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

    Neuronpedia

    INDEX
    Explanations

    certain types of parameters and their attributes in a configuration or settings context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.75
    verwijspagina
    -0.73
     lenker
    -0.67
    Hochspringen
    -0.64
    Revenir
    -0.60
     marié
    -0.60
    forChild
    -0.57
    Erstellt
    -0.56
    zzleHttp
    -0.56
    PLEMENT
    -0.55
    POSITIVE LOGITS
    کان
    0.62
     mergeFrom
    0.62
    nodoc
    0.62
     sáng
    0.61
    قه
    0.59
     "-"
    0.59
    ："
    0.56
    tigem
    0.56
     Stephens
    0.55
     Constance
    0.54
    Act Density 0.053%

    No Known Activations