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

    Neuronpedia

    INDEX
    Explanations

    mentions of the importance or impact of events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive sentiment or enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oulos
    -0.59
     Adin
    -0.54
    bestos
    -0.54
     Kaplan
    -0.50
     Madd
    -0.49
     Sutton
    -0.49
     meanwhile
    -0.49
     postwar
    -0.48
     Whitman
    -0.48
     moreover
    -0.48
    POSITIVE LOGITS
     alot
    0.89
     ;)
    0.73
     haha
    0.69
     :)
    0.67
     crap
    0.67
     shit
    0.66
     dont
    0.65
     :(
    0.64
     pic
    0.64
     gonna
    0.63
    Act Density 2.133%

    No Known Activations