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

    Neuronpedia

    INDEX
    Explanations

    phrases related to products or services

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.94
    vernment
    -0.76
    nesty
    -0.73
     abortions
    -0.69
    rade
    -0.65
     withdraw
    -0.63
    iberal
    -0.63
     Rita
    -0.63
     because
    -0.63
     without
    -0.62
    POSITIVE LOGITS
     aforementioned
    1.14
     widest
    1.08
     simplest
    1.05
     same
    1.03
     finest
    1.01
     basics
    1.00
     fundamentals
    0.99
     smallest
    0.97
    ses
    0.96
     latest
    0.96
    Act Density 0.736%

    No Known Activations