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

    Neuronpedia

    INDEX
    Explanations

    references to bonuses or rewards in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppard
    -0.16
    à¥ĭध
    -0.15
    iska
    -0.15
     èĸ
    -0.14
    ãģĵãĤį
    -0.14
    æ¯ĶèµĽ
    -0.13
    loo
    -0.13
    awah
    -0.13
    tek
    -0.13
    lements
    -0.13
    POSITIVE LOGITS
    (es
    0.19
    aries
    0.18
    ssp
    0.17
    ware
    0.17
    /free
    0.16
    zers
    0.16
    ylvania
    0.16
    ãĤ¤ãĤº
    0.16
    readcr
    0.16
    Ç
    0.15
    Act Density 0.011%

    No Known Activations