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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific substances or medical conditions, particularly caffeine-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to caffeine and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.77
    flies
    -0.74
    ships
    -0.73
    ship
    -0.72
    chool
    -0.72
    soever
    -0.69
    \<
    -0.67
     Turtles
    -0.66
    irt
    -0.66
    OTA
    -0.64
    POSITIVE LOGITS
     Osw
    0.87
    inated
    0.81
    ishment
    0.78
    ting
    0.78
    rection
    0.76
    ining
    0.75
    ormal
    0.74
    ornings
    0.72
    zers
    0.72
    aser
    0.71
    Act Density 0.053%

    No Known Activations