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

    Neuronpedia

    INDEX
    Explanations

    specific pieces of information in documents, such as fact sheets, reports, and statements

    oai_token-act-pair · gpt-3.5-turbo

    references to formal documents or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Osw
    -0.74
    owler
    -0.69
    cffff
    -0.68
     boo
    -0.65
    population
    -0.63
     antagon
    -0.63
    zech
    -0.63
     prox
    -0.61
    ooth
    -0.61
    pload
    -0.60
    POSITIVE LOGITS
     outlining
    0.89
     detailing
    0.85
     summarizes
    0.83
    velop
    0.83
    isode
    0.82
     titled
    0.81
    Frag
    0.76
     entitled
    0.76
     outlines
    0.76
     memorandum
    0.75
    Act Density 0.284%

    No Known Activations