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

    Neuronpedia

    INDEX
    Explanations

    numerical values indicating some form of a record or milestone being set

    oai_token-act-pair · gpt-3.5-turbo

    references to record-breaking achievements or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lez
    -0.77
    atown
    -0.75
    east
    -0.75
    imaru
    -0.72
    west
    -0.72
    ranch
    -0.71
     Matters
    -0.67
    ç
    -0.66
    quest
    -0.66
    afer
    -0.65
    POSITIVE LOGITS
     consecutive
    0.80
     recorded
    0.79
     rainfall
    0.76
     viewership
    0.71
     unbeliev
    0.68
     wiret
    0.67
    644
    0.65
     FIR
    0.65
     MPG
    0.65
     accomplishment
    0.63
    Act Density 0.146%

    No Known Activations