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

    Neuronpedia

    INDEX
    Explanations

    locations like cities and states

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific U.S. states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.74
     Crimean
    -0.69
     caution
    -0.65
    DragonMagazine
    -0.62
     foot
    -0.60
     pointers
    -0.58
     multiplication
    -0.57
     Naked
    -0.57
     Gravity
    -0.56
     favour
    -0.56
    POSITIVE LOGITS
    .,
    1.89
    .;
    1.55
    .:
    1.40
    .?
    1.34
    ./
    1.27
    .,"
    1.25
    .—
    1.19
    .--
    1.16
    .),
    1.13
    .-
    1.10
    Act Density 0.049%

    No Known Activations