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

    Neuronpedia

    INDEX
    Explanations

    references to dignity and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricular
    -0.18
    tes
    -0.18
    tings
    -0.17
    ertools
    -0.17
    ricula
    -0.17
    ting
    -0.17
    stroy
    -0.17
    ters
    -0.15
    uction
    -0.15
    ropol
    -0.15
    POSITIVE LOGITS
    ified
    0.39
    itary
    0.33
    ifying
    0.29
    it
    0.26
    ity
    0.26
    ify
    0.25
     dign
    0.23
    IFIED
    0.23
    atories
    0.23
    ifies
    0.22
    Act Density 0.009%

    No Known Activations