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

    Neuronpedia

    INDEX
    Explanations

    expressions related to enjoyment and fun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding intensifiers of positive experiences

    np_acts-logits-general · gemini-2.0-flash

    fun and enjoyment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كومونز
    -0.75
     betweenstory
    -0.62
    AfterClass
    -0.59
    GHIJKLM
    -0.59
     kohta
    -0.55
    protoimpl
    -0.53
     quizá
    -0.51
     Normdatei
    -0.50
    PrivateRoute
    -0.49
    hadur
    -0.48
    POSITIVE LOGITS
     fun
    2.63
    fun
    2.17
     enjoyment
    2.07
    Fun
    2.02
     enjoyable
    2.01
     Fun
    2.00
     FUN
    2.00
     divertido
    1.78
    FUN
    1.76
     pleasure
    1.73
    Act Density 0.311%

    No Known Activations