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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĢĤæľ¬
    -0.17
    ’
    -0.16
     escape
    -0.15
     hum
    -0.15
    -↵
    -0.14
     ar
    -0.14
    urg
    -0.14
    emin
    -0.14
     re
    -0.13
     :-↵
    -0.13
    POSITIVE LOGITS
     endregion
    0.18
    ashi
    0.17
     onCancelled
    0.17
    ìĭľìĺ¤
    0.15
    infeld
    0.15
    еи
    0.14
    .synthetic
    0.14
    StackNavigator
    0.14
    jie
    0.14
    ughs
    0.14
    Act Density 0.202%

    No Known Activations