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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ?".
    -0.66
     queue
    -0.62
    MQ
    -0.62
     Isis
    -0.62
     fulfillment
    -0.61
    undred
    -0.61
     toll
    -0.60
     Ce
    -0.59
     benefit
    -0.59
     remainder
    -0.57
    POSITIVE LOGITS
    endiary
    0.74
    ographs
    0.70
    lar
    0.69
     Hogan
    0.68
    ograph
    0.68
    earchers
    0.67
    phalt
    0.66
    ograp
    0.65
    regor
    0.61
     BaseType
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.