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

    Neuronpedia

    INDEX
    Explanations

    words related to political decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific political process or mechanism, mainly focusing on plebiscites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bear
    -0.63
    LOAD
    -0.63
    worthiness
    -0.59
     Hels
    -0.59
     Modi
    -0.59
     Ingram
    -0.58
     shorth
    -0.58
    Dispatch
    -0.57
     Yam
    -0.57
     Siberian
    -0.57
    POSITIVE LOGITS
    uits
    1.19
    onduct
    1.18
    uity
    1.13
    ount
    1.10
    retion
    1.05
    ussion
    1.04
    rete
    1.01
    hetti
    1.00
    uit
    1.00
    ayne
    0.98
    Act Density 0.023%

    No Known Activations