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

    Neuronpedia

    INDEX
    Explanations

    phrases that express exceptions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.72
    UnusedPrivate
    -0.71
     Baillargeon
    -0.71
     kasarigan
    -0.71
     estimés
    -0.69
    $_['
    -0.63
    таратура
    -0.63
    رشف
    -0.63
    IUrlHelper
    -0.62
     invokingState
    -0.62
    POSITIVE LOGITS
     exhaustive
    0.92
    exhaus
    0.77
     exclusive
    0.73
     exhaus
    0.69
    exclusive
    0.68
     EXCLUSIVE
    0.67
    Exclusive
    0.65
     inclusive
    0.65
     exklu
    0.64
     Exclusive
    0.62
    Act Density 0.281%

    No Known Activations