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

    Neuronpedia

    INDEX
    Explanations

    references to individuals holding presidential titles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Borgo
    -0.69
    ỡng
    -0.69
     Roskov
    -0.69
    ñoz
    -0.68
    DropColumn
    -0.66
    jerg
    -0.65
     LK
    -0.64
    oog
    -0.63
     Turin
    -0.63
     ske
    -0.62
    POSITIVE LOGITS
     Presidents
    1.30
     presidents
    1.29
     President
    1.22
     president
    1.17
    Presidents
    1.16
     PRESIDENT
    1.09
     presidential
    1.01
     presidency
    0.98
    President
    0.97
     Präsident
    0.97
    Act Density 0.040%

    No Known Activations