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

    Neuronpedia

    INDEX
    Explanations

    references to the "Coco" dataset and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Coco, OCO, Koko, Cocom, Poco

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tchèque
    -0.46
    Andrzej
    -0.43
    Lawn
    -0.43
     gouver
    -0.43
    hetamine
    -0.41
     Chartres
    -0.41
     roulant
    -0.40
     évêque
    -0.39
     Pamplona
    -0.38
     Sénat
    -0.38
    POSITIVE LOGITS
     Coco
    2.22
    Coco
    2.13
    coco
    2.02
     coco
    2.02
     cocoon
    1.24
     COC
    1.23
     Koko
    1.11
    Koko
    1.05
    ココ
    1.01
    COC
    0.98
    Act Density 0.008%

    No Known Activations