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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions that indicate superiority, inferiority, or differences between subjects or parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comparison, using "than"

    np_acts-logits-general · gemini-2.0-flash

    comparisons using than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    openqa
    -0.46
     boj
    -0.45
    門
    -0.44
     caddy
    -0.44
     Phry
    -0.44
    testng
    -0.44
     Ory
    -0.43
     Manly
    -0.43
    chy
    -0.43
    iffy
    -0.43
    POSITIVE LOGITS
     AssemblyTitle
    0.94
     those
    0.90
     saites
    0.80
     decât
    0.79
    XmlAccessorType
    0.77
     than
    0.76
     AssemblyCompany
    0.76
    those
    0.72
     سایر
    0.69
    didSet
    0.68
    Act Density 0.375%

    No Known Activations