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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Cub
    -0.69
    ube
    -0.67
    uer
    -0.65
     Fletcher
    -0.64
     Deus
    -0.64
    LLOW
    -0.63
     Solitaire
    -0.62
     Less
    -0.62
    mann
    -0.61
     Sut
    -0.60
    POSITIVE LOGITS
    enza
    0.85
    gypt
    0.80
    ignty
    0.77
    origin
    0.67
    olulu
    0.67
    helps
    0.66
     livest
    0.66
    kas
    0.66
     appropriation
    0.66
    culosis
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.