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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geopolitical events and international relationships, especially involving the U.S

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "U.S." followed by a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ellison
    -0.60
     Dylan
    -0.59
    ·
    -0.57
     Elvis
    -0.57
     iceberg
    -0.57
     Titanic
    -0.57
     epid
    -0.56
     cherry
    -0.55
     Glacier
    -0.54
     fid
    -0.54
    POSITIVE LOGITS
    .-
    3.60
    .–
    2.50
    .--
    2.05
    )-
    1.79
    .—
    1.78
    .:
    1.75
    ./
    1.74
    .(
    1.64
    :-
    1.62
    .�
    1.59
    Act Density 0.021%

    No Known Activations