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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific timeframe in the near future

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "few" to indicate time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.84
    ashtra
    -0.68
    alam
    -0.68
    umed
    -0.67
    UAL
    -0.65
    webkit
    -0.63
    NAS
    -0.63
     conclud
    -0.63
    Draft
    -0.62
    rador
    -0.61
    POSITIVE LOGITS
     dozen
    1.19
     hundred
    1.16
     weeks
    1.03
     thousand
    1.02
     days
    0.98
     months
    0.95
     minutes
    0.90
     paragraphs
    0.87
     seconds
    0.86
     nights
    0.85
    Act Density 0.025%

    No Known Activations