INDEX
Explanations
expressions of existential concerns or feelings of uncertainty
New Auto-Interp
Negative Logits
S
-0.91
p
-0.90
L
-0.89
P
-0.89
T
-0.88
p
-0.86
D
-0.86
M
-0.85
C
-0.84
N
-0.82
POSITIVE LOGITS
myſelf
2.22
itſelf
2.14
Monfieur
1.96
Anſ
1.95
himſelf
1.95
themſelves
1.94
ſelf
1.93
ſeveral
1.91
purpoſe
1.88
raiſ
1.87
Activations Density 0.140%