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

    Neuronpedia

    INDEX
    Explanations

    locations mentioned along with abbreviated state names

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or codes related to geographic locations, particularly in New Jersey and New York

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     slic
    -0.65
    DragonMagazine
    -0.64
    Maker
    -0.58
    adobe
    -0.58
     sleeper
    -0.58
    handedly
    -0.57
    poke
    -0.57
     Clicker
    -0.57
     comprom
    -0.56
    theless
    -0.56
    POSITIVE LOGITS
    .,
    1.92
    .;
    1.62
    .:
    1.57
    .?
    1.56
    ./
    1.42
    .,"
    1.38
    .—
    1.28
    .),
    1.27
    .-
    1.22
    .–
    1.21
    Act Density 0.040%

    No Known Activations