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

    Neuronpedia

    INDEX
    Explanations

    references to the novelty or significance of scientific findings or methods

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    lical
    -0.56
     tails
    -0.54
     polarity
    -0.54
     área
    -0.53
    asilan
    -0.52
     retribu
    -0.52
     préc
    -0.52
    cusa
    -0.50
    GeneratedCode
    -0.50
    tymologie
    -0.49
    POSITIVE LOGITS
     maturity
    2.19
     Maturity
    1.84
    maturity
    1.71
     novelty
    0.87
     curfew
    0.72
     Italijani
    0.68
    TintMode
    0.68
    jit
    0.66
     ExecuteAsync
    0.66
    bukkit
    0.64
    Act Density 0.005%

    No Known Activations