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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rification
    -0.80
     envy
    -0.69
    zl
    -0.65
     Zin
    -0.63
     Meier
    -0.62
    oning
    -0.62
     Ethan
    -0.61
     snaps
    -0.61
     finance
    -0.61
    ickr
    -0.60
    POSITIVE LOGITS
    ãĥĩãĤ£
    0.78
    catentry
    0.70
    handled
    0.67
    AMI
    0.67
     Appears
    0.65
    urger
    0.64
    è¦ļéĨĴ
    0.64
     ãĥ
    0.63
    AZ
    0.63
    abases
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.