INDEX
Explanations
separators
The neuron is specialized to pick out version identifiers (especially hyphens and adjacent numerals) in dependency coordinates or file names.
New Auto-Interp
Negative Logits
VV
-0.07
Kabul
-0.06
hvě
-0.06
Animate
-0.06
beraber
-0.06
Vector
-0.06
dagen
-0.06
Icon
-0.06
pregnant
-0.06
εξ
-0.06
POSITIVE LOGITS
приб
0.06
_terminal
0.06
이다
0.06
ithmetic
0.06
nast
0.06
not
0.06
↵↵↵↵↵↵↵↵↵↵↵↵↵↵
0.06
apparent
0.06
給
0.06
شان
0.06
Activations Density 0.013%