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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hung
    0.96
     steeply
    0.95
     evil
    0.91
     giới
    0.88
     severe
    0.88
     uranium
    0.87
     unpaid
    0.87
     repeated
    0.85
     cuộc
    0.85
     والث
    0.84
    POSITIVE LOGITS
    $
    1.07
    $`
    1.02
     особенности
    1.00
    goers
    0.99
    $\
    0.99
    robes
    0.98
    couple
    0.98
    in
    0.98
    $'
    0.97
     Л
    0.97
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.