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

    Neuronpedia

    INDEX
    Explanations

    the beginning of statements or sections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.06
    Portale
    -0.90
    Tikang
    -0.81
    rxjs
    -0.73
    Rüyada
    -0.72
     SUDOC
    -0.72
    IntoConstraints
    -0.71
     هيا
    -0.70
    sizePolicy
    -0.70
     pinulongan
    -0.70
    POSITIVE LOGITS
    '
    0.88
    mathrm
    0.70
     dalamnya
    0.67
    ñora
    0.67
    [toxicity=0]
    0.64
     nicio
    0.62
    󠁿
    0.61
     nostru
    0.60
    ;#
    0.60
     strå
    0.60
    Act Density 0.000%

    No Known Activations