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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and related personal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.49
    :✨
    -0.48
    Портали
    -0.47
     ExecuteAsync
    -0.43
     дописавши
    -0.42
    LookAnd
    -0.42
    лтемелер
    -0.42
     ویکی‌پدی
    -0.41
     tartalomajánló
    -0.40
     saites
    -0.40
    POSITIVE LOGITS
    MLLoader
    0.42
    ckså
    0.42
     skjø
    0.40
     veroor
    0.39
    蚪
    0.39
     wonder
    0.39
    spotted
    0.38
     thought
    0.38
     wanted
    0.37
     undersø
    0.37
    Act Density 0.132%

    No Known Activations