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

    Neuronpedia

    INDEX
    Explanations

    references to loops in programming or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.73
    +#+
    -0.71
     Danilo
    -0.69
    st
    -0.69
    SAE
    -0.69
    excell
    -0.68
    ,:);
    -0.68
     assolu
    -0.67
     pitié
    -0.67
     Montal
    -0.64
    POSITIVE LOGITS
     loop
    1.45
     loops
    1.38
     circle
    1.36
     CIR
    1.34
     Loop
    1.31
     circles
    1.31
     Loops
    1.31
     CIRCLE
    1.30
     LOOP
    1.30
    loop
    1.30
    Act Density 0.231%

    No Known Activations