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

    Neuronpedia

    INDEX
    Explanations

    terms pertaining to pressure changes and their effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.05
    2:0.14
    3:0.06
    4:0.04
    5:0.05
    6:0.15
    7:0.04
    8:0.04
    9:0.28
    10:0.03
    11:0.03
    Negative Logits
     Hallow
    -3.72
     Maiden
    -3.71
     yarn
    -3.68
     millenn
    -3.60
     McAuliffe
    -3.38
     Yad
    -3.34
     Carn
    -3.29
     Din
    -3.27
     Nerd
    -3.23
     Trail
    -3.17
    POSITIVE LOGITS
    pressure
    7.39
     Pressure
    7.27
     pressure
    6.67
     pressures
    6.17
     PRESS
    5.48
    PRESS
    5.27
    press
    5.18
    Press
    5.13
     pressuring
    4.91
     pressured
    4.87
    Act Density 0.002%

    No Known Activations