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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    olor
    -0.65
    ritis
    -0.65
     reckoned
    -0.64
    efined
    -0.64
    rils
    -0.63
    ERA
    -0.62
    urat
    -0.62
    Ren
    -0.61
    hift
    -0.61
    category
    -0.61
    POSITIVE LOGITS
    WARD
    0.75
     bragging
    0.67
    SpaceEngineers
    0.62
    rawdownloadcloneembedreportprint
    0.61
    actionDate
    0.61
     Hamm
    0.58
     ¯
    0.57
    batch
    0.57
    ubes
    0.57
    atche
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.