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

    Neuronpedia

    INDEX
    Explanations

    key details related to property descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?
    -0.15
    ou
    -0.14
    .
    -0.14
     odds
    -0.14
    -t
    -0.14
     parl
    -0.14
    ised
    -0.14
    ib
    -0.13
    airs
    -0.13
    chron
    -0.13
    POSITIVE LOGITS
     pec
    0.15
    akis
    0.15
    undos
    0.15
     Blowjob
    0.15
    igham
    0.15
    aggi
    0.15
    ģm
    0.15
    pec
    0.14
    rito
    0.14
    inness
    0.14
    Act Density 0.302%

    No Known Activations