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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vain
    -0.66
    ARI
    -0.66
    Sing
    -0.66
    artifacts
    -0.64
    apixel
    -0.62
    xual
    -0.61
    ibaba
    -0.61
    uras
    -0.61
     è£ıç
    -0.58
     RGB
    -0.57
    POSITIVE LOGITS
     2025
    0.87
     2030
    0.83
     2050
    0.83
     2021
    0.73
     exhaustion
    0.72
    reau
    0.72
     2020
    0.69
    âĸĪâĸĪ
    0.69
     2024
    0.68
    century
    0.67
    Act Density 0.085%

    No Known Activations