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

    Neuronpedia

    INDEX
    Explanations

    words related to political campaigns and announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to emergency situations or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.66
    ibles
    -0.47
    riad
    -0.47
    clinton
    -0.46
    \":
    -0.46
    ãĥķãĤ¡
    -0.45
    ELY
    -0.43
    ormon
    -0.43
     GOODMAN
    -0.42
    embed
    -0.42
    POSITIVE LOGITS
    .</
    0.58
    .",
    0.57
    .;
    0.57
     };
    0.57
    ļéĨĴ
    0.50
    .).
    0.49
     @@
    0.49
    utm
    0.48
    .}
    0.47
    ,...
    0.46
    Act Density 2.440%

    No Known Activations