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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or use of specific information or instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in the" occurring frequently in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lasted
    -0.79
    hov
    -0.69
    0000000000000000
    -0.66
    SPONSORED
    -0.64
    ugu
    -0.63
     sincerely
    -0.63
    olit
    -0.60
     unless
    -0.60
     expires
    -0.60
     alas
    -0.59
    POSITIVE LOGITS
     Appendix
    0.95
     Chapter
    0.88
     Table
    0.87
     Exhibit
    0.85
     Figures
    0.84
     Annex
    0.84
     relation
    0.83
     Figure
    0.81
     Section
    0.81
     accordance
    0.81
    Act Density 0.108%

    No Known Activations