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

    Neuronpedia

    INDEX
    Explanations

    political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    references to political leadership and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atown
    -0.73
    complex
    -0.73
    asy
    -0.71
    atten
    -0.69
    ascript
    -0.68
    cycles
    -0.68
    eger
    -0.67
    stakes
    -0.66
    erning
    -0.66
    avascript
    -0.65
    POSITIVE LOGITS
     leader
    1.68
     president
    1.65
     ambassador
    1.53
     mayor
    1.51
     Chief
    1.47
     chief
    1.47
     chancellor
    1.46
     governor
    1.45
     chairman
    1.43
     CEO
    1.41
    Act Density 0.553%

    No Known Activations