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

    Neuronpedia

    INDEX
    Explanations

    references to additional studies or further reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.46
     createSprite
    -0.43
    Composable
    -0.40
    osť
    -0.39
    styleType
    -0.39
    wußt
    -0.38
    AndView
    -0.37
    ్రామ
    -0.37
    ronpa
    -0.37
    RefNanny
    -0.36
    POSITIVE LOGITS
     afield
    1.02
    emore
    0.60
    MORE
    0.60
     elaboration
    0.59
     ado
    0.59
     investigation
    0.56
     refinement
    0.52
     refine
    0.51
     arşivlendi
    0.51
    entiation
    0.51
    Act Density 0.126%

    No Known Activations