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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to exceptions, shortages, and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.78
    weeney
    -0.70
    igslist
    -0.62
     wizard
    -0.62
     Moder
    -0.59
     Restoration
    -0.59
     Methodist
    -0.59
    inka
    -0.59
    ixon
    -0.58
    ø
    -0.58
    POSITIVE LOGITS
     whatsoever
    1.04
    tips
    0.77
    aunts
    0.70
    milo
    0.66
    jer
    0.63
    opers
    0.62
    HE
    0.61
    stroke
    0.61
    astic
    0.60
    properties
    0.59
    Act Density 0.065%

    No Known Activations