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

    Neuronpedia

    INDEX
    Explanations

    instances of repetition and emphasis in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </em>
    -0.50
     F
    -0.42
    гну
    -0.42
    дра
    -0.40
    جب
    -0.40
     J
    -0.39
    cis
    -0.39
    F
    -0.38
    ull
    -0.37
     O
    -0.37
    POSITIVE LOGITS
    StructEnd
    1.34
    GEBURTSDATUM
    1.34
    Geplaatst
    1.13
    aarrggbb
    1.10
     تضيفلها
    1.10
    ThroughAttribute
    1.10
    ViewFeatures
    1.09
    parsedMessage
    1.06
     Савезне
    1.06
    ArrowToggle
    1.05
    Act Density 0.295%

    No Known Activations