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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various topics or concepts across different domains

    oai_token-act-pair · gpt-3.5-turbo

    empty tokens or non-content, placeholder elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Azerb
    -0.05
    elsius
    -0.04
    Þ
    -0.04
     guiActiveUn
    -0.04
    oÄŁ
    -0.04
    ñ
    -0.04
    ij士
    -0.04
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.03
    qqa
    -0.03
    ļéĨĴ
    -0.03
    POSITIVE LOGITS
    ↵
    0.05
    ,
    0.05
     the
    0.05
     and
    0.05
    .
    0.05
    -
    0.05
    The
    0.05
     in
    0.04
     to
    0.04
     of
    0.04
    Act Density 3.396%

    No Known Activations