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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pron
    -0.69
    boss
    -0.67
     Benedict
    -0.64
    ert
    -0.64
    fest
    -0.63
    arr
    -0.63
    rio
    -0.63
    smith
    -0.61
    cha
    -0.61
    erie
    -0.59
    POSITIVE LOGITS
    ._
    0.71
    isd
    0.70
     tradem
    0.69
    theless
    0.67
     Sundays
    0.67
    etary
    0.66
     Taj
    0.64
    ailable
    0.63
    EY
    0.63
    yx
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.