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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Core
    -0.74
     Bry
    -0.69
    ä¹
    -0.66
     cz
    -0.64
     Redd
    -0.63
     Grain
    -0.63
     Ry
    -0.63
     Azure
    -0.62
     Nec
    -0.62
    Emer
    -0.61
    POSITIVE LOGITS
     teasp
    0.85
    pour
    0.81
    enegger
    0.80
    ilan
    0.78
    entin
    0.77
     citiz
    0.76
    eter
    0.73
    jriwal
    0.72
    ierrez
    0.72
    ikers
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.