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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Oath
    -0.93
     Rated
    -0.74
    Guard
    -0.73
    bow
    -0.70
    Ring
    -0.65
     Proud
    -0.63
     Viper
    -0.63
    TON
    -0.60
    ãĥ¬
    -0.60
     Pledge
    -0.60
    POSITIVE LOGITS
    ileaks
    0.83
    umped
    0.77
    adobe
    0.76
    icient
    0.75
    ensen
    0.70
    erent
    0.70
    aido
    0.68
    aucas
    0.67
    theless
    0.67
    iment
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.