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

    Neuronpedia

    INDEX
    Explanations

    words related to challenging or questioning authority or established norms

    oai_token-act-pair · gpt-3.5-turbo

    phrases and constructions related to coordination or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patriots
    -0.66
     Newport
    -0.65
     Cotton
    -0.62
     Yao
    -0.62
     Colts
    -0.61
     Dolphins
    -0.61
     Oaks
    -0.61
     Quinn
    -0.60
     Broncos
    -0.60
    iens
    -0.59
    POSITIVE LOGITS
    rogens
    1.09
    rogen
    1.00
    )=(
    0.74
     educate
    0.73
    ropolitan
    0.69
     humili
    0.69
     eliminate
    0.68
    thur
    0.68
     simplify
    0.67
    rew
    0.67
    Act Density 0.220%

    No Known Activations