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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     vanishing
    -0.68
    PDATE
    -0.61
    monary
    -0.60
    Cro
    -0.60
    Interstitial
    -0.60
    haw
    -0.58
    hern
    -0.58
     depl
    -0.57
     pat
    -0.57
     trophy
    -0.57
    POSITIVE LOGITS
    akeru
    0.72
    inc
    0.70
    prising
    0.69
    edin
    0.68
    conn
    0.68
    edIn
    0.66
    makers
    0.66
     Builder
    0.66
     undercut
    0.64
     assemblies
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.