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

    Neuronpedia

    INDEX
    Explanations

    topics related to technology and performance in gaming and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.90
    Tikang
    -0.75
    ьаж
    -0.71
    QMetaType
    -0.71
    IContainer
    -0.70
    eynman
    -0.66
    uxxxx
    -0.65
    RTCF
    -0.65
    inghouse
    -0.65
     Roskov
    -0.64
    POSITIVE LOGITS
     wise
    2.65
    wise
    2.52
    Wise
    1.81
    WISE
    1.72
     Wise
    1.63
     WISE
    1.59
     speaking
    1.10
     wisest
    1.10
     wiser
    1.04
    istically
    1.02
    Act Density 0.164%

    No Known Activations