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

    Neuronpedia

    INDEX
    Explanations

    mentions of errors or problems

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    BOOK
    -1.11
     psychiat
    -1.07
    BLE
    -1.06
     pupils
    -1.00
    hands
    -1.00
    è¯
    -1.00
    åĭ
    -0.98
    âĸº
    -0.97
    poke
    -0.97
    MEN
    -0.94
    POSITIVE LOGITS
    omaly
    1.77
    alogue
    1.69
    onym
    1.65
    alyses
    1.65
    esthetic
    1.64
    terior
    1.59
    alys
    1.54
    notation
    1.53
    omal
    1.48
    ubis
    1.47
    Act Density 0.922%

    No Known Activations