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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cius
    -0.70
    __
    -0.66
    ______
    -0.66
    assium
    -0.64
    ___
    -0.63
    Corp
    -0.63
    washer
    -0.61
    ween
    -0.61
    atoes
    -0.60
    eteenth
    -0.60
    POSITIVE LOGITS
     JC
    0.72
    accompan
    0.70
    osponsors
    0.70
     certs
    0.68
    370
    0.64
     Juda
    0.63
     Explos
    0.63
    380
    0.63
     Assassins
    0.63
     Leilan
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.