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

    Neuronpedia

    INDEX
    Explanations

    specific words associated with categorization or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ate
    -1.63
    ть
    -1.29
    ize
    -0.95
    ATE
    -0.90
    ć
    -0.66
    ulate
    -0.55
    atex
    -0.47
    geable
    -0.46
    licate
    -0.45
    RefNanny
    -0.44
    POSITIVE LOGITS
    httphttps
    0.54
     nahilalakip
    0.49
    Personendaten
    0.45
     contextLoads
    0.44
    -------------</
    0.43
    ⓧ
    0.42
     NSCoder
    0.42
    oredCriteria
    0.41
    InjectAttribute
    0.41
    outState
    0.40
    Act Density 0.418%

    No Known Activations