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

    Neuronpedia

    INDEX
    Explanations

    names of specific presidents

    oai_token-act-pair · gpt-3.5-turbo

    references to U.S. presidents and their terms in office

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atown
    -0.72
     srf
    -0.70
    ript
    -0.67
     detector
    -0.66
     workshops
    -0.63
    utra
    -0.63
    isphere
    -0.63
    Forge
    -0.62
    mol
    -0.62
    liga
    -0.62
    POSITIVE LOGITS
     Barack
    1.58
     Reagan
    1.58
     Presidents
    1.58
     Ronald
    1.53
     FDR
    1.49
     Lyndon
    1.46
     presidents
    1.44
     Eisenhower
    1.44
     Nixon
    1.41
     George
    1.40
    Act Density 0.473%

    No Known Activations