Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of positivity or admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.95
     okuyayım
    -0.78
     ModelExpression
    -0.77
    argout
    -0.75
    InjectMocks
    -0.74
    endpush
    -0.73
    AntiForgeryToken
    -0.73
     Deum
    -0.73
    Xf
    -0.72
    IntentFilter
    -0.72
    POSITIVE LOGITS
     pretty
    1.42
     Pretty
    1.31
    Pretty
    1.28
    pretty
    1.27
     darn
    1.16
     PRET
    1.00
     Fairly
    0.96
     fairly
    0.94
    PRET
    0.92
    retty
    0.87
    Act Density 0.046%

    No Known Activations