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

    Neuronpedia

    INDEX
    Explanations

    comparisons or changes in values over time

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" in various contexts, indicating comparisons or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leness
    -0.68
    lez
    -0.68
    Rub
    -0.68
    wic
    -0.66
    neg
    -0.66
    Ò
    -0.65
    bear
    -0.65
    Ess
    -0.63
    ãĥĦ
    -0.63
    minus
    -0.63
    POSITIVE LOGITS
    piring
    1.03
    pects
    1.00
     evidenced
    0.99
     well
    0.94
    ylum
    0.92
     soon
    0.92
    ynchron
    0.86
     opposed
    0.82
    phy
    0.82
    pired
    0.81
    Act Density 0.182%

    No Known Activations