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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     refugees
    1.11
     heroes
    1.08
     suppliers
    1.02
     monkeys
    1.02
     experts
    1.01
     soldiers
    0.95
     employees
    0.95
     brothers
    0.94
     judges
    0.94
     manufacturers
    0.93
    POSITIVE LOGITS
    5
    0.99
    1
    0.88
    .'
    0.86
    3
    0.85
    ."
    0.84
    7
    0.84
    ,"
    0.83
     Upon
    0.83
    single
    0.82
    4
    0.82
    Act Density 0.000%

    No Known Activations