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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and dialogue indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olis
    -0.16
    lex
    -0.15
     frontal
    -0.15
    ods
    -0.14
    ugin
    -0.14
    infos
    -0.14
    inen
    -0.13
    finity
    -0.13
    ukan
    -0.13
    ufen
    -0.13
    POSITIVE LOGITS
    phans
    0.17
    Ľå»º
    0.16
    ERG
    0.15
    sWith
    0.15
    apons
    0.15
     Clarkson
    0.14
    clado
    0.14
    Buffers
    0.14
    ToDevice
    0.13
    ampus
    0.13
    Act Density 0.055%

    No Known Activations