INDEX
Explanations
terms related to sizes and scales in scientific contexts, particularly focusing on "macro" and "micro"
New Auto-Interp
Negative Logits
myſelf
-0.53
Houſe
-0.52
ſta
-0.52
Eſ
-0.52
juſ
-0.50
Jefus
-0.50
beſ
-0.49
Conſ
-0.49
Reſ
-0.49
houſe
-0.48
POSITIVE LOGITS
macro
0.79
:✨
0.68
Mir
0.68
Mir
0.68
macro
0.66
micro
0.66
mir
0.63
Macro
0.61
Macro
0.59
Micro
0.57
Activations Density 0.457%