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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     monotonically
    0.94
     thumbnails
    0.89
     substrings
    0.83
     delimiters
    0.82
     checkboxes
    0.79
     amplitudes
    0.78
     stylesheets
    0.78
     coefficients
    0.78
     emojis
    0.77
     spurious
    0.77
    POSITIVE LOGITS
    IT
    0.80
    Encycl
    0.79
    林
    0.78
    rewsbury
    0.75
    St
    0.73
    IA
    0.73
    Storia
    0.73
    MA
    0.73
    ETH
    0.73
    Se
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.