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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    eport
    -0.78
    uds
    -0.78
    anes
    -0.72
    ecided
    -0.69
    ragon
    -0.67
    owntown
    -0.67
    Initialized
    -0.67
    uni
    -0.66
     Alloy
    -0.66
    ortun
    -0.65
    POSITIVE LOGITS
    SPONSORED
    0.82
     veto
    0.70
    eering
    0.68
    zai
    0.67
     Clause
    0.65
    itarian
    0.65
     lawy
    0.63
     IPM
    0.61
     capit
    0.61
    ··
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.