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

    Neuronpedia

    INDEX
    Explanations

    technical terms and acronyms related to technological or political aspects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    edly
    -0.63
    cius
    -0.61
    itably
    -0.60
     actionGroup
    -0.60
    aunder
    -0.58
    pection
    -0.58
    ulators
    -0.57
    unknown
    -0.57
    iners
    -0.56
    inet
    -0.56
    POSITIVE LOGITS
    uple
    0.99
    olkien
    0.87
    olerance
    0.85
    uesday
    0.82
    itled
    0.82
    onomy
    0.81
    ourney
    0.79
    pole
    0.78
    pees
    0.78
    ango
    0.77
    Act Density 1.504%

    No Known Activations