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

    Neuronpedia

    INDEX
    Explanations

    quantitative information related to performance and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Foley
    -0.15
     Property
    -0.15
     Caul
    -0.14
    nio
    -0.14
    нен
    -0.14
     F
    -0.14
     indef
    -0.14
     Ful
    -0.14
    ắm
    -0.13
     Rae
    -0.13
    POSITIVE LOGITS
     points
    0.27
    Points
    0.22
    (points
    0.21
    points
    0.21
    POINTS
    0.20
     Points
    0.20
    _points
    0.20
    -points
    0.19
    oints
    0.18
    .points
    0.18
    Act Density 0.053%

    No Known Activations