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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nuisance
    -0.72
    ergic
    -0.72
     tyr
    -0.64
     Nos
    -0.64
     symp
    -0.63
     depress
    -0.62
    ignt
    -0.62
     needless
    -0.62
     Harm
    -0.62
     Wool
    -0.61
    POSITIVE LOGITS
    andowski
    0.92
    slot
    0.79
    hung
    0.78
    CHAT
    0.78
    TPS
    0.75
    Ku
    0.71
    GPU
    0.69
    clair
    0.68
    Board
    0.68
    culus
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.