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

    Neuronpedia

    INDEX
    Explanations

    the word "only" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     communis
    -0.64
    kkue
    -0.61
    baguna
    -0.58
    yntaxException
    -0.58
     numberWith
    -0.56
    Simplicity
    -0.56
     trocken
    -0.54
     llorar
    -0.53
    ÍTICA
    -0.52
    gtest
    -0.52
    POSITIVE LOGITS
     dopiero
    0.79
     autorytatywna
    0.74
     only
    0.63
     till
    0.63
     until
    0.63
    脚注の使い方
    0.62
     baru
    0.61
     Erst
    0.60
    RenderAtEndOf
    0.59
     ogóle
    0.59
    Act Density 0.296%

    No Known Activations