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

    Neuronpedia

    INDEX
    Explanations

    ratings and evaluations, specifically relating to stars or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubat
    -0.14
    ëłī
    -0.14
    ìĿ´ë²Ħ
    -0.13
    ļĮ
    -0.13
    arto
    -0.13
     DNS
    -0.12
    ç´Ķ
    -0.12
    ÑĢам
    -0.12
     dns
    -0.12
    ÏĦίοÏħ
    -0.12
    POSITIVE LOGITS
     star
    1.40
     stars
    1.28
     Star
    1.17
    -star
    1.16
    star
    1.16
     Stars
    1.12
    Star
    1.09
    æĺŁ
    1.07
    stars
    1.06
     STAR
    1.04
    Act Density 0.122%

    No Known Activations