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

    Neuronpedia

    INDEX
    Explanations

    words related to programming loops and their iterations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.74
    hiro
    -0.69
    insula
    -0.68
    undai
    -0.66
    rament
    -0.65
     Aram
    -0.62
    rd
    -0.62
    assadors
    -0.61
    price
    -0.60
     Spartans
    -0.60
    POSITIVE LOGITS
    back
    0.92
    ingly
    0.88
    ing
    0.88
     loop
    0.83
    overs
    0.82
    ed
    0.81
    loop
    0.79
    Closure
    0.79
    ioned
    0.78
     loops
    0.75
    Act Density 0.020%

    No Known Activations