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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ibli
    -0.91
    ãĤ¼ãĤ¦ãĤ¹
    -0.77
    Marginal
    -0.75
     Gutenberg
    -0.75
    alian
    -0.74
    Õ
    -0.69
    ĸļ
    -0.69
    ells
    -0.68
    çĶ
    -0.67
    culosis
    -0.66
    POSITIVE LOGITS
    visor
    0.70
     descending
    0.62
     distinguished
    0.62
     Jolly
    0.61
     discord
    0.60
     assemble
    0.58
     emblem
    0.58
     Trident
    0.58
    wagen
    0.58
     MX
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.