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

    Neuronpedia

    INDEX
    Explanations

    verbs related to progression or change

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "take" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bey
    -0.79
    enegger
    -0.79
    rehens
    -0.73
    idated
    -0.70
    76561
    -0.68
    tch
    -0.67
    tu
    -0.65
    psey
    -0.64
    zx
    -0.63
    mini
    -0.63
    POSITIVE LOGITS
     precedence
    1.34
     shape
    1.17
     hold
    1.09
     root
    1.08
     center
    0.91
     Shape
    0.86
     centre
    0.85
     place
    0.82
     priority
    0.80
     precedent
    0.80
    Act Density 0.057%

    No Known Activations