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

    Neuronpedia

    INDEX
    Explanations

    mentions of knowledge or expertise

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge and understanding in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odder
    -0.72
    itter
    -0.68
    sty
    -0.64
    emale
    -0.62
     Pengu
    -0.61
    odd
    -0.61
     Temper
    -0.59
    issions
    -0.58
    dule
    -0.57
    raine
    -0.56
    POSITIVE LOGITS
    ledge
    1.09
     glean
    0.99
     gained
    0.97
    lege
    0.93
     about
    0.93
    fulness
    0.91
    base
    0.90
     comprehension
    0.84
     pertaining
    0.84
     base
    0.82
    Act Density 0.060%

    No Known Activations