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

    Neuronpedia

    INDEX
    Explanations

    characters or sequences in text that indicate non-standard encoding or formatting issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëĶĶìĭľ
    -0.17
    yled
    -0.15
    tutorial
    -0.15
    ystack
    -0.14
    kili
    -0.14
    ighth
    -0.14
     Korea
    -0.14
    idla
    -0.14
    ivot
    -0.14
    ÑĤом
    -0.14
    POSITIVE LOGITS
    aku
    0.23
    iken
    0.20
    ei
    0.19
    oku
    0.18
     Nich
    0.18
    anse
    0.17
     Sans
    0.17
    ets
    0.17
     gou
    0.17
    sets
    0.17
    Act Density 0.049%

    No Known Activations