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

    Neuronpedia

    INDEX
    Explanations

    instances where action or decision-making is attributed to a governmental entity

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the government has" followed by various issues or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eem
    -0.70
    thing
    -0.67
    ickle
    -0.66
    ogue
    -0.65
    %%%%
    -0.62
    inducing
    -0.62
    vill
    -0.60
    ateful
    -0.59
    opian
    -0.58
    —-
    -0.58
    POSITIVE LOGITS
     been
    1.33
     begun
    1.07
     gotten
    0.98
     undergone
    0.97
     become
    0.97
     always
    0.97
     already
    0.96
     traditionally
    0.93
     instituted
    0.91
     gone
    0.91
    Act Density 0.319%

    No Known Activations