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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enjoyment and pleasure

    oai_token-act-pair · gpt-3.5-turbo

    references to enjoying various activities and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ural
    -0.74
    pled
    -0.65
    raft
    -0.64
     dare
    -0.64
    ene
    -0.64
    ethical
    -0.61
    agnetic
    -0.61
     scrimmage
    -0.61
     carriers
    -0.60
    ©¶æ
    -0.59
    POSITIVE LOGITS
    nels
    0.87
    ably
    0.86
    joy
    0.85
     enjoys
    0.84
    lihood
    0.84
     enjoyment
    0.80
    ĸļ
    0.79
     enjoyed
    0.79
     enjoying
    0.78
    quished
    0.77
    Act Density 0.031%

    No Known Activations