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

    Neuronpedia

    INDEX
    Explanations

    information or sections continuing an article below a certain point

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating continuation or sections of articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reb
    -0.72
    RAW
    -0.70
     Rebellion
    -0.63
    rament
    -0.62
     Noir
    -0.60
     mosqu
    -0.59
    shapeshifter
    -0.58
    romy
    -0.58
     reneg
    -0.57
    bucks
    -0.56
    POSITIVE LOGITS
     Below
    0.75
    idth
    0.68
    ached
    0.65
    prev
    0.65
     Sort
    0.64
     Loading
    0.63
     Thumbnails
    0.60
    etitive
    0.60
     Close
    0.59
    Sort
    0.59
    Act Density 0.012%

    No Known Activations