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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with scores, statistics, or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.88
    spread
    -0.68
    ilater
    -0.67
    essen
    -0.62
    izzle
    -0.61
     [/
    -0.60
    ...?
    -0.60
     calcul
    -0.57
    plin
    -0.57
     manifold
    -0.57
    POSITIVE LOGITS
    +)
    1.33
    %)
    1.23
    )/
    1.22
    )
    1.22
    )—
    1.19
    ),"
    1.15
    %),
    1.12
    )--
    1.11
    )=
    1.10
    )"
    1.07
    Act Density 0.114%

    No Known Activations