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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" frequently, indicating a focus on conjunctions and connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oof
    -0.66
     Mechdragon
    -0.64
    merga
    -0.62
    pmwiki
    -0.62
    CHAT
    -0.62
    ellig
    -0.61
    lux
    -0.61
    urd
    -0.59
    eeds
    -0.59
    ied
    -0.59
    POSITIVE LOGITS
     thus
    0.91
     hopefully
    0.91
    uin
    0.87
     therefore
    0.87
     consequently
    0.86
    romeda
    0.85
     hence
    0.80
     congr
    0.78
     furthermore
    0.77
     congratulations
    0.76
    Act Density 0.323%

    No Known Activations