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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     checkpoint
    -0.71
     Lauderdale
    -0.67
     checkpoints
    -0.63
     crossings
    -0.63
     swings
    -0.62
     cones
    -0.62
     finite
    -0.61
     temporary
    -0.61
     stressed
    -0.60
     visitor
    -0.59
    POSITIVE LOGITS
    ateurs
    0.80
    ionage
    0.80
    tackle
    0.72
    ateur
    0.71
    agra
    0.70
    Anth
    0.68
    inea
    0.66
    ois
    0.65
    adem
    0.65
    udeb
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.