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

    Neuronpedia

    INDEX
    Explanations

    references to poetry and literary elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     اÙĦعظ
    -0.15
    reff
    -0.15
    微软éĽħé»ij
    -0.15
    heimer
    -0.15
    ëį°ìĿ´íĬ¸
    -0.15
    rozen
    -0.14
    ynes
    -0.14
    обов
    -0.14
    пион
    -0.14
    svp
    -0.14
    POSITIVE LOGITS
     /
    0.16
     cunt
    0.15
    絡
    0.14
     Plex
    0.14
     Dickinson
    0.14
     c
    0.14
    257
    0.13
     wd
    0.13
    etro
    0.13
     Mn
    0.13
    Act Density 0.287%

    No Known Activations