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

    Neuronpedia

    INDEX
    Explanations

    instances of non-standard or ambiguous formatting and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orte
    -0.17
    ula
    -0.15
    thon
    -0.15
    acin
    -0.15
    ries
    -0.15
    istrat
    -0.14
    庫
    -0.14
    efined
    -0.14
    ela
    -0.14
    137
    -0.14
    POSITIVE LOGITS
    .Abstract
    0.16
    licate
    0.15
    jvu
    0.15
    atürk
    0.14
     olsun
    0.14
    Ïħκ
    0.14
    AGMA
    0.14
    789
    0.14
    ä¹İ
    0.14
    enk
    0.14
    Act Density 0.045%

    No Known Activations