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

    Neuronpedia

    INDEX
    Explanations

    topics related to various forms of accusations or claims

    oai_token-act-pair · gpt-3.5-turbo

    references to significant issues or concerns in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.77
     Aging
    -0.65
     Increases
    -0.64
     Athletics
    -0.63
     Accounting
    -0.63
     Prompt
    -0.62
    ĸļ
    -0.62
     Tactics
    -0.61
     Serve
    -0.60
    CHAT
    -0.60
    POSITIVE LOGITS
    iest
    1.00
     imaginable
    0.84
     involved
    0.82
     notor
    0.72
    nut
    0.72
    liest
    0.72
    ses
    0.72
    ailable
    0.71
    nuts
    0.70
    farious
    0.68
    Act Density 0.410%

    No Known Activations