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

    Neuronpedia

    INDEX
    Explanations

    acronyms or initialisms related to organizations or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsi
    -0.20
    wap
    -0.19
    erialize
    -0.16
    OPY
    -0.16
    oster
    -0.15
    gger
    -0.15
    oles
    -0.15
    elf
    -0.15
    ël
    -0.14
     αÏĥÏĦ
    -0.14
    POSITIVE LOGITS
    rollo
    0.19
    rena
    0.17
    utom
    0.17
    IRO
    0.17
    bones
    0.15
    ngen
    0.15
    pecially
    0.14
    aan
    0.14
    riel
    0.14
    æł¼
    0.14
    Act Density 0.015%

    No Known Activations