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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    merce
    -0.73
    lesh
    -0.72
     inj
    -0.71
     wounding
    -0.70
     looph
    -0.67
    license
    -0.63
    çİĭ
    -0.63
    mbuds
    -0.63
    ãĤ¨ãĥ«
    -0.61
    try
    -0.61
    POSITIVE LOGITS
    otes
    0.70
     Shant
    0.68
     Rouse
    0.66
     Alonso
    0.66
     Concord
    0.64
    bats
    0.63
     Scalia
    0.63
     Anger
    0.63
     Sett
    0.62
     Attributes
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.