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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    that indicate time or order

    np_acts-logits-general · gemini-2.0-flash

    temporal sequence marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tomorrow
    -0.98
     now
    -0.93
     currently
    -0.90
    currently
    -0.89
     artık
    -0.83
    tomorrow
    -0.80
     current
    -0.78
     morrow
    -0.78
     derzeit
    -0.77
     maintenant
    -0.75
    POSITIVE LOGITS
     last
    1.29
     damals
    1.28
     earlier
    1.23
     originally
    1.22
     förra
    1.19
     initially
    1.17
    earlier
    1.11
     yesterday
    1.09
     originalmente
    1.06
     toen
    1.06
    Act Density 0.919%

    No Known Activations