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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ĥİ
    -0.80
    tle
    -0.67
    thur
    -0.66
     Doodle
    -0.65
    llan
    -0.65
     mechan
    -0.63
    âĸł
    -0.63
     Ago
    -0.63
    ãĢı
    -0.61
    Attempt
    -0.61
    POSITIVE LOGITS
    yna
    0.82
    rous
    0.74
    ippi
    0.71
    erg
    0.69
    eware
    0.69
    Ô
    0.67
     fingerprints
    0.66
    iat
    0.65
    auri
    0.65
    OTOS
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.