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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ICLE
    -0.64
    hement
    -0.63
    tics
    -0.62
    arg
    -0.61
    analy
    -0.60
    reply
    -0.60
    clud
    -0.59
     å¤
    -0.59
    majority
    -0.58
    sis
    -0.58
    POSITIVE LOGITS
     Emin
    0.68
     watts
    0.64
    angan
    0.63
     Wast
    0.63
     pastors
    0.62
     charism
    0.61
     pizz
    0.61
     Te
    0.60
     interns
    0.59
     Gateway
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.