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

    Neuronpedia

    INDEX
    Explanations

    references to research and validation in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ienda
    -0.16
     Ins
    -0.16
     re
    -0.15
     cob
    -0.15
    izo
    -0.15
     attracts
    -0.15
    vant
    -0.14
     reportedly
    -0.14
    Äħ
    -0.14
     bypass
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.17
    achat
    0.16
    ucht
    0.15
    oren
    0.15
    ctest
    0.15
    enderit
    0.15
    íĨ¡
    0.15
    rnek
    0.15
    arkin
    0.14
    caler
    0.14
    Act Density 1.321%

    No Known Activations