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

    Neuronpedia

    INDEX
    Explanations

    interjections or filler phrases indicating uncertainty or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.79
    AnchorStyles
    -0.74
    addCriterion
    -0.73
    Tikang
    -0.67
     الرياضيه
    -0.65
    ConstraintMaker
    -0.64
    UnusedPrivate
    -0.62
    atchi
    -0.60
     Prentice
    -0.59
     Ti
    -0.59
    POSITIVE LOGITS
     uovo
    0.66
    atrième
    0.65
     Pong
    0.65
    bliž
    0.64
     Matth
    0.63
     Phry
    0.62
     Balt
    0.61
     énergétique
    0.61
     stratégique
    0.60
     leçon
    0.60
    Act Density 0.460%

    No Known Activations