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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Shape
    -0.85
    Profile
    -0.74
    ADVERTISEMENT
    -0.70
    Leaks
    -0.69
     -->
    -0.66
    -|
    -0.66
    Closure
    -0.65
    -->
    -0.64
     Biblical
    -0.63
     Mahjong
    -0.63
    POSITIVE LOGITS
     condem
    0.76
    estate
    0.73
     veterinarian
    0.73
    utenant
    0.71
     srf
    0.67
     facult
    0.67
    doms
    0.64
    recomm
    0.64
    accompan
    0.64
     carbohyd
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.