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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bourg
    -0.83
    export
    -0.80
    super
    -0.72
    oen
    -0.69
    ult
    -0.69
    EA
    -0.68
    guard
    -0.68
    Meg
    -0.65
    gov
    -0.65
    tern
    -0.64
    POSITIVE LOGITS
     incorpor
    0.71
    gery
    0.66
     disguised
    0.63
     captains
    0.62
     indebted
    0.61
     android
    0.59
     sparks
    0.59
     valiant
    0.59
     distortions
    0.59
     futile
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.