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

    Neuronpedia

    INDEX
    Explanations

    references to specific file paths or resource URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uars
    -0.15
    å¾
    -0.14
    itele
    -0.14
    beros
    -0.14
    à¥įतव
    -0.14
    HEET
    -0.14
    vrd
    -0.14
     bypass
    -0.14
    æľĭ
    -0.14
    cts
    -0.13
    POSITIVE LOGITS
    AGER
    0.16
    åı¥è¯Ŀ
    0.16
     wp
    0.14
    unday
    0.14
    ies
    0.14
     Rosenberg
    0.14
     Davies
    0.13
    Ill
    0.13
    wil
    0.13
    atha
    0.13
    Act Density 0.011%

    No Known Activations