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

    Neuronpedia

    INDEX
    Explanations

    numeric values, code snippets, and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to gaming or combat mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.71
     .)
    -0.63
    BuyableInstoreAndOnline
    -0.63
     disg
    -0.60
     )]
    -0.59
     unpop
    -0.58
     pseudonym
    -0.55
    "},"
    -0.55
     ancest
    -0.55
     ferment
    -0.54
    POSITIVE LOGITS
    *:
    1.28
    %:
    1.26
    :
    1.23
    !:
    1.19
    ':
    1.13
    ":
    1.07
    ?:
    1.07
    :#
    1.02
    ():
    0.98
     :
    0.96
    Act Density 0.289%

    No Known Activations