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

    Neuronpedia

    INDEX
    Explanations

    references to loops and looping structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    loop structures and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fac
    -0.39
    #
    -0.38
     National
    -0.38
    (");
    -0.37
    "]);
    -0.36
    ."));
    -0.36
    '])
    -0.35
    "])
    -0.34
    ')).
    -0.34
    .}\
    -0.34
    POSITIVE LOGITS
     loop
    2.50
     Loop
    2.38
    loop
    2.30
     LOOP
    2.27
    Loop
    2.25
     loops
    2.20
     Loops
    2.06
    loops
    1.97
    LOOP
    1.94
     looped
    1.92
    Act Density 0.008%

    No Known Activations