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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     spaced
    -0.73
     justified
    -0.72
     resur
    -0.69
     perm
    -0.68
     whistlebl
    -0.68
     hugs
    -0.64
    wx
    -0.64
     lyn
    -0.63
     Xin
    -0.63
     rested
    -0.62
    POSITIVE LOGITS
    etter
    0.82
     Offense
    0.81
    oscope
    0.79
    pour
    0.78
    chel
    0.77
    istance
    0.76
    workshop
    0.75
    Entry
    0.73
    eer
    0.71
    ustom
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.