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

    Neuronpedia

    INDEX
    Explanations

    references to inclusivity or the concept of "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Compat
    -0.06
    ndern
    -0.06
    okit
    -0.06
    ãĥ¼ãĤ¹ãĥĪ
    -0.06
    oz
    -0.06
     [âĢ¦]↵↵
    -0.06
    :description
    -0.06
     jew
    -0.06
    .ast
    -0.06
    alleries
    -0.06
    POSITIVE LOGITS
     things
    0.30
     everything
    0.25
     Things
    0.24
    Things
    0.23
     anything
    0.22
    things
    0.22
     thing
    0.22
    everything
    0.21
    anything
    0.19
     Everything
    0.19
    Act Density 0.024%

    No Known Activations