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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific concepts and terms

    oai_token-act-pair · gpt-3.5-turbo

    references to types of proteins, particularly ones that end with "ines"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GoldMagikarp
    -0.75
    board
    -0.71
     Falk
    -0.70
    erton
    -0.68
    talk
    -0.68
    rave
    -0.64
    sie
    -0.64
    roller
    -0.63
    atever
    -0.63
    rollers
    -0.63
    POSITIVE LOGITS
    hift
    1.27
    poons
    1.23
    pace
    1.21
    cale
    1.15
    pring
    1.14
    cence
    1.14
    aurus
    1.13
    peed
    1.10
    cript
    1.08
    pect
    1.05
    Act Density 0.058%

    No Known Activations