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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey expectations, desires, or conditions regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    borg
    -0.17
    ãĤ¯ãĥĪ
    -0.16
    á»ĩn
    -0.15
     ----------------------------------------------------------------------------↵
    -0.14
    yms
    -0.14
     ì¡
    -0.14
    dued
    -0.14
    她çļĦ
    -0.14
    rive
    -0.13
     ÑŁ
    -0.13
    POSITIVE LOGITS
     to
    0.23
     να
    0.17
     us
    0.16
     you
    0.16
    ÙĪÙĨا
    0.14
    443
    0.14
     someone
    0.14
    ìĥģìĿĦ
    0.14
    warts
    0.14
    shed
    0.14
    Act Density 0.167%

    No Known Activations