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

    Neuronpedia

    INDEX
    Explanations

    details or specific information mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    the term "details" and its variations in contexts related to information or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.87
    ammers
    -0.80
    rade
    -0.71
    arte
    -0.69
    boa
    -0.68
    agall
    -0.67
    onz
    -0.67
    azar
    -0.67
    igham
    -0.66
    sw
    -0.65
    POSITIVE LOGITS
     details
    1.07
     detail
    0.97
     surrounding
    0.96
     redacted
    0.92
     glean
    0.91
    displayText
    0.90
     thereof
    0.85
     pertaining
    0.77
     regarding
    0.76
     unfold
    0.74
    Act Density 0.041%

    No Known Activations