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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atural
    -0.17
    typeorm
    -0.16
    ogany
    -0.15
    scala
    -0.14
    formula
    -0.14
    ë§Ŀ
    -0.14
    043
    -0.14
     Sour
    -0.13
     quant
    -0.13
     burst
    -0.13
    POSITIVE LOGITS
     tolerance
    0.23
     toler
    0.22
    tol
    0.22
     tol
    0.20
     precision
    0.19
    _tolerance
    0.18
     accuracy
    0.17
    (tol
    0.17
     Accuracy
    0.17
     Precision
    0.17
    Act Density 0.043%

    No Known Activations