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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     streng
    -0.69
     fullest
    -0.67
    cation
    -0.64
    wide
    -0.63
     exha
    -0.63
    average
    -0.62
     explor
    -0.61
     adjourn
    -0.60
    baugh
    -0.60
    nation
    -0.60
    POSITIVE LOGITS
     Cosponsors
    0.85
    anamo
    0.72
     Radar
    0.71
    ocry
    0.70
    estern
    0.68
    osate
    0.68
     Lump
    0.67
    oway
    0.66
    eed
    0.66
    angering
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.