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

    Neuronpedia

    INDEX
    Explanations

    words related to specific needs and requirements

    oai_token-act-pair · gpt-3.5-turbo

    references to various human needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.64
    onym
    -0.62
     Dak
    -0.61
     rabbit
    -0.59
    âĸ¬
    -0.59
     Bad
    -0.58
     Bom
    -0.58
     rook
    -0.57
     Pill
    -0.57
     skiing
    -0.57
    POSITIVE LOGITS
    cale
    0.78
    afety
    0.75
    pace
    0.75
    afe
    0.73
    giving
    0.73
     attention
    0.70
    lessly
    0.70
    î
    0.68
     dictate
    0.67
    ylum
    0.67
    Act Density 0.034%

    No Known Activations