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

    Neuronpedia

    INDEX
    Explanations

    emphatic phrases and expressions of positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    horn
    -0.15
    rych
    -0.14
    _BP
    -0.14
    ufs
    -0.14
    ayette
    -0.14
    미
    -0.14
    alsex
    -0.13
     ÐŁÐ¾Ñĩ
    -0.13
    'gc
    -0.13
    _GU
    -0.13
    POSITIVE LOGITS
    maz
    0.16
    onis
    0.15
    pty
    0.14
    twig
    0.14
    -called
    0.14
     Schro
    0.14
    923
    0.14
    444
    0.14
     Trou
    0.13
     troub
    0.13
    Act Density 0.080%

    No Known Activations