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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to variation or variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.63
    EDEFAULT
    -0.63
     wikipagina
    -0.56
    脚注の使い方
    -0.55
     незавершена
    -0.55
    TagMode
    -0.52
    MigrationBuilder
    -0.52
    ########.
    -0.52
    RectangleBorder
    -0.52
    -0.51
    POSITIVE LOGITS
     VARI
    0.91
    VARI
    0.87
     variation
    0.86
     Var
    0.83
     Vari
    0.83
     vari
    0.82
     Variation
    0.82
     var
    0.82
    Var
    0.77
    vari
    0.77
    Act Density 1.685%

    No Known Activations