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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    heit
    -0.97
    hap
    -0.89
    bidden
    -0.86
    atem
    -0.81
    antics
    -0.74
    onson
    -0.74
    ners
    -0.74
    pir
    -0.74
    piracy
    -0.72
    ucci
    -0.71
    POSITIVE LOGITS
     Malone
    0.88
    soDeliveryDate
    0.83
     Daytona
    0.74
     Cosponsors
    0.73
     Tinker
    0.66
     Qiao
    0.65
     Nebula
    0.64
     Donetsk
    0.64
     Cyborg
    0.63
     Barkley
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.