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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    circle
    -0.76
    ariat
    -0.73
    ibli
    -0.71
    ghazi
    -0.67
    sch
    -0.67
    cle
    -0.65
    arian
    -0.64
    hen
    -0.64
    cience
    -0.64
    rave
    -0.64
    POSITIVE LOGITS
     challeng
    0.72
     tremend
    0.68
    yss
    0.66
    etting
    0.65
     culminating
    0.64
     jaws
    0.63
     Inferno
    0.63
     downhill
    0.61
     tremendous
    0.61
     GOODMAN
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.