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

    Neuronpedia

    INDEX
    Explanations

    instances of quoted dialogue or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONUS
    -0.15
     Flesh
    -0.15
    uliar
    -0.15
    عا
    -0.15
    WM
    -0.14
    èŃ
    -0.14
    setLayout
    -0.14
     cruise
    -0.14
    ë°Ģ
    -0.14
    itar
    -0.14
    POSITIVE LOGITS
    ázev
    0.15
    corn
    0.15
    udd
    0.14
    orris
    0.14
    irl
    0.14
    AO
    0.14
    noch
    0.14
    nap
    0.14
    Ìĥ
    0.14
    osen
    0.14
    Act Density 0.020%

    No Known Activations