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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ODY
    -0.80
    ãĥĦ
    -0.65
     Domain
    -0.65
    ierre
    -0.64
     reapp
    -0.63
     Cree
    -0.62
    itatively
    -0.61
    ocl
    -0.61
    haus
    -0.61
     Ny
    -0.61
    POSITIVE LOGITS
    interstitial
    0.77
    bull
    0.73
    hops
    0.73
    gae
    0.69
    ident
    0.69
    opus
    0.68
    asking
    0.67
    mates
    0.66
    aturdays
    0.66
    ecided
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.