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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gow
    -0.68
    stage
    -0.68
    cffffcc
    -0.66
    ĸļ
    -0.65
     theaters
    -0.62
    zag
    -0.59
    arse
    -0.59
    opa
    -0.58
    CAST
    -0.58
    hof
    -0.58
    POSITIVE LOGITS
    encers
    0.80
    aders
    0.77
    encer
    0.68
    Fed
    0.65
     Hus
    0.64
    anship
    0.62
    à¥
    0.62
    hra
    0.61
     Fields
    0.60
    atcher
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.