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

    Neuronpedia

    INDEX
    Explanations

    instances where importance or necessity is emphasized

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uter
    -0.17
    anship
    -0.15
    itas
    -0.15
    dp
    -0.15
    ason
    -0.14
    ci
    -0.14
     Perr
    -0.14
    kara
    -0.14
    cin
    -0.14
    ı
    -0.13
    POSITIVE LOGITS
    antly
    0.16
    sled
    0.15
    _marshall
    0.15
    /INFO
    0.15
    å°¾
    0.14
    IGHL
    0.14
    etimes
    0.14
    _bullet
    0.14
    untu
    0.13
    abit
    0.13
    Act Density 0.117%

    No Known Activations