INDEX
Explanations
dimensional
This neuron detects mentions of “two-dimensional” descriptors in the text.
New Auto-Interp
Negative Logits
copyright
-0.07
Zoo
-0.06
124
-0.06
-back
-0.06
satış
-0.06
greetings
-0.06
back
-0.06
request
-0.06
Aircraft
-0.06
763
-0.06
POSITIVE LOGITS
UILTIN
0.07
Sit
0.07
thoải
0.07
omap
0.07
Calculator
0.06
’’
0.06
dimensional
0.06
observational
0.06
parach
0.06
Θ
0.06
Activations Density 0.008%