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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    BO
    -0.75
    Ĥİ
    -0.74
    NEY
    -0.70
    ESE
    -0.70
    æĥ
    -0.69
    IRT
    -0.69
    wn
    -0.68
    LI
    -0.67
    agame
    -0.64
    itures
    -0.63
    POSITIVE LOGITS
     hence
    1.05
     consequently
    1.00
     therefore
    1.00
     thus
    0.95
    rogen
    0.89
    rogens
    0.88
     thereby
    0.87
     consequ
    0.82
    alus
    0.80
     vice
    0.80
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.