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

    Neuronpedia

    INDEX
    Explanations

    terms that refer to precision or accuracy in measurements and models

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    aged
    -0.72
    Billie
    -0.70
    styleType
    -0.70
     Misch
    -0.69
     Bundy
    -0.69
     ImGui
    -0.68
    かれています
    -0.68
    ezy
    -0.67
     Gentile
    -0.65
    Specified
    -0.64
    POSITIVE LOGITS
     Exacts
    0.61
    igneur
    0.59
     tramonto
    0.58
    CloseOperation
    0.57
    ⓧ
    0.57
     Lev
    0.56
    arkiv
    0.55
    HttpFoundation
    0.55
    Linq
    0.53
    (!__
    0.53
    Act Density 0.006%

    No Known Activations