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

    Neuronpedia

    INDEX
    Explanations

    references to inner structures or components within a system

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     referenties
    -0.91
    VersionUID
    -0.89
    ization
    -0.88
    providedIn
    -0.87
     nahilalakip
    -0.84
    xFFFFFFFF
    -0.83
    gerald
    -0.79
    alisation
    -0.78
    ized
    -0.78
    ➟
    -0.78
    POSITIVE LOGITS
     Sewell
    0.84
    y
    0.75
     INNER
    0.75
    INNER
    0.68
    ing
    0.67
     Inner
    0.67
    Gonna
    0.67
     Brenner
    0.67
     CreateTagHelper
    0.65
     Winn
    0.65
    Act Density 0.009%

    No Known Activations