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

    Neuronpedia

    INDEX
    Explanations

    elements related to class and function definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ainfi
    -1.40
    <unused52>
    -1.27
    <unused16>
    -1.27
     auroit
    -1.27
    <unused14>
    -1.27
    [@BOS@]
    -1.27
    <unused28>
    -1.26
    <unused51>
    -1.26
    <unused8>
    -1.26
    <unused3>
    -1.26
    POSITIVE LOGITS
    n
    0.35
    d
    0.35
    e
    0.31
    r
    0.30
    er
    0.29
      
    0.28
    NA
    0.28
    　
    0.28
    t
    0.27
    TI
    0.27
    Act Density 0.481%

    No Known Activations