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

    Neuronpedia

    INDEX
    Explanations

    expressions of enjoyment or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ssil
    -0.56
    Idade
    -0.55
    ReusableCell
    -0.51
    Bae
    -0.50
    initState
    -0.49
     Manchester
    -0.49
    ########.
    -0.48
    PMailer
    -0.48
    κε
    -0.48
    breakpoints
    -0.47
    POSITIVE LOGITS
     enjoy
    3.71
     enjoyed
    3.60
    enjoy
    3.53
     Enjoy
    3.41
     enjoying
    3.38
     ENJOY
    3.20
    Enjoy
    3.15
     enjoys
    3.09
     enjoyment
    2.79
    ENJOY
    2.64
    Act Density 0.072%

    No Known Activations