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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially those that indicate a pause or continuation in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idge
    -0.17
    otts
    -0.14
     Copp
    -0.14
    thetic
    -0.13
    ика
    -0.13
    ground
    -0.13
    _GATE
    -0.13
    pole
    -0.13
    Rectangle
    -0.13
     buds
    -0.13
    POSITIVE LOGITS
    _intr
    0.17
    OPY
    0.16
    indre
    0.14
    vise
    0.14
    د
    0.14
     UIF
    0.13
    unde
    0.13
    rians
    0.13
    ìĤ´
    0.13
    adal
    0.13
    Act Density 0.009%

    No Known Activations