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

    Neuronpedia

    INDEX
    Explanations

    references to classifications and characteristics of groups or units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ward
    -0.37
    leps
    -0.35
     AMD
    -0.34
    AMD
    -0.34
    WARD
    -0.34
    weile
    -0.33
     /\.
    -0.32
     rack
    -0.32
     Ward
    -0.32
     Zy
    -0.31
    POSITIVE LOGITS
     ModelExpression
    0.56
     informée
    0.54
     continúas
    0.52
    RTLU
    0.50
     AspNetCore
    0.50
    Personendaten
    0.47
     متعلقه
    0.47
    iNdEx
    0.45
    AccessorTable
    0.45
    脚注の使い方
    0.44
    Act Density 0.100%

    No Known Activations