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

    Neuronpedia

    INDEX
    Explanations

    quantitative phrases related to limits and thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     getItemId
    -0.58
    getDefault
    -0.46
     sqlalchemy
    -0.45
     niyang
    -0.45
    AXB
    -0.45
     Deum
    -0.44
    coltà
    -0.41
    parsedMessage
    -0.41
    esgue
    -0.41
    WSGI
    -0.40
    POSITIVE LOGITS
     too
    2.38
     Too
    2.20
    Too
    2.18
    too
    2.14
     TOO
    2.06
    TOO
    1.80
     terlalu
    1.65
     demasiado
    1.63
     demasi
    1.63
     слишком
    1.62
    Act Density 0.347%

    No Known Activations