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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intention or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wrote
    -0.68
     nicknamed
    -0.65
    noticed
    -0.65
    answered
    -0.64
     drafts
    -0.64
     doubted
    -0.63
     Talks
    -0.62
    Got
    -0.61
     dubbed
    -0.61
     Preferred
    -0.61
    POSITIVE LOGITS
     stimulate
    1.37
     elicit
    1.34
     provoke
    1.32
     evoke
    1.32
     alleviate
    1.28
     discourage
    1.27
     emulate
    1.25
     facilitate
    1.25
     encourage
    1.25
     relieve
    1.24
    Act Density 0.140%

    No Known Activations