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

    Neuronpedia

    INDEX
    Explanations

    numbers mentioned within textual content

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or extensive amounts of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.66
    allery
    -0.66
    bernatorial
    -0.63
     Slightly
    -0.63
     Moder
    -0.63
     Identified
    -0.63
    escription
    -0.62
    issan
    -0.62
    retty
    -0.60
    PN
    -0.59
    POSITIVE LOGITS
     crammed
    1.17
     vying
    1.09
     endlessly
    1.09
     countless
    1.08
     piled
    1.04
     annually
    1.03
     imaginable
    1.01
     every
    1.00
     untold
    0.99
     simultaneously
    0.99
    Act Density 0.658%

    No Known Activations