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

    Neuronpedia

    INDEX
    Explanations

    phrases and statements emphasizing superlatives or extremes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     paperwork
    -0.52
     papier
    -0.50
    hloromethane
    -0.49
     cords
    -0.47
     kerja
    -0.46
    OfWork
    -0.45
    CharCode
    -0.45
     CrossRef
    -0.45
     bales
    -0.44
     CURIAM
    -0.44
    POSITIVE LOGITS
     most
    1.00
    Most
    1.00
     Most
    0.98
     MOST
    0.95
    most
    0.95
    MOST
    0.90
     meest
    0.73
     moft
    0.71
    最
    0.71
     mest
    0.66
    Act Density 0.159%

    No Known Activations