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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     postulates
    1.16
     decreases
    1.06
    です
    1.05
    <0x8A>
    0.98
     narrates
    0.98
     terminates
    0.98
     acts
    0.97
     increases
    0.96
     parses
    0.96
    ной
    0.96
    POSITIVE LOGITS
    ه
    1.24
    i
    1.20
    רים
    1.13
    ار
    1.06
    Heights
    0.99
    urile
    0.98
    e
    0.97
    ک
    0.97
    م
    0.95
     lunga
    0.95
    Act Density 0.000%

    No Known Activations