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

    Neuronpedia

    INDEX
    Explanations

    terms related to political positions and governmental roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    governor and mayor titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.63
     ſmall
    -0.55
     leſs
    -0.53
     myſelf
    -0.52
    ſelf
    -0.52
     quæ
    -0.51
     leaſt
    -0.50
     ſche
    -0.49
     ſta
    -0.49
     faſt
    -0.46
    POSITIVE LOGITS
     governor
    0.65
     Governor
    0.65
    Governor
    0.62
     governors
    0.59
    governor
    0.56
     mayors
    0.55
     gobernador
    0.55
    stdc
    0.54
     governorship
    0.54
     governador
    0.54
    Act Density 0.001%

    No Known Activations