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

    Neuronpedia

    INDEX
    Explanations

    repeated expressions or phrases in a non-English language, possibly focusing on emotional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑĢÑĤ
    -0.15
    ä¿Ĥ
    -0.14
    antan
    -0.14
    üstü
    -0.14
    andro
    -0.14
    #Region
    -0.14
    ůl
    -0.14
    Unused
    -0.14
    {@
    -0.14
    ulkan
    -0.13
    POSITIVE LOGITS
    683
    0.16
    kin
    0.16
    hod
    0.16
    neh
    0.15
    osta
    0.15
    546
    0.15
    aar
    0.15
    iston
    0.14
    loy
    0.14
    iste
    0.14
    Act Density 0.004%

    No Known Activations