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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    =#
    -0.77
     Indigo
    -0.66
    under
    -0.65
    Republic
    -0.65
    )|
    -0.64
    ãĤĵ
    -0.63
    unin
    -0.63
    izoph
    -0.60
    âĸº
    -0.60
    Detroit
    -0.60
    POSITIVE LOGITS
    reau
    0.81
    llah
    0.73
    senal
    0.72
    pell
    0.71
    arin
    0.67
    mens
    0.66
    ghai
    0.66
     acceler
    0.65
     intertw
    0.63
     commissions
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.