3.71e+00

Pos logit contributions
isy+0.031
lf+0.030
 performance+0.029
fulness+0.028
 trophy+0.028
Neg logit contributions
 trash-0.024
 extingu-0.023
 bruised-0.022
gy-0.022
oc-0.022
Token something
Token ID1223
Feature activation-2.34e+00

Pos logit contributions
lf+0.093
isy+0.092
 performance+0.085
 trophy+0.085
pron+0.084
Neg logit contributions
 trash-0.074
 extingu-0.069
 dece-0.069
gy-0.068
oc-0.068
Token new
Token ID649
Feature activation-3.55e-01

Pos logit contributions
lf+0.046
isy+0.044
 performance+0.041
pron+0.039
fulness+0.039
Neg logit contributions
 trash-0.062
 bruised-0.058
 extingu-0.058
 dece-0.057
 bit-0.056
Token.
Token ID13
Feature activation-1.05e+00

Pos logit contributions
lf+0.010
isy+0.010
 performance+0.009
fulness+0.009
is+0.009
Neg logit contributions
 trash-0.006
 extingu-0.006
gy-0.006
 bruised-0.006
oc-0.006
Token
Token ID198
Feature activation-3.13e-01

Pos logit contributions
lf+0.023
isy+0.023
 performance+0.023
fulness+0.022
 trophy+0.022
Neg logit contributions
 trash-0.023
 bruised-0.022
 extingu-0.022
gy-0.021
 dece-0.021
Token
Token ID198
Feature activation-4.12e-01

Pos logit contributions
isy+0.009
lf+0.009
 performance+0.008
 trophy+0.008
fulness+0.008
Neg logit contributions
 trash-0.005
 extingu-0.005
oc-0.005
gy-0.005
 bruised-0.005
Token She
Token ID1375
Feature activation-1.05e+00

Pos logit contributions
isy+0.037
lf+0.037
 performance+0.035
fulness+0.034
 accomplishment+0.033
Neg logit contributions
 extingu-0.029
 trash-0.029
 bruised-0.028
gy-0.028
oc-0.027
Token realized
Token ID6939
Feature activation-1.33e+00

Pos logit contributions
lf+0.027
isy+0.027
 performance+0.026
fulness+0.025
 trophy+0.025
Neg logit contributions
 trash-0.020
 extingu-0.020
gy-0.019
 bruised-0.019
oc-0.019
Token that
Token ID326
Feature activation-1.71e+00

Pos logit contributions
isy+0.029
lf+0.029
 performance+0.029
pron+0.029
 vows+0.027
Neg logit contributions
 trash-0.028
 Wh-0.028
 bruised-0.027
Bad-0.026
fired-0.026
Token sometimes
Token ID3360
Feature activation-1.99e+00

Pos logit contributions
isy+0.039
lf+0.037
 performance+0.036
is+0.035
pron+0.034
Neg logit contributions
 trash-0.039
 bruised-0.037
 dece-0.036
 extingu-0.036
 Wh-0.036
Token things
Token ID1243
Feature activation-3.27e+00

Pos logit contributions
isy+0.046
lf+0.045
pron+0.042
 performance+0.042
is+0.042
Neg logit contributions
 trash-0.046
 bruised-0.042
 dece-0.042
gy-0.040
 extingu-0.040
Token can
Token ID460
Feature activation-4.14e+00

Pos logit contributions
lf+0.086
isy+0.085
 performance+0.082
is+0.078
fulness+0.078
Neg logit contributions
 trash-0.061
 extingu-0.058
 bruised-0.057
gy-0.057
 dece-0.055
Token seem
Token ID1283
Feature activation-2.94e+00

Pos logit contributions
lf+0.100
isy+0.099
 performance+0.095
fulness+0.091
 trophy+0.090
Neg logit contributions
 trash-0.085
 extingu-0.083
gy-0.082
 bruised-0.081
oc-0.079
Token scary
Token ID14343
Feature activation-1.88e+00

Pos logit contributions
isy+0.058
 performance+0.057
lf+0.055
 trophy+0.053
fulness+0.052
Neg logit contributions
oc-0.073
 extingu-0.071
gy-0.070
 trash-0.068
 bruised-0.068
Token,
Token ID11
Feature activation-2.75e+00

Pos logit contributions
isy+0.044
 performance+0.044
lf+0.044
fulness+0.042
 trophy+0.041
Neg logit contributions
 extingu-0.038
oc-0.038
 trash-0.037
gy-0.037
 bruised-0.036
Token but
Token ID475
Feature activation-1.51e+00

Pos logit contributions
lf+0.073
isy+0.073
 performance+0.071
fulness+0.068
 trophy+0.067
Neg logit contributions
 trash-0.049
 extingu-0.048
gy-0.047
oc-0.046
 bruised-0.046
Token they
Token ID484
Feature activation-2.05e+00

Pos logit contributions
lf+0.035
isy+0.034
 performance+0.032
pron+0.031
ves+0.030
Neg logit contributions
 trash-0.034
 bruised-0.033
 dece-0.032
 extingu-0.031
fired-0.030
Token the
Token ID262
Feature activation-3.83e-01

Pos logit contributions
 extingu+0.049
 trash+0.049
 bruised+0.048
oc+0.048
 dece+0.047
Neg logit contributions
lf-0.058
 performance-0.056
isy-0.054
 trophy-0.054
 accomplishment-0.053
Token yacht
Token ID43207
Feature activation+6.34e-03

Pos logit contributions
isy+0.008
fulness+0.008
lf+0.008
quet+0.008
 performance+0.007
Neg logit contributions
 trash-0.010
 extingu-0.009
 hyd-0.008
gy-0.008
 bit-0.008
Token and
Token ID290
Feature activation-6.24e-02

Pos logit contributions
 trash+0.000
 extingu+0.000
 bruised+0.000
 dece+0.000
oc+0.000
Neg logit contributions
lf-0.000
isy-0.000
 performance-0.000
 trophy-0.000
fulness-0.000
Token started
Token ID2067
Feature activation-4.06e-01

Pos logit contributions
lf+0.002
isy+0.002
 performance+0.002
 trophy+0.001
fulness+0.001
Neg logit contributions
 trash-0.001
 extingu-0.001
 bruised-0.001
gy-0.001
oc-0.001
Token to
Token ID284
Feature activation+4.72e-01

Pos logit contributions
isy+0.011
lf+0.011
fulness+0.010
 performance+0.010
is+0.010
Neg logit contributions
 trash-0.007
gy-0.007
 extingu-0.007
o-0.007
 bruised-0.007
Token play
Token ID711
Feature activation-4.19e+00

Pos logit contributions
 trash+0.011
 extingu+0.011
gy+0.011
 bruised+0.011
oc+0.010
Neg logit contributions
isy-0.010
lf-0.010
 performance-0.010
fulness-0.009
is-0.009
Token.
Token ID13
Feature activation-6.71e-01

Pos logit contributions
isy+0.131
lf+0.123
 performance+0.121
pron+0.120
fulness+0.118
Neg logit contributions
 trash-0.062
oc-0.059
 Wh-0.052
gy-0.052
 extingu-0.051
Token He
Token ID679
Feature activation-5.11e-01

Pos logit contributions
lf+0.014
isy+0.014
 hardly+0.014
fulness+0.013
 accomplishment+0.013
Neg logit contributions
 extingu-0.015
 bruised-0.015
 trash-0.014
 hyd-0.014
 dece-0.014
Token felt
Token ID2936
Feature activation-3.82e-01

Pos logit contributions
lf+0.013
isy+0.013
 performance+0.012
 trophy+0.012
is+0.012
Neg logit contributions
 extingu-0.010
 trash-0.010
 bruised-0.010
oc-0.009
gy-0.009
Token very
Token ID845
Feature activation+5.99e-01

Pos logit contributions
isy+0.007
 performance+0.007
lf+0.007
 trophy+0.006
 accomplishment+0.006
Neg logit contributions
 extingu-0.010
gy-0.010
oc-0.010
 trash-0.010
fired-0.009
Token comfort
Token ID4467
Feature activation-6.41e-01

Pos logit contributions
 trash+0.016
 bruised+0.015
 dece+0.015
oc+0.014
 extingu+0.014
Neg logit contributions
lf-0.012
isy-0.012
 performance-0.011
fulness-0.010
pron-0.010
Token loved
Token ID6151
Feature activation-1.71e+00

Pos logit contributions
isy+0.045
 performance+0.045
lf+0.044
fulness+0.043
 achievement+0.043
Neg logit contributions
 trash-0.030
gy-0.029
oc-0.028
o-0.028
 bruised-0.027
Token to
Token ID284
Feature activation-2.04e+00

Pos logit contributions
isy+0.057
fulness+0.054
lf+0.051
 accomplishment+0.050
 achievement+0.050
Neg logit contributions
 trash-0.027
 Wh-0.026
o-0.025
 cigarettes-0.022
 extingu-0.022
Token draw
Token ID3197
Feature activation-5.81e+00

Pos logit contributions
isy+0.057
fulness+0.056
is+0.053
lf+0.053
 accomplishment+0.052
Neg logit contributions
 trash-0.035
 extingu-0.034
gy-0.032
 Wh-0.032
 bit-0.032
Token and
Token ID290
Feature activation-1.33e+00

Pos logit contributions
isy+0.157
 accomplishment+0.156
 performance+0.154
 achievement+0.153
fulness+0.150
Neg logit contributions
 trash-0.101
c-0.098
oc-0.094
 Wh-0.092
o-0.089
Token make
Token ID787
Feature activation-5.20e+00

Pos logit contributions
fulness+0.036
isy+0.036
LC+0.034
 achievement+0.033
ement+0.033
Neg logit contributions
 trash-0.025
 bit-0.022
 cigarettes-0.020
c-0.020
 Wh-0.020
Token things
Token ID1243
Feature activation-3.66e+00

Pos logit contributions
isy+0.125
fulness+0.121
lf+0.117
 ceremony+0.114
pron+0.113
Neg logit contributions
 trash-0.118
 Wh-0.104
c-0.103
 dece-0.102
 cigarettes-0.098
Token.
Token ID13
Feature activation-1.83e+00

Pos logit contributions
lf+0.121
isy+0.117
mber+0.116
pron+0.111
LC+0.110
Neg logit contributions
 trash-0.050
 extingu-0.045
c-0.041
 bruised-0.041
 hyd-0.040
Token One
Token ID1881
Feature activation-8.72e-01

Pos logit contributions
lf+0.055
isy+0.055
 performance+0.054
 achievement+0.051
 accomplishment+0.051
Neg logit contributions
 trash-0.029
gy-0.026
 Wh-0.026
 extingu-0.026
 bruised-0.025
Token day
Token ID1110
Feature activation-7.84e-01

Pos logit contributions
lf+0.011
isy+0.011
 performance+0.011
fulness+0.010
 trophy+0.010
Neg logit contributions
 trash-0.028
 extingu-0.027
oc-0.027
gy-0.027
 bruised-0.026
Token,
Token ID11
Feature activation-1.76e+00

Pos logit contributions
lf+0.018
isy+0.018
 performance+0.017
 trophy+0.016
fulness+0.016
Neg logit contributions
 extingu-0.017
 trash-0.017
gy-0.017
oc-0.017
 bruised-0.016
Token she
Token ID673
Feature activation-1.56e+00

Pos logit contributions
isy+0.035
 performance+0.034
lf+0.033
fulness+0.032
 achievement+0.031
Neg logit contributions
 trash-0.046
 Wh-0.043
 bruised-0.042
 extingu-0.042
gy-0.041
Token wanted
Token ID2227
Feature activation-1.80e+00

Pos logit contributions
 trash+0.011
 extingu+0.011
 bruised+0.011
gy+0.010
oc+0.010
Neg logit contributions
lf-0.014
isy-0.014
 performance-0.013
fulness-0.013
is-0.013
Token to
Token ID284
Feature activation-5.14e-01

Pos logit contributions
isy+0.047
lf+0.047
 performance+0.044
 trophy+0.042
fulness+0.042
Neg logit contributions
 trash-0.035
 extingu-0.034
 bruised-0.033
gy-0.032
o-0.032
Token stay
Token ID2652
Feature activation-8.05e-01

Pos logit contributions
lf+0.012
isy+0.012
 performance+0.011
fulness+0.011
is+0.011
Neg logit contributions
 trash-0.011
gy-0.010
 extingu-0.010
 bruised-0.010
 Wh-0.010
Token home
Token ID1363
Feature activation+2.13e-01

Pos logit contributions
lf+0.019
 performance+0.019
isy+0.019
 achievement+0.017
 accomplishment+0.017
Neg logit contributions
 trash-0.016
 extingu-0.016
oc-0.016
 bruised-0.016
 dece-0.015
Token and
Token ID290
Feature activation-4.35e-01

Pos logit contributions
 trash+0.004
 extingu+0.004
oc+0.004
 bruised+0.004
gy+0.004
Neg logit contributions
lf-0.005
isy-0.005
 performance-0.005
fulness-0.005
 trophy-0.005
Token play
Token ID711
Feature activation-3.87e+00

Pos logit contributions
isy+0.010
lf+0.010
 performance+0.009
is+0.009
fulness+0.009
Neg logit contributions
 trash-0.010
gy-0.009
 bruised-0.009
 extingu-0.009
oc-0.009
Token.
Token ID13
Feature activation-5.09e-01

Pos logit contributions
isy+0.107
lf+0.105
 performance+0.101
is+0.097
fulness+0.097
Neg logit contributions
 trash-0.067
 extingu-0.063
oc-0.063
gy-0.063
 bruised-0.062
Token
Token ID198
Feature activation+3.50e-01

Pos logit contributions
lf+0.012
isy+0.011
 performance+0.011
fulness+0.011
pron+0.010
Neg logit contributions
 trash-0.011
 extingu-0.011
 bruised-0.010
gy-0.010
 dece-0.010
Token
Token ID198
Feature activation+4.22e-02

Pos logit contributions
 trash+0.005
 extingu+0.005
 bruised+0.005
gy+0.005
oc+0.005
Neg logit contributions
lf-0.010
isy-0.010
 performance-0.010
fulness-0.010
 trophy-0.009
TokenGrand
Token ID23581
Feature activation-1.92e+00

Pos logit contributions
 trash+0.001
 extingu+0.001
gy+0.001
 bruised+0.001
oc+0.001
Neg logit contributions
lf-0.001
isy-0.001
 performance-0.001
fulness-0.001
is-0.001
Tokenma
Token ID2611
Feature activation+8.13e-01

Pos logit contributions
isy+0.050
 trophy+0.047
 performance+0.046
 accomplishment+0.046
fulness+0.045
Neg logit contributions
o-0.036
oc-0.034
 extingu-0.034
c-0.033
 trash-0.032