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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating temporal references and past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CG
    -0.67
    atio
    -0.65
    Entry
    -0.65
    Scot
    -0.65
     suits
    -0.64
     masks
    -0.64
    Optional
    -0.63
    Later
    -0.63
    emaker
    -0.63
     offsets
    -0.62
    POSITIVE LOGITS
    lished
    0.79
    stros
    0.72
     Rampage
    0.70
     announcing
    0.66
     headlined
    0.65
    mber
    0.64
    ODUCT
    0.63
     commenter
    0.62
    NAS
    0.61
     STUD
    0.61
    Act Density 0.198%

    No Known Activations