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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Guatem
    -0.73
     fitt
    -0.72
     choked
    -0.67
     spac
    -0.66
     smugg
    -0.66
     assass
    -0.65
     Major
    -0.65
     perish
    -0.64
     slain
    -0.63
    odied
    -0.63
    POSITIVE LOGITS
    rawl
    0.82
    Incre
    0.80
    rir
    0.74
    akeru
    0.74
    iture
    0.72
    lopp
    0.72
    ãĥĹ
    0.70
    coins
    0.70
    atars
    0.68
    glers
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.