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

    Neuronpedia

    INDEX
    Explanations

    patterns of speech or expressions that indicate caution or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTS
    -0.18
    ypi
    -0.15
    loit
    -0.15
    ylim
    -0.14
    avez
    -0.14
    OTA
    -0.14
    ei
    -0.14
    czy
    -0.14
    Ven
    -0.14
    gems
    -0.14
    POSITIVE LOGITS
    hol
    0.15
     regist
    0.15
    cona
    0.14
    regist
    0.14
    eros
    0.14
     Kok
    0.14
    /rss
    0.14
    à¥ĩà¤ľ
    0.14
     Hoch
    0.13
    holm
    0.13
    Act Density 0.006%

    No Known Activations