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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "decrease" and its variations in context

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

    decrease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgumentParser
    -0.53
    Ike
    -0.52
    RFI
    -0.49
    ISupport
    -0.49
    Stam
    -0.48
    Syd
    -0.48
    Autowired
    -0.47
    ++++++++++++++++
    -0.47
    Sydney
    -0.47
     pater
    -0.47
    POSITIVE LOGITS
     decrease
    1.47
     Decrease
    1.38
     decreased
    1.30
    decrease
    1.30
    Decrease
    1.26
     decreasing
    1.20
     Decreased
    1.16
     decreases
    1.16
     Decre
    1.09
    Decre
    1.03
    Act Density 0.019%

    No Known Activations