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

    Neuronpedia

    INDEX
    Explanations

    dates and time references

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atics
    -0.80
    ioxide
    -0.76
    bryce
    -0.71
    ibles
    -0.69
    Optional
    -0.69
    Course
    -0.69
    fml
    -0.66
    eers
    -0.66
    Unique
    -0.65
    ater
    -0.64
    POSITIVE LOGITS
     headlined
    0.87
     Rampage
    0.78
    lished
    0.72
     announcing
    0.72
    iannopoulos
    0.71
     earthqu
    0.69
     Krish
    0.66
     railing
    0.65
     citing
    0.64
     alerted
    0.62
    Act Density 0.193%

    No Known Activations