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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oqu
    -0.38
    hern
    -0.37
    artisan
    -0.37
    optional
    -0.36
     Railroad
    -0.36
    sole
    -0.35
    claimed
    -0.34
    erness
    -0.34
    adj
    -0.34
     Airl
    -0.32
    POSITIVE LOGITS
     punches
    0.41
    ãĥ£
    0.39
    isons
    0.37
    ãĤ©
    0.36
    oes
    0.35
    ãĥ¼ãĥĨãĤ£
    0.35
    furt
    0.32
    ãĥ¥
    0.32
    Cs
    0.32
     cohorts
    0.32
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.