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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Sek
    -0.72
     citiz
    -0.71
    Ħ¢
    -0.69
     mosqu
    -0.69
     SAS
    -0.64
     arming
    -0.64
     seq
    -0.63
     DEAD
    -0.62
     anonymity
    -0.62
     haste
    -0.62
    POSITIVE LOGITS
    arent
    0.88
    Ford
    0.86
    nard
    0.84
    rolet
    0.81
    ham
    0.79
    rown
    0.79
    dor
    0.76
    dain
    0.76
    ovy
    0.76
    nih
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.