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

    Neuronpedia

    INDEX
    Explanations

    statements of attribution or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.14
     Phát
    -0.14
     Cyr
    -0.14
     Mild
    -0.14
     Trem
    -0.14
    ãĥ¼ãĥĩ
    -0.13
    ÅĻad
    -0.13
    ÏĢιÏĥ
    -0.13
    ÄĽÅĻ
    -0.13
    ild
    -0.13
    POSITIVE LOGITS
    esa
    0.15
    endale
    0.15
    VL
    0.14
    ãģ£ãģ¨
    0.14
    ensus
    0.14
    note
    0.14
    ยว
    0.14
    endum
    0.14
    iect
    0.14
    chia
    0.13
    Act Density 0.017%

    No Known Activations