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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to organizations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dor
    -0.22
     ad
    -0.21
    dba
    -0.19
     dod
    -0.18
     dint
    -0.18
     dol
    -0.18
    adal
    -0.17
     Id
    -0.17
    eded
    -0.17
    -ad
    -0.17
    POSITIVE LOGITS
    DD
    0.35
    DED
    0.34
    BD
    0.34
    SD
    0.34
    DTD
    0.33
    KD
    0.33
    HD
    0.32
    TD
    0.31
    Ｄ
    0.30
    DST
    0.30
    Act Density 0.064%

    No Known Activations