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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    llah
    -0.77
    UE
    -0.72
     Mant
    -0.69
    ancel
    -0.63
    MQ
    -0.63
    racuse
    -0.62
    ente
    -0.60
     Templar
    -0.60
     EVENTS
    -0.60
     UE
    -0.59
    POSITIVE LOGITS
    oun
    0.82
    sen
    0.78
    law
    0.75
    tein
    0.70
    nel
    0.66
    kers
    0.65
    per
    0.62
    iery
    0.62
     solicitor
    0.62
    iland
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.