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

    Neuronpedia

    INDEX
    Explanations

    phrases related to composition and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åľŃ
    -0.17
    ipherals
    -0.16
    bsp
    -0.15
    iges
    -0.15
    istrovstvÃŃ
    -0.15
    inspace
    -0.15
    елÑı
    -0.15
    ienes
    -0.14
     Witnesses
    -0.14
    chez
    -0.14
    POSITIVE LOGITS
     elements
    0.23
     components
    0.22
     fewer
    0.20
     two
    0.19
     mix
    0.19
     parts
    0.18
     component
    0.17
     Components
    0.17
     element
    0.16
     members
    0.16
    Act Density 0.078%

    No Known Activations