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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    awaru
    -1.04
    uese
    -0.83
    racuse
    -0.82
    ktop
    -0.81
    igmatic
    -0.79
    erred
    -0.75
    rament
    -0.75
    ignt
    -0.75
    neau
    -0.74
    ugi
    -0.73
    POSITIVE LOGITS
     Manziel
    0.70
     escal
    0.68
     strangers
    0.67
     galaxies
    0.65
     wiser
    0.64
     Revenge
    0.63
     contingency
    0.61
     parks
    0.60
     scout
    0.60
     malt
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.