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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     incre
    -0.81
    ecided
    -0.67
     navy
    -0.64
     forwarded
    -0.61
     chang
    -0.61
    wine
    -0.61
     Rouge
    -0.60
    minus
    -0.58
     Alexandria
    -0.58
     Whe
    -0.57
    POSITIVE LOGITS
    enegger
    1.00
    choice
    0.74
    ounter
    0.72
     condoms
    0.71
    opian
    0.71
    aceae
    0.70
    ounters
    0.69
    essions
    0.69
    iatrics
    0.68
    oms
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.