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

    Neuronpedia

    INDEX
    Explanations

    articles (such as "the" and "an") followed by specific words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     besides
    -0.63
    ibl
    -0.62
    !!!
    -0.58
    ???
    -0.58
     resided
    -0.57
    !.
    -0.57
    aji
    -0.57
     reminis
    -0.57
     distinguishes
    -0.57
    itars
    -0.56
    POSITIVE LOGITS
     nation
    0.99
     same
    0.96
     latter
    0.96
     country
    0.95
     Kremlin
    0.90
     United
    0.89
     latest
    0.89
     Clintons
    0.86
     Philippines
    0.85
     aftermath
    0.84
    Act Density 0.989%

    No Known Activations