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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     challenges
    1.20
     laude
    1.07
     manoe
    1.07
    embrie
    1.01
     finances
    0.97
     ditches
    0.96
    бал
    0.96
     maneuvers
    0.96
     dá
    0.95
     expedition
    0.95
    POSITIVE LOGITS
    s
    1.16
    r
    1.11
    وب
    1.01
    suffixes
    0.99
     ursprüng
    0.97
     Сле
    0.96
     كانوا
    0.96
    sampler
    0.94
    suffix
    0.93
    rn
    0.93
    Act Density 0.000%

    No Known Activations