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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    overflow
    1.15
     Controversy
    1.11
     constitue
    1.05
     Literally
    1.04
    ie
    1.02
    hatta
    1.01
    ați
    1.01
    ına
    0.98
    ﮧ
    0.98
     mariage
    0.97
    POSITIVE LOGITS
    拯
    1.20
    AN
    1.18
     СК
    1.18
    ীক
    1.17
     headlights
    1.16
     ensembles
    1.16
    ной
    1.11
     recollections
    1.11
     Wanderers
    1.10
    שי
    1.10
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.