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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    achus
    -0.73
    utherford
    -0.68
    Morning
    -0.66
     aut
    -0.66
    Mini
    -0.65
    idon
    -0.62
    ependence
    -0.61
    oday
    -0.61
    Zone
    -0.60
    kies
    -0.60
    POSITIVE LOGITS
     taxp
    0.75
    oker
    0.68
     Mub
    0.66
     Vaugh
    0.65
     toile
    0.64
    anca
    0.64
    gettable
    0.63
    payer
    0.61
     haun
    0.60
     Cambod
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.