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

    Neuronpedia

    INDEX
    Explanations

    instances of enjoyment or amusement in the context of politics or societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elerik
    -0.16
    igth
    -0.15
    quares
    -0.15
    glomer
    -0.14
    481
    -0.14
    uluk
    -0.13
    ãģıãĤī
    -0.13
    âĢĥ
    -0.13
    оÑĢож
    -0.13
    ¼åIJĪ
    -0.13
    POSITIVE LOGITS
    dex
    0.16
    azio
    0.16
    ocr
    0.14
    atra
    0.14
    ento
    0.14
    strap
    0.14
     Appe
    0.14
    asin
    0.14
    è¨
    0.14
    oola
    0.14
    Act Density 0.456%

    No Known Activations