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

    Neuronpedia

    INDEX
    Explanations

    references to high quality or high standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Trotter
    -0.71
    UserAgent
    -0.69
    adaptiveStyles
    -0.68
     Creatures
    -0.67
    зец
    -0.67
     redé
    -0.67
     trấn
    -0.66
     Schäfer
    -0.66
     entière
    -0.66
     ménages
    -0.66
    POSITIVE LOGITS
     High
    1.59
     high
    1.53
    High
    1.52
     HIGH
    1.50
    HIGH
    1.44
    high
    1.43
     Low
    1.23
    Low
    1.18
    高
    1.14
     LOW
    1.13
    Act Density 0.163%

    No Known Activations