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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Rudd
    -0.78
     Revel
    -0.75
     Proposition
    -0.73
    uggest
    -0.72
     Twist
    -0.71
     Cardinal
    -0.69
     Answers
    -0.68
     Abbott
    -0.66
     Nightmares
    -0.66
     Warn
    -0.64
    POSITIVE LOGITS
    arers
    0.71
    oton
    0.70
     corps
    0.69
    asant
    0.67
     acad
    0.64
    aves
    0.62
     sidelines
    0.62
     shore
    0.61
    present
    0.61
    ×Ļ×
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.