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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the importance of accuracy and up-to-date information

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

    "up" followed by "to" or variations of "date"

    np_acts-logits-general · gemini-2.0-flash

    up-to-date information or stock prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.81
    __':
    -0.71
    kháu
    -0.70
    __':
    -0.65
    __":
    -0.63
    __":
    -0.61
     oprot
    -0.61
    usermodel
    -0.60
     <=",
    -0.59
    SequentialGroup
    -0.57
    POSITIVE LOGITS
     updated
    1.73
     updating
    1.50
     updates
    1.49
    updated
    1.45
     update
    1.45
    Updating
    1.31
     Updating
    1.31
     Updates
    1.30
    Updated
    1.28
     outdated
    1.28
    Act Density 0.186%

    No Known Activations