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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogo
    -0.15
    ysz
    -0.15
    ouver
    -0.15
    abus
    -0.15
    ponder
    -0.14
    OutOfBounds
    -0.14
    _Exception
    -0.14
    uish
    -0.14
    inder
    -0.14
    ugin
    -0.13
    POSITIVE LOGITS
     omas
    0.18
     yiy
    0.15
    úi
    0.15
    emens
    0.15
    illard
    0.14
    ahy
    0.14
    ellation
    0.14
     omin
    0.14
    unes
    0.14
    ÙĪÙĤع
    0.14
    Act Density 0.092%

    No Known Activations