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

    Neuronpedia

    INDEX
    Explanations

    words related to physical discomfort or negative experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to headaches and their impact, contrasting them with pleasantries or unpleasant situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yson
    -0.71
    ature
    -0.66
    Max
    -0.66
    ized
    -0.63
    Origin
    -0.63
    wana
    -0.63
    reverse
    -0.62
    Age
    -0.61
    laws
    -0.61
    max
    -0.61
    POSITIVE LOGITS
     pleasant
    2.22
     unpleasant
    2.14
     headache
    1.78
    pleasant
    1.73
     headaches
    1.58
     painful
    1.40
     enjoyable
    1.27
     thorn
    1.26
     friction
    1.24
     pleasure
    1.14
    Act Density 0.023%

    No Known Activations