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

    Neuronpedia

    INDEX
    Explanations

    political criticism targeting specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve criticism or strong disapproval of entities and individuals, particularly in the political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prest
    -0.71
     Caldwell
    -0.67
    llular
    -0.65
    along
    -0.63
     Approximately
    -0.62
    aea
    -0.62
    erves
    -0.61
     Seah
    -0.60
    Med
    -0.60
    VILLE
    -0.59
    POSITIVE LOGITS
     hypocrisy
    1.05
     inaction
    0.97
     coward
    0.95
     unfair
    0.92
     motives
    0.91
     sexist
    0.90
     arrogance
    0.89
     inconsistency
    0.89
     bigotry
    0.89
     perceived
    0.88
    Act Density 0.456%

    No Known Activations