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

    Neuronpedia

    INDEX
    Explanations

    mentions of awards or achievements

    oai_token-act-pair · gpt-3.5-turbo

    winning related nouns and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     counselors
    -1.07
     resorts
    -1.06
     DJs
    -1.05
     chefs
    -1.03
     stadiums
    -1.02
     kitchens
    -1.02
     casinos
    -1.00
     lenders
    -1.00
     warehouses
    -1.00
     instructors
    -0.99
    POSITIVE LOGITS
     version
    1.09
     variant
    1.00
     replica
    0.91
     incarnation
    0.90
     prototype
    0.85
     copy
    0.82
     counterpart
    0.82
     specimen
    0.81
     iteration
    0.80
     example
    0.80
    Act Density 0.674%

    No Known Activations