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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __*/
    -0.68
    Autoritní
    -0.62
    RegressionTest
    -0.54
    IsContent
    -0.52
    extendable
    -0.48
    Personendaten
    -0.47
    estors
    -0.47
     بيها
    -0.46
    guous
    -0.46
    WaitGroup
    -0.46
    POSITIVE LOGITS
     kasarigan
    0.49
    【
    0.39
    “(
    0.39
    ˹
    0.39
    رشف
    0.38
      (
    0.36
    //(
    0.36
    ][
    0.36
    bindingNavigator
    0.36
    ,(
    0.36
    Act Density 1.380%

    No Known Activations