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

    Neuronpedia

    INDEX
    Explanations

    terms related to perception and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brook
    -0.17
    à¸ĩาà¸Ļ
    -0.17
    erman
    -0.16
    icked
    -0.16
    ics
    -0.16
    ãĥ¼ãĤº
    -0.15
    oca
    -0.15
    aylight
    -0.14
    åIJĪãĤıãģĽ
    -0.14
    weit
    -0.14
    POSITIVE LOGITS
    ately
    0.20
    inal
    0.18
    داشت
    0.16
    lation
    0.16
    edly
    0.16
    ship
    0.16
     ìĤ¬íķŃ
    0.16
    SSION
    0.15
    aten
    0.15
    ships
    0.15
    Act Density 0.017%

    No Known Activations