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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    chan
    -0.73
    igsaw
    -0.71
    KER
    -0.71
    hover
    -0.70
    raper
    -0.68
    ="#
    -0.67
    Pic
    -0.66
    ired
    -0.66
    Canadian
    -0.66
    armor
    -0.65
    POSITIVE LOGITS
     tremend
    0.88
     sinners
    0.73
     strat
    0.70
     relegation
    0.69
     tumult
    0.68
    awei
    0.68
     EPS
    0.66
     conduc
    0.65
     tempt
    0.64
    Ĥª
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.