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

    Neuronpedia

    INDEX
    Explanations

    references to measurements or statistical significance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IndentedString
    -0.75
    __*/
    -0.65
    ագրություններ
    -0.64
    LabelTagHelper
    -0.56
    NewUrlParser
    -0.52
    UrlResolution
    -0.50
    scaleY
    -0.50
    تفصیلات
    -0.50
     Signalez
    -0.50
     Exacts
    -0.50
    POSITIVE LOGITS
     auffi
    0.67
     purpoſe
    0.67
     pleaſure
    0.67
     ſche
    0.66
    ſelves
    0.64
    æng
    0.63
     Reſ
    0.63
     MNRAS
    0.62
     ainfi
    0.61
     ſeveral
    0.60
    Act Density 0.048%

    No Known Activations