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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related language, emphasizing later and earlier occurrences

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

    "later"

    np_acts-logits-general · gemini-2.0-flash

    later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.66
    исленность
    -0.60
     المعيارى
    -0.52
     esternos
    -0.52
    formerly
    -0.52
     sebelumnya
    -0.52
     ​​
    -0.51
     tenuta
    -0.51
     &___
    -0.50
     précédentes
    -0.50
    POSITIVE LOGITS
     generations
    0.89
     than
    0.87
     дописавши
    0.75
     stages
    0.73
    enumi
    0.72
     editions
    0.71
    CloseOperation
    0.70
    ⓧ
    0.70
    itic
    0.69
     versions
    0.68
    Act Density 0.087%

    No Known Activations