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

    Neuronpedia

    INDEX
    Explanations

    references to scientific models and theories in physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etti
    -0.15
    Ñĵ
    -0.15
    iffin
    -0.15
    _ORIENTATION
    -0.14
    ips
    -0.14
    _OM
    -0.13
    aft
    -0.13
    133
    -0.13
    .Dial
    -0.13
    FullYear
    -0.13
    POSITIVE LOGITS
    arios
    0.16
    اÙĪÙĬ
    0.14
     Cornel
    0.14
    ln
    0.14
    iyan
    0.14
     barn
    0.14
    æ¡Ĩ
    0.13
    town
    0.13
    THREAD
    0.13
    ISTR
    0.13
    Act Density 0.001%

    No Known Activations