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

    Neuronpedia

    INDEX
    Explanations

    names or references to individuals involved in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    379
    -0.16
    ivet
    -0.15
    ension
    -0.14
    laughter
    -0.14
     TextAlign
    -0.13
    arme
    -0.13
    STANCE
    -0.13
    wyn
    -0.13
    Outcome
    -0.13
    noon
    -0.13
    POSITIVE LOGITS
    bies
    0.16
    aukee
    0.15
     ç¥
    0.14
    /or
    0.13
     gep
    0.13
    yon
    0.13
    yles
    0.13
    ãĤĪãģı
    0.12
     arkadaÅŁ
    0.12
     Pavilion
    0.12
    Act Density 0.033%

    No Known Activations