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

    Neuronpedia

    INDEX
    Explanations

    short phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adjud
    -0.77
     dye
    -0.70
     overl
    -0.69
     depot
    -0.69
     enrol
    -0.68
     dyed
    -0.66
     footing
    -0.65
     cram
    -0.65
     assign
    -0.64
     hub
    -0.64
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    1.44
    Hey
    1.14
    We
    1.11
    Our
    1.04
    I
    1.02
    Faith
    1.02
    Sorry
    1.00
    Everything
    1.00
    quickShipAvailable
    1.00
    Jesus
    0.99
    Act Density 0.106%

    No Known Activations