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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bluff
    -0.74
    ikuman
    -0.68
     lawy
    -0.67
     subsequ
    -0.67
     fortun
    -0.66
     regards
    -0.64
     ener
    -0.63
     mathemat
    -0.63
     amen
    -0.62
     spor
    -0.62
    POSITIVE LOGITS
     attRot
    0.80
    vous
    0.77
     Decay
    0.73
    cedes
    0.72
    doi
    0.71
     srfAttach
    0.70
    ));
    0.68
    URI
    0.66
    Already
    0.66
    azed
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.