INDEX
Explanations
the word "rather" indicating preferences or alternatives in various contexts
New Auto-Interp
Negative Logits
ridge
-0.19
ahl
-0.17
irit
-0.15
acon
-0.15
acia
-0.14
’te
-0.14
exion
-0.14
Buffers
-0.14
amura
-0.14
úi
-0.13
POSITIVE LOGITS
than
0.37
than
0.26
THAN
0.21
_than
0.20
niż
0.19
-than
0.18
Than
0.18
än
0.17
Than
0.17
než
0.17
Activations Density 0.016%