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

    Neuronpedia

    INDEX
    Explanations

    references to pages in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agra
    -0.16
    el
    -0.16
     ============================================================================↵
    -0.15
    enburg
    -0.15
     -----------------------------------------------------------------------------↵
    -0.15
    ods
    -0.15
    i
    -0.14
    Ùİج
    -0.14
    ãĥ¼ãĤ¸
    -0.14
    awn
    -0.14
    POSITIVE LOGITS
     povol
    0.15
    rens
    0.15
    flix
    0.14
    ADOR
    0.14
    ÑĢаÑĩ
    0.14
    indre
    0.14
    LEC
    0.14
    fila
    0.14
    _inches
    0.13
    çIJ´
    0.13
    Act Density 0.020%

    No Known Activations