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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    OST
    -0.77
    ONEY
    -0.73
    ORK
    -0.70
     Unloaded
    -0.67
    aintain
    -0.66
    ittance
    -0.63
     arose
    -0.63
    alter
    -0.61
     Abram
    -0.61
    anish
    -0.61
    POSITIVE LOGITS
     Suns
    0.69
    nces
    0.68
     Droid
    0.66
     Samar
    0.65
     Accountability
    0.65
    intendent
    0.63
    pants
    0.63
     princ
    0.62
     Spartan
    0.61
     Carly
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.