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

    Neuronpedia

    INDEX
    Explanations

    textual separators like periods, commas, and symbols

    oai_token-act-pair · gpt-3.5-turbo

    references to sports statistics and player performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     frontline
    -0.86
     speeding
    -0.84
     spir
    -0.84
    ensical
    -0.82
     weaving
    -0.80
     carving
    -0.78
     reluct
    -0.77
     spitting
    -0.77
    etheless
    -0.75
     racing
    -0.75
    POSITIVE LOGITS
    Rated
    1.57
    RAW
    1.54
    Advertisement
    1.45
    Article
    1.42
    Loading
    1.42
    Advertisements
    1.41
    Topic
    1.39
    Posted
    1.38
    Topics
    1.38
    Trivia
    1.36
    Act Density 0.430%

    No Known Activations