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

    Neuronpedia

    INDEX
    Explanations

    specific details or information within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    references to specifics or particulars within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azar
    -0.72
    ammers
    -0.71
     Jindal
    -0.69
    nder
    -0.69
    azed
    -0.69
    asus
    -0.67
    asis
    -0.64
    own
    -0.64
     Sabha
    -0.63
    mire
    -0.62
    POSITIVE LOGITS
     details
    1.23
     detail
    1.02
    displayText
    0.94
     specifics
    0.92
    details
    0.92
     Details
    0.92
     particulars
    0.90
     detailing
    0.79
     nuances
    0.78
    etter
    0.77
    Act Density 0.021%

    No Known Activations