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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.84
    hammad
    -0.82
    anta
    -0.82
    icans
    -0.78
    actionDate
    -0.75
    ento
    -0.75
    acas
    -0.74
    ursor
    -0.73
     captcha
    -0.70
    modules
    -0.70
    POSITIVE LOGITS
    PRO
    0.68
     Brach
    0.66
    Executive
    0.62
    enged
    0.62
    Deal
    0.61
    Own
    0.60
    negie
    0.59
    NVIDIA
    0.59
    batch
    0.58
     McLaren
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.