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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal structures and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.72
    OGND
    -0.69
    SharedDtor
    -0.68
    MLLoader
    -0.68
    rungsseite
    -0.65
     للاسماء
    -0.65
    ⤹
    -0.65
     NSCoder
    -0.65
    SourceChecksum
    -0.62
    ьаж
    -0.62
    POSITIVE LOGITS
     gezondheid
    0.32
     kracht
    0.32
     hoogte
    0.31
    ientí
    0.31
     alongside
    0.30
     unnoticed
    0.30
     uomini
    0.29
     gedeelte
    0.28
     történ
    0.28
     někdo
    0.28
    Act Density 0.984%

    No Known Activations