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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or conditions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trick
    -0.16
     Ric
    -0.15
    -
    -0.15
    -0.15
     Ritual
    -0.14
    mos
    -0.14
    et
    -0.14
    è¾ij
    -0.14
    ,
    -0.13
    ocker
    -0.13
    POSITIVE LOGITS
    ODO
    0.17
    \CMS
    0.16
    /sites
    0.14
    esson
    0.14
    imu
    0.14
    resher
    0.14
    ToPoint
    0.14
    ToUpper
    0.14
    ANGO
    0.14
    ongyang
    0.14
    Act Density 0.087%

    No Known Activations