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

    Neuronpedia

    INDEX
    Explanations

    terms related to inclusivity and its importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coon
    -0.77
    çek
    -0.64
    乓
    -0.64
    nete
    -0.63
     Noth
    -0.62
    dataSet
    -0.61
     MotionEvent
    -0.59
    EXP
    -0.59
     relever
    -0.58
     Stepan
    -0.58
    POSITIVE LOGITS
     inclusive
    1.32
     clarification
    1.17
    Inclusive
    1.14
     Inclusive
    1.13
    inclusive
    1.11
     clarify
    1.07
     clarified
    1.00
     clarifying
    1.00
     clarity
    0.97
    clar
    0.91
    Act Density 0.065%

    No Known Activations