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

    Neuronpedia

    INDEX
    Explanations

    entries that contain specific strings of characters, which may be related to locations or names

    oai_token-act-pair · gpt-3.5-turbo

    specific lowercase or capitalized letters consistently appearing in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     terminal
    -0.62
     paraly
    -0.60
    Answer
    -0.58
     resent
    -0.55
     thereto
    -0.54
     machine
    -0.54
     visually
    -0.53
     discounted
    -0.53
     deception
    -0.52
     dracon
    -0.52
    POSITIVE LOGITS
    rost
    1.21
    iltration
    1.12
    ornia
    1.12
    ication
    1.10
    estival
    1.10
    ellow
    1.10
    ritz
    1.09
    ruits
    1.09
    ilipp
    1.08
    isher
    1.06
    Act Density 0.039%

    No Known Activations