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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the need for citations or additional sources of information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "citation" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olen
    -0.92
    antle
    -0.71
    chest
    -0.67
    ther
    -0.64
    tails
    -0.63
    rame
    -0.63
    oshenko
    -0.62
     saline
    -0.62
    oop
    -0.62
    tackle
    -0.61
    POSITIVE LOGITS
    itation
    0.87
     citation
    0.84
     Citation
    0.83
    itations
    0.78
     footnote
    0.76
     quotes
    0.75
     Publication
    0.74
     citations
    0.74
    =]
    0.72
    ...]
    0.71
    Act Density 0.024%

    No Known Activations