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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    elta
    -0.80
    etr
    -0.74
    ndra
    -0.72
    ancial
    -0.69
    ertodd
    -0.65
    izontal
    -0.64
    aneers
    -0.63
    folk
    -0.62
    }"
    -0.62
    ovi
    -0.61
    POSITIVE LOGITS
     charact
    0.68
    acus
    0.64
     lengths
    0.63
    laughs
    0.63
     Hastings
    0.63
     symp
    0.62
    izational
    0.62
     Waterloo
    0.61
    Laughs
    0.59
    hod
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.