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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    agra
    -0.81
     captcha
    -0.75
    ocrates
    -0.74
    ould
    -0.73
    velength
    -0.73
    ente
    -0.72
    ĸļ
    -0.70
     ancest
    -0.70
    ergy
    -0.69
    DonaldTrump
    -0.68
    POSITIVE LOGITS
     TN
    0.78
     Vengeance
    0.70
     DD
    0.65
     Predator
    0.63
     Tanzania
    0.62
     Ports
    0.60
     Tornado
    0.60
    process
    0.60
    tracking
    0.60
     Hydra
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.