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

    Neuronpedia

    INDEX
    Explanations

    configurations and options in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dre
    -0.18
     Elias
    -0.17
    sWith
    -0.16
    RLF
    -0.15
    SD
    -0.15
    ynam
    -0.14
    ationale
    -0.14
    uko
    -0.14
    .sd
    -0.14
    urgeon
    -0.13
    POSITIVE LOGITS
    unsafe
    0.15
    eld
    0.14
    \OptionsResolver
    0.14
    å¤ķ
    0.14
    anst
    0.14
    à¸Ĭม
    0.14
    ople
    0.14
    jez
    0.14
    iggins
    0.13
    ___↵↵
    0.13
    Act Density 0.129%

    No Known Activations