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

    Neuronpedia

    INDEX
    Explanations

    technical jargon or keywords in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anela
    -0.17
    igure
    -0.17
    æŃ
    -0.16
    754
    -0.15
    utzer
    -0.15
    ÅĻiv
    -0.14
    710
    -0.14
    enuity
    -0.14
     Dress
    -0.14
    alars
    -0.14
    POSITIVE LOGITS
    tery
    0.16
    igan
    0.15
     tast
    0.14
    dac
    0.14
    .Foundation
    0.14
    ^K
    0.14
     Jed
    0.14
    \\.
    0.14
    ton
    0.14
    nard
    0.14
    Act Density 0.021%

    No Known Activations