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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    1.04
    t
    1.01
    table
    1.00
    T
    0.97
    filter
    0.96
    take
    0.94
    tt
    0.94
    tf
    0.94
    ta
    0.93
    tattoo
    0.92
    POSITIVE LOGITS
    ობის
    0.69
     teammates
    0.68
     annoyed
    0.68
     peric
    0.65
    溏
    0.64
     durg
    0.63
     únic
    0.62
     για
    0.62
     dla
    0.61
     politely
    0.61
    Act Density 0.000%

    No Known Activations