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

    Neuronpedia

    INDEX
    Explanations

    types of establishments with specific policies or characteristics such as being kid-friendly, dog-friendly, non-smoking, etc

    oai_token-act-pair · gpt-3.5-turbo

    terms related to safety, defense, and welfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.67
    ascript
    -0.64
    hidden
    -0.58
    hower
    -0.58
    etime
    -0.57
     cellul
    -0.56
    ework
    -0.56
    strings
    -0.56
    utsche
    -0.56
    ryu
    -0.55
    POSITIVE LOGITS
     Tycoon
    0.70
    iasco
    0.70
     Bett
    0.67
    escription
    0.65
    ichick
    0.63
    âĨij
    0.63
    itiz
    0.62
    unta
    0.61
    opa
    0.59
     Gian
    0.58
    Act Density 0.459%

    No Known Activations