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

    Neuronpedia

    INDEX
    Explanations

    pronouns and phrases expressing personal experience or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĤ«ãĥ¼
    -0.18
    iland
    -0.15
    ilion
    -0.15
    .scalablytyped
    -0.15
    veloper
    -0.15
    اذا
    -0.14
    WND
    -0.14
    riad
    -0.14
    >[]
    -0.14
    ิว
    -0.14
    POSITIVE LOGITS
     despite
    0.23
     finally
    0.20
     although
    0.20
     besides
    0.18
     final
    0.18
     Finally
    0.17
     aside
    0.17
    finally
    0.17
     after
    0.17
     while
    0.17
    Act Density 0.008%

    No Known Activations