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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Tribune
    0.88
    ps
    0.83
    versions
    0.82
     Seitz
    0.81
    ceptions
    0.80
    ❐
    0.78
     thumb
    0.78
    ported
    0.77
    waj
    0.77
     tangent
    0.77
    POSITIVE LOGITS
    ",
    1.44
    },
    1.42
    ],
    1.32
     },
    1.27
    ”,
    1.26
    ',
    1.25
    `,
    1.25
    },\
    1.22
    }$,
    1.21
     ],
    1.21
    Act Density 0.595%

    No Known Activations