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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riz
    -0.15
    hips
    -0.15
    ha
    -0.15
    kin
    -0.14
    059
    -0.14
     \↵
    -0.13
    ÎŃν
    -0.13
     caution
    -0.13
    issen
    -0.13
     Stamp
    -0.13
    POSITIVE LOGITS
    byname
    0.19
    Leap
    0.17
    ió
    0.16
    оÑĤÑĮ
    0.16
     Leap
    0.15
    illez
    0.14
    itemap
    0.14
    lesia
    0.14
    umbn
    0.14
    cpt
    0.14
    Act Density 0.383%

    No Known Activations