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

    Neuronpedia

    INDEX
    Explanations

    references to pagination or page numbers related to documents or databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jeta
    -0.17
    enha
    -0.17
    oog
    -0.17
    æ¯
    -0.16
    stras
    -0.16
    æģ
    -0.16
    jvu
    -0.15
    orial
    -0.14
    uforia
    -0.14
    jours
    -0.14
    POSITIVE LOGITS
     Pag
    0.20
     pg
    0.18
    /pg
    0.17
     ReturnType
    0.17
    oda
    0.16
    .pg
    0.16
    andom
    0.15
    urus
    0.15
    (pg
    0.15
     Nack
    0.15
    Act Density 0.017%

    No Known Activations