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

    Neuronpedia

    INDEX
    Explanations

    high-quality items or attributes

    oai_token-act-pair · gpt-3.5-turbo

    references to high-quality products or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shy
    -0.74
     fore
    -0.69
     gang
    -0.65
     apprehens
    -0.64
     asc
    -0.63
     pen
    -0.61
     Hyper
    -0.61
     orally
    -0.60
     circles
    -0.60
     initi
    -0.60
    POSITIVE LOGITS
    quality
    4.06
    Quality
    2.24
     quality
    2.06
     Quality
    1.81
    grade
    1.51
    equality
    1.38
    fficiency
    1.35
    qual
    1.35
    caliber
    1.32
    performance
    1.24
    Act Density 0.010%

    No Known Activations