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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating requests or specific actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ«
    -0.15
    _AUX
    -0.15
    andle
    -0.15
    OSE
    -0.15
     gode
    -0.15
    amilies
    -0.14
    \OptionsResolver
    -0.14
    :num
    -0.14
     Exhaust
    -0.14
    oggle
    -0.13
    POSITIVE LOGITS
    mür
    0.16
    NSNotification
    0.16
    elik
    0.15
    ayah
    0.15
    ÃŃses
    0.15
    ÏĢοÏį
    0.15
    anus
    0.15
    soever
    0.14
    phant
    0.14
    ckt
    0.14
    Act Density 0.002%

    No Known Activations