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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to people or entities involved in actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    적으로
    -0.52
    Ờ
    -0.43
     życiu
    -0.43
    uny
    -0.42
     vian
    -0.42
     okazji
    -0.42
    isEqual
    -0.42
    jména
    -0.42
     ural
    -0.41
    적인
    -0.41
    POSITIVE LOGITS
    InjectAttribute
    1.08
     ostavi
    1.05
    лтемелер
    1.00
    __':
    0.99
    verwijspagina
    0.99
     nakalista
    0.98
    Diwedd
    0.91
    UnsafeEnabled
    0.91
    UnknownFieldSet
    0.89
     gynnwys
    0.87
    Act Density 0.613%

    No Known Activations