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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     an
    0.57
     exceeds
    0.46
     foods
    0.46
     to
    0.46
     allows
    0.45
     ovarian
    0.44
     delicacies
    0.43
     maximale
    0.43
     einem
    0.43
     can
    0.42
    POSITIVE LOGITS
    otherArchive
    0.45
    诌
    0.43
     premiership
    0.43
    pyx
    0.42
    ponden
    0.42
    stan
    0.41
    English
    0.41
    gür
    0.41
    вшихся
    0.41
    bum
    0.40
    Act Density 0.010%

    No Known Activations