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

    Neuronpedia

    INDEX
    Explanations

    details or specific information mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Details" and its variations related to information or specifics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.81
    ammers
    -0.72
    rade
    -0.72
    igham
    -0.71
    ratulations
    -0.68
    ÃŃs
    -0.68
    reath
    -0.68
    boa
    -0.66
    duct
    -0.64
    vic
    -0.64
    POSITIVE LOGITS
     redacted
    1.03
     surrounding
    0.97
     glean
    0.95
     details
    0.91
     regarding
    0.90
     detail
    0.87
     pertaining
    0.87
     thereof
    0.85
    paces
    0.79
     TBA
    0.78
    Act Density 0.057%

    No Known Activations