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

    Neuronpedia

    INDEX
    Explanations

    references to pockets

    oai_token-act-pair · gpt-3.5-turbo

    references to financial resources or income

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ANGEL
    -0.94
    Reviewer
    -0.78
    actionDate
    -0.73
    slow
    -0.72
    jad
    -0.68
    CAST
    -0.68
    SPA
    -0.67
     Abuse
    -0.63
    REDACTED
    -0.61
     Arri
    -0.61
    POSITIVE LOGITS
     pocket
    1.00
    pocket
    0.93
     pouch
    0.86
     pockets
    0.85
    book
    0.84
    lain
    0.83
    books
    0.82
    ricular
    0.79
    knife
    0.78
    nuts
    0.78
    Act Density 0.013%

    No Known Activations