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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tes
    -0.76
    Hour
    -0.69
    sign
    -0.69
    WORK
    -0.64
    lich
    -0.63
    phant
    -0.63
    inces
    -0.62
    riers
    -0.62
    dule
    -0.61
    agos
    -0.61
    POSITIVE LOGITS
    eworld
    0.95
    enthal
    0.81
    ESE
    0.70
    liness
    0.69
     renamed
    0.68
     overdose
    0.66
    ugen
    0.66
    roxy
    0.65
    aq
    0.63
    ADS
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.