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

    Neuronpedia

    INDEX
    Explanations

    instances where imperfections are highlighted or acknowledged

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and discussions of perfection or ideality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wash
    -0.62
    querade
    -0.59
     li
    -0.59
    appa
    -0.58
     Quote
    -0.57
     WARN
    -0.56
     @@
    -0.56
     WATCH
    -0.55
     brace
    -0.54
    757
    -0.54
    POSITIVE LOGITS
     anymore
    1.29
     nor
    1.12
     specifics
    0.82
     yet
    0.75
    necess
    0.70
     necessarily
    0.66
    teness
    0.65
    yet
    0.64
    specific
    0.63
     Obj
    0.62
    Act Density 0.474%

    No Known Activations