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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Highlights
    -0.78
     resumes
    -0.72
     contrasts
    -0.70
     slideshow
    -0.70
     IMAGES
    -0.68
     mandate
    -0.68
     reversal
    -0.67
     hinges
    -0.67
     culmin
    -0.66
     signifies
    -0.65
    POSITIVE LOGITS
     asleep
    1.12
     assassinated
    1.12
     murdered
    1.05
     killed
    1.03
     able
    0.99
     born
    0.99
    wolf
    0.99
     kidnapped
    0.98
     bitten
    0.94
     gunned
    0.93
    Act Density 0.402%

    No Known Activations