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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atra
    -0.77
    utterstock
    -0.64
     "$:/
    -0.62
    irl
    -0.59
     eats
    -0.59
     Dun
    -0.58
    jar
    -0.57
    yd
    -0.57
     qualifies
    -0.57
    pt
    -0.57
    POSITIVE LOGITS
    mble
    0.85
     lett
    0.68
     pse
    0.66
    lli
    0.64
    meric
    0.64
    ĸļ
    0.64
    Honest
    0.62
    uum
    0.62
    Aren
    0.62
     investigator
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.