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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enjoyment and positive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ine
    -0.75
    B
    -0.65
    Al
    -0.64
     B
    -0.63
    الت
    -0.63
    Le
    -0.63
     Al
    -0.60
    les
    -0.60
    Het
    -0.59
    um
    -0.59
    POSITIVE LOGITS
    enjoy
    1.54
     enjoyment
    1.53
     Enjoy
    1.41
     ENJOY
    1.39
     enjoy
    1.35
     enjoyed
    1.35
    Enjoying
    1.32
     pleaſure
    1.31
    Enjoyed
    1.28
    ENJOY
    1.27
    Act Density 0.040%

    No Known Activations