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

    Neuronpedia

    INDEX
    Explanations

    terms related to separation and distinction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     velho
    -0.57
     Gamb
    -0.56
    unnitel
    -0.56
    PageRoute
    -0.55
    Pratique
    -0.54
    PageIndex
    -0.53
     Hawkeye
    -0.53
    DataAnnotations
    -0.53
    примеча
    -0.52
     Fittings
    -0.52
    POSITIVE LOGITS
     separating
    0.99
     Separation
    0.98
     separation
    0.95
     Separ
    0.95
     separ
    0.95
     SEPAR
    0.92
    Separation
    0.91
     separates
    0.90
     separations
    0.87
     Separator
    0.83
    Act Density 0.103%

    No Known Activations