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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PE
    -1.23
     PE
    -1.15
     Ply
    -1.02
    pe
    -0.94
     peas
    -0.91
     Pom
    -0.89
     Olive
    -0.88
    PU
    -0.87
    PI
    -0.87
     Petersen
    -0.86
    POSITIVE LOGITS
    ault
    1.04
    Bull
    0.94
     Bull
    0.90
    Az
    0.89
    aults
    0.88
     Braz
    0.83
     bull
    0.82
    bull
    0.82
     Crypt
    0.82
    coll
    0.80
    Act Density 0.641%

    No Known Activations