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

    Neuronpedia

    INDEX
    Explanations

    terms related to high and low values, specifically in a comparative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Creatures
    -0.77
     Trotter
    -0.74
     voyez
    -0.73
    creatures
    -0.72
     suivants
    -0.72
    UserAgent
    -0.71
     Schäfer
    -0.69
    kmäler
    -0.69
     redé
    -0.68
     ménages
    -0.68
    POSITIVE LOGITS
     High
    2.00
    High
    1.98
     high
    1.94
    high
    1.88
     HIGH
    1.82
    HIGH
    1.78
     Low
    1.46
    高
    1.45
    Low
    1.44
     LOW
    1.34
    Act Density 0.130%

    No Known Activations