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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    medium
    -0.82
    pel
    -0.76
    ispers
    -0.75
    bones
    -0.69
    eln
    -0.68
    maxwell
    -0.68
    tube
    -0.66
    milo
    -0.65
     burner
    -0.64
    spe
    -0.64
    POSITIVE LOGITS
     Dul
    0.75
     Camer
    0.67
     ¶
    0.65
     FROM
    0.64
     Scythe
    0.63
     Babe
    0.62
     Phen
    0.61
     Stard
    0.61
     Auth
    0.61
     Greenwood
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.