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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific action or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Appears
    -0.83
    listed
    -0.80
    heavy
    -0.69
    done
    -0.68
    auga
    -0.67
    lime
    -0.64
    Ĭ
    -0.63
     Required
    -0.63
    checked
    -0.63
     Needs
    -0.63
    POSITIVE LOGITS
     maximize
    1.16
     fulfill
    1.15
     satisfy
    1.09
     achieve
    1.08
     facilitate
    1.07
     promote
    1.05
     minimize
    1.05
     create
    1.03
     compensate
    1.03
     avoid
    1.02
    Act Density 0.066%

    No Known Activations