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

    Neuronpedia

    INDEX
    Explanations

    references to organizational divisions or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    454
    -0.15
    ienne
    -0.14
     Vaults
    -0.14
    наÑĤ
    -0.14
    ints
    -0.14
    ocha
    -0.13
    лÑĮ
    -0.13
     ########.
    -0.13
    icie
    -0.13
    Ñīин
    -0.13
    POSITIVE LOGITS
    alone
    0.16
    branch
    0.15
    illis
    0.15
    ù
    0.15
    /sub
    0.15
     branches
    0.14
    (branch
    0.14
    wizard
    0.14
    iles
    0.14
    bos
    0.14
    Act Density 0.042%

    No Known Activations