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

    Neuronpedia

    INDEX
    Explanations

    mathematical derivatives

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    enumi
    -0.78
    Hauptartikel
    -0.77
     FetchType
    -0.73
     Efq
    -0.73
    ArgsConstructor
    -0.70
     nakalista
    -0.70
     Talley
    -0.70
     fhort
    -0.70
     Shakspeare
    -0.70
     Nego
    -0.68
    POSITIVE LOGITS
     للاسماء
    0.68
    Grin
    0.55
    er
    0.52
    orn
    0.52
    ido
    0.51
     My
    0.49
     Grin
    0.48
    ád
    0.48
    >');
    0.48
     lại
    0.48
    Act Density 0.004%

    No Known Activations