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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     smugglers
    -0.76
    Actor
    -0.75
    adden
    -0.70
     Heist
    -0.70
    ics
    -0.67
     credits
    -0.67
     Warehouse
    -0.65
    CBS
    -0.65
    /$
    -0.64
     Actor
    -0.63
    POSITIVE LOGITS
     moderation
    0.83
     sclerosis
    0.78
    irrel
    0.75
    rador
    0.74
     Neurolog
    0.69
    olit
    0.69
    anke
    0.67
    omal
    0.67
    Ń·
    0.67
    hower
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.