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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Byrne
    -0.75
    IZ
    -0.66
     rall
    -0.64
     Modes
    -0.63
     Spielberg
    -0.61
     Trave
    -0.60
    inse
    -0.59
     COUR
    -0.59
     undecided
    -0.57
     independ
    -0.57
    POSITIVE LOGITS
    arer
    0.76
    SourceFile
    0.76
    DonaldTrump
    0.73
    resents
    0.72
    ifer
    0.72
    hus
    0.71
    Enlarge
    0.69
    cause
    0.68
    âĵĺ
    0.66
    arers
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.