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

    Neuronpedia

    INDEX
    Explanations

    common phrases and structures in written content, indicating emphasis on specific details or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.52
    Демографія
    -0.47
    cheinend
    -0.47
    Доброго
    -0.46
    graphique
    -0.45
    まで
    -0.45
    ofern
    -0.45
     associée
    -0.44
     distanciation
    -0.44
    Explicación
    -0.44
    POSITIVE LOGITS
     including
    0.82
    avyzd
    0.73
    たとえば
    0.72
     utafitiHapana
    0.67
    including
    0.67
    包括
    0.66
     namely
    0.66
    比如说
    0.65
    include
    0.64
     Examples
    0.64
    Act Density 0.162%

    No Known Activations