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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uria
    -0.86
    ographers
    -0.79
    urus
    -0.78
    ober
    -0.76
    tein
    -0.74
     Leilan
    -0.72
    uterte
    -0.72
    pher
    -0.72
    dor
    -0.71
    umbnails
    -0.70
    POSITIVE LOGITS
     Conn
    0.75
     McCorm
    0.73
     Breitbart
    0.71
     Cub
    0.68
     Wr
    0.68
     Batt
    0.65
     Ru
    0.64
     Carr
    0.64
     FML
    0.63
     Sab
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.