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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    xus
    -0.79
    £ı
    -0.69
    iciency
    -0.66
    riber
    -0.64
     Instruction
    -0.63
    ģĸ
    -0.63
     anesthesia
    -0.61
    rists
    -0.61
    ingen
    -0.61
    idan
    -0.60
    POSITIVE LOGITS
     guesses
    0.80
     Mahjong
    0.72
    ascript
    0.70
    ãĤ±
    0.64
     batted
    0.64
    tein
    0.61
     Cind
    0.60
     Vaugh
    0.60
    gnu
    0.60
    Reviewer
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.