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

    Neuronpedia

    INDEX
    Explanations

    references to small-scale or minor events, actions, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uvo
    -0.68
    lıyor
    -0.67
     ModelExpression
    -0.65
     berlina
    -0.64
    גרת
    -0.64
    eraard
    -0.63
    quehanna
    -0.63
    |}{\
    -0.63
    المصدر
    -0.61
    Награды
    -0.61
    POSITIVE LOGITS
     small
    1.92
     Small
    1.89
    small
    1.84
    Small
    1.84
     SMALL
    1.83
    SMALL
    1.70
     smal
    1.45
     tiny
    1.42
     Smal
    1.35
    小
    1.33
    Act Density 0.084%

    No Known Activations