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

    Neuronpedia

    INDEX
    Explanations

    references to legal violations or criminal acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uggy
    -0.16
    uckle
    -0.16
    --
    -0.16
    achel
    -0.15
    (--
    -0.14
    ela
    -0.14
     analog
    -0.14
    ÑģÑĮко
    -0.14
    Extern
    -0.14
     favor
    -0.13
    POSITIVE LOGITS
     âĢł
    0.18
     handjob
    0.16
    947
    0.15
    iams
    0.14
     **)
    0.14
    oho
    0.14
    RK
    0.14
    engu
    0.14
     -:
    0.14
     ,↵
    0.14
    Act Density 0.055%

    No Known Activations