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

    Neuronpedia

    INDEX
    Explanations

    specific noun forms that are common in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylie
    -0.15
    essim
    -0.14
     اÙĦÙħØ´
    -0.14
     Mob
    -0.14
    eldo
    -0.14
    _CHILD
    -0.14
    -tab
    -0.13
    ding
    -0.13
    phasis
    -0.13
    colo
    -0.13
    POSITIVE LOGITS
    anooga
    0.19
    zcze
    0.16
    lotte
    0.15
    acter
    0.15
    ographed
    0.15
    lain
    0.14
    ä¹İ
    0.14
    utting
    0.14
    kowski
    0.14
    lek
    0.14
    Act Density 0.064%

    No Known Activations