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

    Neuronpedia

    INDEX
    Explanations

    measurements, calculations, and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.40
    rrggbb
    -0.36
    LookAnd
    -0.34
     ovunque
    -0.33
    lop
    -0.31
    GeoNames
    -0.31
     partout
    -0.31
    ]]:
    -0.30
    endpush
    -0.29
     geográfica
    -0.29
    POSITIVE LOGITS
    homonymie
    0.68
    Tembelea
    0.57
    WriteTagHelper
    0.54
    Geplaatst
    0.52
    didSet
    0.51
    adpleegd
    0.50
    Хьажоргаш
    0.49
    repres
    0.49
    ギュア
    0.48
    #+#
    0.48
    Act Density 0.535%

    No Known Activations