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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures in programming or scientific documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.62
     propOrder
    -0.61
     Stoppers
    -0.59
     Roskov
    -0.58
     transfieras
    -0.58
    elemField
    -0.55
    CharStream
    -0.55
    Filmographie
    -0.55
    ỏng
    -0.53
     Picchu
    -0.53
    POSITIVE LOGITS
    assertArray
    0.61
    IsRequired
    0.55
     Вікіпе
    0.55
    {}".
    0.53
    undred
    0.53
     ModelExpression
    0.52
    ).__
    0.52
    lossene
    0.51
    ponym
    0.51
    umumkan
    0.50
    Act Density 0.640%

    No Known Activations