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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons and statistical data related to variations and measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     виправивши
    -0.90
     propOrder
    -0.79
     MainAxisSize
    -0.76
    IVEREF
    -0.75
    MessageOf
    -0.72
    EDEFAULT
    -0.71
    χρι
    -0.71
    évaluateur
    -0.71
     المعيارى
    -0.71
     beginnetje
    -0.70
    POSITIVE LOGITS
     mesmas
    0.45
    .
    0.43
    Likewise
    0.42
     same
    0.42
     sna
    0.41
    こちらも
    0.41
     mismas
    0.40
     mismo
    0.40
    ↵↵
    0.39
     misma
    0.39
    Act Density 0.141%

    No Known Activations