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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms related to organizations or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REFERRED
    -0.17
    ëŁī
    -0.16
    dsn
    -0.16
    ADDE
    -0.14
     McCart
    -0.14
    caff
    -0.14
    ħn
    -0.14
    nosis
    -0.13
    ERSIST
    -0.13
    ilden
    -0.13
    POSITIVE LOGITS
     [=
    0.15
     [
    0.14
     nic
    0.14
    rav
    0.14
    o
    0.14
     Luk
    0.13
     grat
    0.13
     Je
    0.13
    .me
    0.13
     shed
    0.13
    Act Density 0.166%

    No Known Activations