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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    terday
    -0.73
    idon
    -0.73
    olicy
    -0.71
     Tacoma
    -0.66
    idem
    -0.65
    etus
    -0.65
    isd
    -0.61
     whichever
    -0.60
    poon
    -0.60
     Titus
    -0.59
    POSITIVE LOGITS
    ricular
    0.77
    Laun
    0.74
    iable
    0.72
    iasis
    0.67
    oys
    0.64
    imental
    0.61
    nance
    0.61
    iability
    0.60
     mating
    0.60
    tsy
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.