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

    quotations or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adjud
    -0.78
     administrator
    -0.67
     reconcil
    -0.66
     overl
    -0.66
     footing
    -0.66
     enrol
    -0.66
     hub
    -0.66
     dyed
    -0.65
     depot
    -0.65
     seasoned
    -0.65
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    1.29
    Hey
    1.16
    We
    1.14
    Our
    1.10
    Dear
    1.08
    I
    1.07
    Hello
    1.05
    Everybody
    1.03
    They
    1.03
    Hi
    1.03
    Act Density 0.087%

    No Known Activations