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

    Neuronpedia

    INDEX
    Explanations

    sequences of code function calls or specific programming syntax

    oai_token-act-pair · gpt-3.5-turbo

    code snippets and related programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gearing
    -0.79
    Downloadha
    -0.78
     dod
    -0.78
     regul
    -0.73
     foregoing
    -0.67
     streng
    -0.67
     catast
    -0.67
     bluff
    -0.65
     nose
    -0.65
     Sahara
    -0.65
    POSITIVE LOGITS
    ().
    1.61
    ();
    1.57
    ())
    1.50
    ());
    1.45
    (),
    1.45
    ()
    1.42
    ({
    1.32
    ('
    1.31
    ("
    1.27
     ().
    1.26
    Act Density 0.084%

    No Known Activations