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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    xon
    -0.72
     Luffy
    -0.69
    artney
    -0.67
     Philippines
    -0.67
    oller
    -0.66
     lineback
    -0.65
     Brune
    -0.65
     Capcom
    -0.64
    uese
    -0.64
     shenan
    -0.64
    POSITIVE LOGITS
    WER
    0.71
    aroo
    0.68
    edge
    0.67
    abol
    0.66
     gloomy
    0.65
    hist
    0.65
    è¦ļéĨĴ
    0.65
     Holocaust
    0.65
    committee
    0.64
     PID
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.