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

    Neuronpedia

    INDEX
    Explanations

    words related to reports or official documents

    oai_token-act-pair · gpt-3.5-turbo

    references to formal or official reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    east
    -0.71
     vow
    -0.65
    conservancy
    -0.64
     mortar
    -0.63
     idol
    -0.60
     Denis
    -0.59
     bene
    -0.58
     hypert
    -0.58
     gate
    -0.56
     gratification
    -0.56
    POSITIVE LOGITS
    velop
    0.94
    orial
    0.88
     titled
    0.86
     commissioned
    0.79
     detailing
    0.79
     compiled
    0.79
    Crash
    0.79
    report
    0.78
    books
    0.77
     documenting
    0.75
    Act Density 0.063%

    No Known Activations