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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or brand names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.79
     furthermore
    -0.77
     matters
    -0.76
     tempted
    -0.73
    Joined
    -0.72
     suppose
    -0.72
    iety
    -0.72
     besides
    -0.72
     irrespective
    -0.71
     qualifies
    -0.70
    POSITIVE LOGITS
    atre
    0.84
     Golden
    0.83
     largest
    0.80
     Dalai
    0.79
     "#
    0.79
     Handbook
    0.77
     Great
    0.77
     Butterfly
    0.77
     proverbial
    0.75
     Greatest
    0.75
    Act Density 0.111%

    No Known Activations