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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ategory
    -0.77
    raft
    -0.75
    rary
    -0.70
    uitous
    -0.70
    bole
    -0.68
    aft
    -0.67
    apes
    -0.66
    ãĤ¨ãĥ«
    -0.66
    nesday
    -0.66
    gradient
    -0.66
    POSITIVE LOGITS
     Behavioral
    0.70
     zo
    0.66
     Shelter
    0.64
    DEN
    0.64
     FAA
    0.64
     Disabled
    0.63
     USAF
    0.63
     Anthrop
    0.62
     Investig
    0.62
     grounded
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.