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

    Neuronpedia

    INDEX
    Explanations

    comparisons with a specific item or concept identified by the phrase "the [item/concept]."

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" with varying frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     besides
    -0.79
     Became
    -0.77
    abel
    -0.70
     flanked
    -0.70
    ãĥ»
    -0.69
    iband
    -0.67
    amar
    -0.67
     followed
    -0.66
    fw
    -0.66
    rand
    -0.65
    POSITIVE LOGITS
     rest
    1.34
     usual
    1.23
     slightest
    1.14
     aforementioned
    1.13
     entirety
    1.12
     remainder
    1.06
     ones
    1.02
     latter
    1.02
     proverbial
    1.02
    ses
    1.00
    Act Density 0.230%

    No Known Activations