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

    Neuronpedia

    INDEX
    Explanations

    concepts related to knowledge and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ross
    -0.15
    ello
    -0.15
    ero
    -0.15
     pert
    -0.15
    oler
    -0.14
    -turned
    -0.14
    ulant
    -0.14
    imenti
    -0.14
    acebook
    -0.14
    \<^
    -0.14
    POSITIVE LOGITS
    .microsoft
    0.19
    fulness
    0.17
    zia
    0.16
    ably
    0.16
    fully
    0.16
    heits
    0.16
     Lau
    0.15
     base
    0.15
     about
    0.15
    -base
    0.15
    Act Density 0.049%

    No Known Activations