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

    Neuronpedia

    INDEX
    Explanations

    terms relating to broad concepts and societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sst
    -0.17
     resil
    -0.16
    sock
    -0.15
    ker
    -0.15
    obi
    -0.15
    .FLAG
    -0.14
    ÑĨÑİ
    -0.14
    eln
    -0.13
    ILLISE
    -0.13
    ilst
    -0.13
    POSITIVE LOGITS
    anging
    0.18
    winner
    0.15
    rawler
    0.14
    toa
    0.14
    igham
    0.14
    ENDER
    0.14
     à¹Ĩ
    0.13
    regon
    0.13
    ioc
    0.13
    ding
    0.13
    Act Density 0.027%

    No Known Activations