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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    afer
    -0.66
    hester
    -0.66
     undet
    -0.66
    arij
    -0.65
    alog
    -0.65
    ophers
    -0.64
    kill
    -0.64
    ordon
    -0.63
    iceps
    -0.63
    ivot
    -0.63
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.67
    netflix
    0.66
     Glas
    0.63
    Cry
    0.63
     Helm
    0.62
    ãĤ´
    0.61
    Asset
    0.61
     hospitals
    0.59
     Fifa
    0.58
    govtrack
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.