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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atty
    -0.15
    at
    -0.15
     curs
    -0.15
    metis
    -0.15
     asympt
    -0.14
     feeds
    -0.14
     suites
    -0.14
    ariat
    -0.14
     Sacred
    -0.14
     nearby
    -0.14
    POSITIVE LOGITS
    restriction
    0.19
     restriction
    0.17
    Ware
    0.16
    ÙĪغ
    0.16
    Dual
    0.16
    ASET
    0.15
     corresponding
    0.15
    lef
    0.15
    /Gate
    0.15
    Restr
    0.15
    Act Density 0.207%

    No Known Activations