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

    Neuronpedia

    INDEX
    Explanations

    quotations within sentences

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or dialogue in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.93
    ãĥij
    -0.69
    »Ĵ
    -0.66
    £ı
    -0.65
    anuts
    -0.64
     persecut
    -0.64
     mete
    -0.64
    successfully
    -0.63
    ĪĴ
    -0.62
    ardless
    -0.62
    POSITIVE LOGITS
     says
    1.11
     said
    1.11
    said
    1.07
     recalls
    0.95
     recalled
    0.93
     joked
    0.90
     commented
    0.90
     reads
    0.89
     explained
    0.88
     explains
    0.88
    Act Density 0.085%

    No Known Activations