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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     precon
    -0.72
    buquerque
    -0.67
     habitable
    -0.66
     opin
    -0.66
     doctoral
    -0.65
    cot
    -0.64
    rentice
    -0.64
     Hercules
    -0.63
    hovah
    -0.62
    tons
    -0.62
    POSITIVE LOGITS
    uckles
    0.79
    EE
    0.78
    andan
    0.74
    UME
    0.74
     è£ı
    0.72
     Jade
    0.72
    INESS
    0.72
    SEE
    0.72
    YE
    0.70
    MN
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.