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

    Neuronpedia

    INDEX
    Explanations

    phrases related to risk, impact, and causation

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that indicate risk or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unic
    -0.68
    odo
    -0.66
    ©¶æ
    -0.64
    rounder
    -0.62
     apiece
    -0.62
    ocious
    -0.60
    ebook
    -0.60
    usp
    -0.58
    raph
    -0.56
    amer
    -0.55
    POSITIVE LOGITS
    particularly
    0.76
    eele
    0.71
     namely
    0.70
    especially
    0.68
     outweigh
    0.64
     Particularly
    0.64
    aeda
    0.62
    Whereas
    0.62
     Whereas
    0.60
    bda
    0.60
    Act Density 1.094%

    No Known Activations