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

    Neuronpedia

    INDEX
    Explanations

    references to web navigation or page structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vell
    -0.16
    uat
    -0.16
    aden
    -0.15
    हर
    -0.15
    loit
    -0.14
    ,eg
    -0.14
     Burst
    -0.14
    QA
    -0.14
    .Payload
    -0.13
    égor
    -0.13
    POSITIVE LOGITS
    igan
    0.19
    ahun
    0.17
    struk
    0.15
     Kane
    0.15
    rgan
    0.14
    oster
    0.14
    æĪ
    0.14
    ifetime
    0.14
    itan
    0.14
    istory
    0.14
    Act Density 0.001%

    No Known Activations