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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize correctness or appropriateness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¸ķรว
    -0.15
    ouz
    -0.15
    .scalablytyped
    -0.14
    ÙĪرش
    -0.14
    ingleton
    -0.14
    LEASE
    -0.14
    raman
    -0.14
    æĹıèĩªæ²»
    -0.14
    ayet
    -0.14
    merc
    -0.14
    POSITIVE LOGITS
    508
    0.16
    s
    0.14
    511
    0.14
     XO
    0.14
    erten
    0.14
    ringe
    0.14
     imagin
    0.14
    ugs
    0.14
    iero
    0.13
    2
    0.13
    Act Density 0.130%

    No Known Activations