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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    fromParams
    0.94
    ospheres
    0.85
    Parad
    0.85
    𝗙
    0.84
    phyr
    0.82
    ollar
    0.82
    ensburg
    0.82
    )’
    0.81
    Jess
    0.80
    Kennedy
    0.80
    POSITIVE LOGITS
     ።
    1.01
     leave
    0.98
     --
    0.97
     reg
    0.94
     —
    0.93
     cl
    0.92
     AU
    0.90
     chemical
    0.88
     reading
    0.88
     //
    0.87
    Act Density 0.000%

    No Known Activations