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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific time periods, particularly years and decades

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly focusing on the last few years or decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tomorrow
    -0.70
    ference
    -0.67
    vier
    -0.65
     tomorrow
    -0.60
    Mat
    -0.60
    querque
    -0.60
    edIn
    -0.59
    hod
    -0.58
     Trafford
    -0.57
    Said
    -0.57
    POSITIVE LOGITS
     alone
    1.03
     or
    0.78
     onwards
    0.73
     combined
    0.73
    frames
    0.68
    ional
    0.68
    代
    0.67
    -'
    0.67
     since
    0.65
     attributable
    0.63
    Act Density 0.083%

    No Known Activations