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

    Neuronpedia

    INDEX
    Explanations

    terms related to political parties and leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighbors
    -0.45
     hout
    -0.45
     Neighbors
    -0.42
    films
    -0.41
    エピ
    -0.41
     пло
    -0.40
     Nachbarn
    -0.40
    Especies
    -0.39
    gnancy
    -0.38
     operator
    -0.38
    POSITIVE LOGITS
     party
    1.52
     Party
    1.36
    party
    1.29
    Party
    1.26
     PARTY
    1.25
    PARTY
    1.22
     Partei
    0.99
     caucus
    0.94
     partij
    0.92
     partai
    0.89
    Act Density 0.206%

    No Known Activations