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

    Neuronpedia

    INDEX
    Explanations

    a hierarchy or classification of quality within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erne
    -0.16
    tml
    -0.16
    erence
    -0.15
    ept
    -0.15
    specialchars
    -0.15
    ean
    -0.15
    ambio
    -0.14
    sian
    -0.14
    ansen
    -0.14
    /topics
    -0.14
    POSITIVE LOGITS
    -notch
    0.44
    pling
    0.41
     notch
    0.38
    ographical
    0.37
    ography
    0.35
    -tier
    0.35
    most
    0.34
    -flight
    0.34
    ographic
    0.33
    flight
    0.33
    Act Density 0.052%

    No Known Activations