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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uties
    -0.69
     Krishna
    -0.67
     Than
    -0.67
     desired
    -0.65
     surn
    -0.65
     Yin
    -0.64
     deprecated
    -0.64
    TERN
    -0.64
    angs
    -0.63
     traced
    -0.62
    POSITIVE LOGITS
    unin
    0.87
    surv
    0.81
    Bul
    0.78
    cgi
    0.78
    bull
    0.72
    interstitial
    0.72
    nesia
    0.70
    alysis
    0.70
    phony
    0.69
     correctness
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.