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

    Neuronpedia

    INDEX
    Explanations

    references to arrays and their elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '))
    -0.66
    </em>
    -0.59
     ')
    -0.59
     Baños
    -0.57
     out
    -0.54
     he
    -0.53
     pe
    -0.52
     to
    -0.51
     '
    -0.50
     ge
    -0.50
    POSITIVE LOGITS
    ['
    2.47
    ["
    2.24
    ]['
    1.57
    ]["
    1.56
    ['_
    1.42
    "]["
    1.34
    ()['
    1.28
    [@"
    1.28
    ["_
    1.24
    ']['
    1.23
    Act Density 0.026%

    No Known Activations