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

    Neuronpedia

    INDEX
    Explanations

    the word "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iences
    -1.71
    avour
    -1.60
    ably
    -1.55
     (\<
    -1.55
    abl
    -1.48
    able
    -1.47
    )\].
    -1.47
     roles
    -1.46
    )\]
    -1.44
    quer
    -1.42
    POSITIVE LOGITS
     ↵
    2.23
    <|outofrange|>
    2.23
    ↵↵↵
    2.23
    ↵
    2.23
    2.23
    <|outofrange|>
    2.23
    ↵
    2.23
              ↵
    2.23
    ↵
    2.23
    2.23
    Act Density 0.285%

    No Known Activations