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

    Neuronpedia

    INDEX
    Explanations

    temporal references related to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.10
    3:0.14
    4:0.06
    5:0.03
    6:0.07
    7:0.20
    8:0.05
    9:0.03
    10:0.08
    11:0.13
    Negative Logits
     神
    -1.71
    gently
    -1.68
    tsy
    -1.41
    minecraft
    -1.39
    >.
    -1.37
    govtrack
    -1.34
    soType
    -1.32
    Interstitial
    -1.28
     irrespective
    -1.27
    chin
    -1.23
    POSITIVE LOGITS
     retired
    1.39
     retiring
    1.38
    ounter
    1.38
     stint
    1.32
     retire
    1.31
     conven
    1.23
     longtime
    1.21
     damning
    1.19
     Columbus
    1.19
     compiled
    1.18
    Act Density 0.013%

    No Known Activations