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

    Neuronpedia

    INDEX
    Explanations

    references to various types of rooms and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arter
    -0.17
     nowhere
    -0.16
     addCriterion
    -0.14
    eyse
    -0.14
    ноÑģи
    -0.14
    ghi
    -0.13
    //{{
    -0.13
    å¤
    -0.13
    camp
    -0.13
     Russ
    -0.13
    POSITIVE LOGITS
    ablo
    0.18
     containing
    0.17
     room
    0.17
     area
    0.16
    builtin
    0.15
    lik
    0.15
     partition
    0.15
    ewed
    0.14
    bilt
    0.14
    ÙĬز
    0.14
    Act Density 0.219%

    No Known Activations