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

    Neuronpedia

    INDEX
    Explanations

    instances of leadership roles and political power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Presidents
    -0.70
    EndProject
    -0.66
     Presidency
    -0.63
     presidency
    -0.62
     Presidents
    -0.62
    Presidential
    -0.60
     presidents
    -0.56
    Diweddarwch
    -0.55
    Ministry
    -0.54
     MINISTRY
    -0.52
    POSITIVE LOGITS
     acting
    0.80
     Acting
    0.70
    acting
    0.62
    Acting
    0.59
     leader
    0.50
     demografica
    0.49
     head
    0.49
     boss
    0.48
     interim
    0.46
     ruler
    0.44
    Act Density 0.446%

    No Known Activations