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

    Neuronpedia

    INDEX
    Explanations

    titles of academic publications

    oai_token-act-pair · gpt-3.5-turbo

    references to academic publications and scholarly works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hod
    -0.84
    icably
    -0.76
    azor
    -0.73
    aye
    -0.73
    atsuki
    -0.71
    adra
    -0.69
    oooooooo
    -0.69
    OOOO
    -0.68
    ¬¼
    -0.68
    intent
    -0.66
    POSITIVE LOGITS
     reprinted
    1.09
     Princeton
    0.97
     Handbook
    0.97
     published
    0.96
     Perspect
    0.95
     Retrieved
    0.94
     Proceedings
    0.93
     edited
    0.93
     Volume
    0.92
     Edited
    0.92
    Act Density 0.355%

    No Known Activations