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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    obi
    -0.72
    letal
    -0.66
     Fract
    -0.65
    ahon
    -0.64
     Ninja
    -0.62
    ':
    -0.62
    LINE
    -0.61
    ÃĤ
    -0.61
    perture
    -0.61
    Users
    -0.61
    POSITIVE LOGITS
    thur
    0.87
    sburg
    0.77
     franc
    0.70
     quotas
    0.68
    prus
    0.67
    anwhile
    0.67
     prosec
    0.67
    theless
    0.67
     negoti
    0.66
    vine
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.