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

    Neuronpedia

    INDEX
    Explanations

    terms related to differences and comparisons in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    หวัด
    -0.61
    ట
    -0.54
    兵器
    -0.51
    колеп
    -0.51
     Rouse
    -0.49
    vestres
    -0.49
    >>>
    -0.47
    roskop
    -0.47
    >*/
    -0.47
     */
    -0.47
    POSITIVE LOGITS
     difference
    2.96
     differences
    2.90
     Differences
    2.73
    difference
    2.70
     Difference
    2.66
    Differences
    2.61
    Difference
    2.58
    differences
    2.57
     DIFFERENCE
    2.45
     différences
    2.32
    Act Density 0.163%

    No Known Activations