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

    Neuronpedia

    INDEX
    Explanations

    references to descriptive statistics and their analyses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.80
     autorytatywna
    -0.75
     disambiguazione
    -0.73
     utafitiHapana
    -0.70
    djangoproject
    -0.70
     NLI
    -0.70
     omnia
    -0.69
    Portail
    -0.69
     محفوظة
    -0.69
    IGraphics
    -0.68
    POSITIVE LOGITS
     descriptive
    0.70
    Descriptive
    0.70
     Descriptive
    0.66
     chung
    0.62
    criptive
    0.50
    roller
    0.45
    0.45
    لاک
    0.45
    Nhap
    0.45
    شف
    0.44
    Act Density 0.004%

    No Known Activations