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

    Neuronpedia

    INDEX
    Explanations

    short phrases indicating lists or collections

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating examples or listings of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosity
    -0.77
     Ended
    -0.72
    ĸļ
    -0.72
    aith
    -0.70
    livion
    -0.70
    akery
    -0.69
    atform
    -0.69
    ylum
    -0.67
    ocaust
    -0.67
    hes
    -0.66
    POSITIVE LOGITS
     examples
    1.09
     highlights
    1.09
     testim
    0.99
     excerpts
    0.93
     illust
    0.91
     excerpt
    0.89
     notable
    0.86
     pointers
    0.85
     noteworthy
    0.83
     handy
    0.82
    Act Density 0.134%

    No Known Activations