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

    Neuronpedia

    INDEX
    Explanations

    references to social roles and structures within communities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Direction
    -0.16
     upside
    -0.15
     fewer
    -0.15
     doby
    -0.15
     пÑĢид
    -0.15
    Away
    -0.14
    Upper
    -0.14
     Upper
    -0.14
    reater
    -0.14
     inverted
    -0.14
    POSITIVE LOGITS
     right
    0.54
     up
    0.45
    right
    0.40
     RIGHT
    0.39
     down
    0.36
     all
    0.35
     Right
    0.35
    .right
    0.34
    -right
    0.33
    Right
    0.33
    Act Density 0.212%

    No Known Activations