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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    asar
    -0.75
    ussen
    -0.73
    TPS
    -0.71
    ottenham
    -0.70
     "$:/
    -0.68
    enegger
    -0.65
    Rating
    -0.64
     Oaks
    -0.64
    Flag
    -0.62
     [+
    -0.62
    POSITIVE LOGITS
    lav
    0.72
    hov
    0.67
    avior
    0.65
    eous
    0.61
    âĶĢâĶĢ
    0.60
     causation
    0.60
    lyak
    0.59
    Truth
    0.59
     earthly
    0.58
     therein
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.