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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.95
    ViewImports
    -0.91
    RegressionTest
    -0.85
    PreferredItem
    -0.77
    msgTypes
    -0.76
    InjectAttribute
    -0.75
    ftagPool
    -0.74
     ProtoMessage
    -0.74
    Rüyada
    -0.73
    featureID
    -0.71
    POSITIVE LOGITS
     US
    0.72
     World
    0.64
     Federal
    0.63
    HAUS
    0.60
     American
    0.56
     federal
    0.54
     print
    0.53
     states
    0.52
     States
    0.51
     USA
    0.51
    Act Density 0.213%

    No Known Activations