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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    grave
    -0.86
    ursed
    -0.80
    alien
    -0.76
    lled
    -0.73
    lements
    -0.71
    capital
    -0.70
    sterdam
    -0.69
    eligible
    -0.69
    uffer
    -0.67
    lling
    -0.67
    POSITIVE LOGITS
     )))
    0.64
    Discuss
    0.64
    Enlarge
    0.62
     Views
    0.61
     Poc
    0.61
     skew
    0.61
    Reviewer
    0.61
     diam
    0.61
    Measure
    0.60
     Flavoring
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.