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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political campaigning and policy discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to political processes and election-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.81
    +.
    -0.78
    surprisingly
    -0.75
    !.
    -0.73
     âĵĺ
    -0.68
    ©¶æ¥µ
    -0.67
    %.
    -0.66
    anwhile
    -0.61
     nonetheless
    -0.60
    .(
    -0.59
    POSITIVE LOGITS
     ..."
    1.58
     âĢ¦"
    1.47
    )"
    1.47
    )",
    1.31
    )."
    1.29
    ),"
    1.29
     [
    1.21
    ..."
    1.17
    ?"
    1.17
    ?",
    1.15
    Act Density 1.430%

    No Known Activations