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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Livingston
    -0.74
     Sheffield
    -0.73
     Fighting
    -0.73
     Crowd
    -0.69
     DNC
    -0.67
     McLaren
    -0.67
     Keith
    -0.66
     Scotland
    -0.66
     Walters
    -0.65
     Enhancement
    -0.65
    POSITIVE LOGITS
    ategory
    0.85
    daq
    0.80
    zx
    0.78
    ihar
    0.75
    itionally
    0.74
    fect
    0.74
    ALT
    0.73
    hem
    0.73
    versely
    0.72
    orns
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.