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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific formatting elements in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     sexuales
    -0.51
    esa
    -0.51
     fall
    -0.48
     presença
    -0.47
    tran
    -0.44
     cuire
    -0.44
    waran
    -0.43
     acque
    -0.43
    ↵↵
    -0.42
     voulons
    -0.42
    POSITIVE LOGITS
     Orrell
    0.86
    IsMutable
    0.83
    HideFlags
    0.82
     ModelExpression
    0.82
    mergeFrom
    0.79
     चीज़ों
    0.79
     bezeichneter
    0.75
     raiſ
    0.74
     cdti
    0.72
    EndGlobalSection
    0.71
    Act Density 0.001%

    No Known Activations