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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     STD
    -0.75
    plain
    -0.69
    errors
    -0.66
    brow
    -0.66
     NX
    -0.65
    worm
    -0.64
    tis
    -0.64
    reader
    -0.63
    Arg
    -0.63
     Compl
    -0.63
    POSITIVE LOGITS
    rica
    0.76
    iba
    0.65
    rals
    0.63
    eco
    0.63
    cers
    0.61
    itutional
    0.61
    icultural
    0.60
    ihil
    0.59
    ude
    0.59
    phia
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.