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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    trak
    -0.82
    gur
    -0.71
    ndum
    -0.69
    yip
    -0.68
    arak
    -0.67
    byter
    -0.67
     Barbarian
    -0.66
    xon
    -0.65
    reb
    -0.65
    hen
    -0.64
    POSITIVE LOGITS
    uana
    0.80
    Recomm
    0.75
    rities
    0.73
    3333
    0.71
    ivalent
    0.68
     Dock
    0.66
    joining
    0.64
     Shed
    0.64
    esides
    0.63
    Email
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.