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

    Neuronpedia

    INDEX
    Explanations

    statements or questions that indicate disbelief or a challenge to the norm.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³
    -0.16
    ppard
    -0.15
    anlar
    -0.15
    assis
    -0.15
    atcher
    -0.14
    apons
    -0.14
    .tests
    -0.14
    ازÙĩ
    -0.14
    .rc
    -0.14
    onds
    -0.14
    POSITIVE LOGITS
    jest
    0.15
    ibri
    0.15
    oleÄį
    0.15
    mana
    0.14
    FromBody
    0.14
    utas
    0.14
     verm
    0.14
    :UIAlert
    0.13
    .ease
    0.13
    eb
    0.13
    Act Density 0.000%

    No Known Activations