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

    Neuronpedia

    INDEX
    Explanations

    words related to famous individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    é¾
    -0.78
    -+-+
    -0.70
    irie
    -0.66
    inctions
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
    eele
    -0.65
     Expend
    -0.65
    ioxide
    -0.65
     Ll
    -0.64
    ħĭ
    -0.63
    POSITIVE LOGITS
    igan
    0.75
    inki
    0.71
    warts
    0.70
    igans
    0.69
    wed
    0.66
    wig
    0.65
    behind
    0.64
    sein
    0.63
    gow
    0.61
    idan
    0.61
    Act Density 7.600%

    No Known Activations