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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that indicate quotes or significant dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /or
    -0.18
    adiens
    -0.14
    ãģįãģŁ
    -0.14
    STR
    -0.13
    etine
    -0.13
    /install
    -0.13
     kiá»ĩn
    -0.13
    ãĥ¼ãĤ¹
    -0.12
    eselect
    -0.12
    -caret
    -0.12
    POSITIVE LOGITS
    ÂĿ
    0.25
    s
    0.22
    ed
    0.20
    ÛĮ
    0.17
    an
    0.17
    i
    0.17
    nbsp
    0.17
    447
    0.15
    tractive
    0.15
    gnore
    0.15
    Act Density 0.232%

    No Known Activations