INDEX
Explanations
expressions of futility and lack of purpose in actions or situations
New Auto-Interp
Negative Logits
apes
-0.17
ouncer
-0.16
ноÑģÑĤÑĮÑİ
-0.16
Cond
-0.15
Cond
-0.15
iston
-0.14
ith
-0.14
omy
-0.14
-cond
-0.14
æĨ
-0.14
POSITIVE LOGITS
ikt
0.15
rzy
0.14
Goldberg
0.14
ajan
0.14
Prep
0.14
ados
0.14
orda
0.14
áng
0.14
heim
0.13
iker
0.13
Activations Density 0.207%