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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anwhile
    -0.76
    grounds
    -0.73
     abund
    -0.68
    wcs
    -0.68
    deck
    -0.66
     devise
    -0.66
    arity
    -0.65
    align
    -0.64
    abilities
    -0.63
    raints
    -0.63
    POSITIVE LOGITS
     course
    0.83
    gery
    0.67
     RELE
    0.66
    elia
    0.65
    icial
    0.64
    odox
    0.63
     COUR
    0.62
     sorts
    0.62
    asses
    0.61
     shin
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.