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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     WARN
    -0.91
    ãĥ´
    -0.81
    Atl
    -0.77
     destro
    -0.75
    ahime
    -0.74
     confir
    -0.70
    HUD
    -0.70
    DN
    -0.70
    Bloomberg
    -0.70
    COL
    -0.69
    POSITIVE LOGITS
    oise
    0.78
     amenities
    0.71
     Features
    0.66
    avis
    0.62
     Tigers
    0.62
     Karma
    0.62
    emade
    0.60
     Fields
    0.59
     Effects
    0.57
     Procedure
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.