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

    Neuronpedia

    INDEX
    Explanations

    words that introduce actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intent or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pict
    -0.71
     Appears
    -0.70
     traded
    -0.60
    calling
    -0.60
    itates
    -0.58
    AAAAAAAA
    -0.57
    cards
    -0.56
     disappeared
    -0.56
     forg
    -0.56
    comments
    -0.56
    POSITIVE LOGITS
     summarize
    1.28
    ilet
    1.28
     complicate
    1.27
     illustrate
    1.23
     maximize
    1.19
     accomplish
    1.17
     achieve
    1.16
     facilitate
    1.14
     compensate
    1.14
     reiterate
    1.12
    Act Density 0.047%

    No Known Activations