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

    Neuronpedia

    INDEX
    Explanations

    instances of data structures, justifying conditions, and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥģãĥ¥
    -0.16
    ANTE
    -0.15
    ante
    -0.15
     play
    -0.15
    νÏĦ
    -0.14
    ãĤ
    -0.14
    ãĥįãĥĥãĥĪ
    -0.14
    uent
    -0.14
     Blond
    -0.14
    é½
    -0.13
    POSITIVE LOGITS
    ackbar
    0.16
    ptrdiff
    0.16
    abo
    0.15
    abbo
    0.15
    vetica
    0.15
    idental
    0.14
    stants
    0.14
     FactoryBot
    0.14
    ushman
    0.14
     Kirk
    0.13
    Act Density 0.020%

    No Known Activations