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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicating one thing is of a higher degree or level than another

    oai_token-act-pair · gpt-3.5-turbo

    comparative statements indicating an increase or emphasis on certain characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.78
    etimes
    -0.74
    æ©
    -0.73
    pex
    -0.73
    heid
    -0.70
    atan
    -0.68
    DragonMagazine
    -0.68
    ovies
    -0.67
    OCK
    -0.65
    comings
    -0.65
    POSITIVE LOGITS
     than
    1.34
     efficient
    1.08
     accurate
    1.03
     complicated
    1.01
     likely
    1.00
     expensive
    0.98
     inclined
    0.96
     important
    0.96
     stringent
    0.94
     sophisticated
    0.94
    Act Density 0.110%

    No Known Activations