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

    Neuronpedia

    INDEX
    Explanations

    words related to explanations and descriptions of processes or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rette
    -0.15
    flare
    -0.15
    ÑĦи
    -0.14
    kel
    -0.14
    pcs
    -0.14
    Ãłng
    -0.14
    PCS
    -0.14
    θε
    -0.14
    Snippet
    -0.14
     provision
    -0.13
    POSITIVE LOGITS
     elsewhere
    0.14
    ymb
    0.14
    ENO
    0.14
     Roe
    0.14
    .setUp
    0.14
    ERING
    0.14
     araç
    0.14
    oro
    0.14
    ëŁ
    0.14
    276
    0.14
    Act Density 0.123%

    No Known Activations