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

    Neuronpedia

    INDEX
    Explanations

    variables and their assignments in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umber
    -0.20
    lan
    -0.16
     ìĭ¶
    -0.15
    lip
    -0.15
    lum
    -0.14
    lemen
    -0.14
    enos
    -0.14
    ERM
    -0.14
    ers
    -0.13
    allet
    -0.13
    POSITIVE LOGITS
    IRTUAL
    0.14
    -nil
    0.14
    ERTICAL
    0.14
    Wunused
    0.14
    asp
    0.14
    ÑģÑĮ
    0.14
    eated
    0.14
    $o
    0.14
    主義
    0.14
    idual
    0.13
    Act Density 0.092%

    No Known Activations