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

    Neuronpedia

    INDEX
    Explanations

    political terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding electoral losses, particularly in the context of political figures and their vote counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à©
    -0.59
     newcomers
    -0.56
     corrid
    -0.56
    rawler
    -0.54
     appetite
    -0.53
     anticip
    -0.52
    ãĥ«
    -0.52
    iosyncr
    -0.51
    atile
    -0.50
     encour
    -0.49
    POSITIVE LOGITS
    !!!
    1.43
    !".
    1.43
    ?!
    1.40
    !!!!
    1.39
    !!!!!
    1.39
    ???
    1.37
    !!
    1.36
    !?
    1.36
    ?!"
    1.34
    !",
    1.34
    Act Density 0.891%

    No Known Activations