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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    artisan
    -0.83
     mosqu
    -0.71
    involved
    -0.71
     livest
    -0.69
    duc
    -0.69
    Flor
    -0.68
    Cl
    -0.67
    Marie
    -0.67
    issance
    -0.67
    ALS
    -0.67
    POSITIVE LOGITS
    rans
    0.74
     Bundy
    0.69
     Commodore
    0.65
     Rabb
    0.64
     Inher
    0.64
     Torah
    0.63
    malink
    0.62
     Rebels
    0.62
     Burns
    0.61
     ram
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.