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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating extremes or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccione
    -0.19
    ogan
    -0.17
    άν
    -0.16
    ido
    -0.15
    Ìģt
    -0.14
    रण
    -0.14
    tti
    -0.14
    oky
    -0.14
    جاد
    -0.14
    ÑĤÑİ
    -0.14
    POSITIVE LOGITS
    acades
    0.15
     hdr
    0.15
    atta
    0.15
    é¼ĵ
    0.14
    abad
    0.14
    owan
    0.14
     дела
    0.13
    ноÑģи
    0.13
     eject
    0.13
    uilder
    0.13
    Act Density 0.020%

    No Known Activations