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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lavrov
    -0.84
    ariat
    -0.74
    adium
    -0.72
    ovo
    -0.69
     Armenian
    -0.68
     Radius
    -0.66
     Pagan
    -0.65
     Tanz
    -0.64
    iannopoulos
    -0.64
     Armenia
    -0.64
    POSITIVE LOGITS
    below
    0.76
    birth
    0.71
     tanks
    0.71
     tar
    0.68
     tank
    0.66
    above
    0.64
    pir
    0.64
    renheit
    0.63
     topped
    0.62
    oles
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.