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

    Neuronpedia

    INDEX
    Explanations

    words that signify changes over time or cause and effect relationships

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

    "Then" or similar time-related words

    np_acts-logits-general · gemini-2.0-flash

    then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vooraf
    -0.79
     pourtant
    -0.72
    recently
    -0.71
     Италијани
    -0.70
     lately
    -0.70
    تقاوى
    -0.70
     estekak
    -0.69
     recently
    -0.68
     estimés
    -0.68
     Italijanski
    -0.68
    POSITIVE LOGITS
     proceed
    1.12
     proceeded
    1.12
    Then
    0.93
     further
    0.93
     Then
    0.91
     Далее
    0.90
     proceeds
    0.90
     then
    0.89
    Далее
    0.88
     THEN
    0.88
    Act Density 0.620%

    No Known Activations