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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Patty
    -0.72
    amina
    -0.68
    adish
    -0.68
     Lowry
    -0.66
     Fuller
    -0.64
    ia
    -0.63
    law
    -0.62
     Barron
    -0.62
    ĥ
    -0.62
    idity
    -0.61
    POSITIVE LOGITS
     showc
    0.77
    forward
    0.76
     elig
    0.74
    quartered
    0.74
     compan
    0.72
    minist
    0.70
    eworld
    0.70
     powd
    0.67
     perf
    0.66
     feder
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.