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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "New" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bay
    -0.16
    (StringUtils
    -0.14
    ful
    -0.14
    ktion
    -0.14
    agnostic
    -0.13
    blick
    -0.13
    tant
    -0.13
    à¸ģระ
    -0.13
    /window
    -0.13
    زار
    -0.13
    POSITIVE LOGITS
    airo
    0.16
    rech
    0.14
    ubu
    0.14
    aison
    0.14
    úa
    0.14
    OA
    0.14
    osy
    0.14
     sie
    0.13
    ua
    0.13
    ymax
    0.13
    Act Density 0.061%

    No Known Activations