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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orno
    -0.79
    orem
    -0.75
    akedown
    -0.75
     Editors
    -0.71
    anqu
    -0.70
    wp
    -0.70
    aturday
    -0.69
    ebus
    -0.68
    ebin
    -0.68
    utor
    -0.64
    POSITIVE LOGITS
    çļ
    0.66
     Jade
    0.63
     Gors
    0.63
     particulars
    0.62
    heart
    0.61
    yth
    0.60
     Mutant
    0.60
     Tart
    0.60
     exact
    0.59
     ILCS
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.