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

    Neuronpedia

    INDEX
    Explanations

    activities that people can choose to do in their leisure time

    oai_token-act-pair · gpt-3.5-turbo

    activities relating to leisure and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĢħ
    -0.77
     confirmation
    -0.75
     Outbreak
    -0.69
    ©¶æ¥µ
    -0.69
    Tier
    -0.67
    oppable
    -0.66
     Ambro
    -0.66
     definitive
    -0.66
     conclusive
    -0.65
    ãĤ¦ãĤ¹
    -0.65
    POSITIVE LOGITS
     eat
    1.44
     drink
    1.31
     cook
    1.18
     drank
    1.17
     gamble
    1.16
     partake
    1.16
     pray
    1.12
     ate
    1.12
     swim
    1.09
     sleep
    1.07
    Act Density 0.311%

    No Known Activations