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

    Neuronpedia

    INDEX
    Explanations

    questions or statements expressing doubt or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of confusion or disbelief about specific situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.84
    tsy
    -0.69
    pter
    -0.68
    vantage
    -0.67
    tnc
    -0.65
    aeper
    -0.64
    ieu
    -0.61
    catentry
    -0.61
    cu
    -0.61
    folios
    -0.60
    POSITIVE LOGITS
    ?!"
    1.23
    ?!
    1.18
    !?"
    1.17
    !?
    1.13
    ?",
    0.98
    ?"
    0.98
    ???
    0.98
    ?)
    0.96
    ?
    0.96
    ?),
    0.95
    Act Density 0.184%

    No Known Activations