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

    Neuronpedia

    INDEX
    Explanations

    key concepts and themes related to choice and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ishes
    -0.16
     glob
    -0.15
    ottle
    -0.14
    asil
    -0.14
    elda
    -0.14
    irsch
    -0.14
     except
    -0.14
    егоÑĢ
    -0.13
    wards
    -0.13
    lets
    -0.13
    POSITIVE LOGITS
    RIPT
    0.16
    ì¹ĺëĬĶ
    0.16
    iest
    0.16
    rani
    0.15
    edb
    0.15
    δα
    0.15
    lamaz
    0.15
     SPE
    0.14
    RIX
    0.14
    [js
    0.14
    Act Density 0.265%

    No Known Activations