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

    Neuronpedia

    INDEX
    Explanations

    references to leisure activities or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     natural
    -0.15
    oks
    -0.15
    unn
    -0.15
    aska
    -0.14
    ars
    -0.14
    tring
    -0.14
     rep
    -0.14
    -bre
    -0.14
    oku
    -0.14
    agen
    -0.13
    POSITIVE LOGITS
    pcf
    0.18
    cken
    0.17
    itere
    0.17
    iros
    0.16
    stor
    0.16
    Sharper
    0.15
    cimal
    0.15
    erer
    0.15
    ately
    0.15
    _exempt
    0.14
    Act Density 0.001%

    No Known Activations