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

    Neuronpedia

    INDEX
    Explanations

    terms related to assumptions and properties in statistical modeling, particularly in the context of graphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategorie
    -0.50
     emotionally
    -0.48
    mlı
    -0.47
     Goldstein
    -0.46
    ATIONS
    -0.44
    ेशा
    -0.44
    ed
    -0.44
     Vane
    -0.44
     quarto
    -0.43
     humble
    -0.43
    POSITIVE LOGITS
    fulness
    1.16
    ateness
    0.97
    omeness
    0.95
    reness
    0.90
    teness
    0.90
    siveness
    0.89
    eness
    0.85
    RectangleBorder
    0.85
     nahilalakip
    0.85
    MigrationBuilder
    0.83
    Act Density 0.737%

    No Known Activations