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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and prerequisites before undertaking an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _COMPILE
    -0.15
    anan
    -0.14
    nze
    -0.14
    ollo
    -0.14
    STANCE
    -0.14
    aki
    -0.14
    QN
    -0.13
    498
    -0.13
    ाà¤Ĺर
    -0.13
     Kramer
    -0.13
    POSITIVE LOGITS
    oled
    0.15
    æĪIJ人
    0.15
     Sesso
    0.15
    ModelProperty
    0.15
    urnal
    0.14
    egl
    0.14
    oden
    0.14
     initial
    0.14
     prelim
    0.14
    iffies
    0.13
    Act Density 0.172%

    No Known Activations