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

    Neuronpedia

    INDEX
    Explanations

    temporal references or time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.11
    3:0.15
    4:0.34
    5:0.02
    6:0.04
    7:0.06
    8:0.03
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
    aeda
    -2.00
    cius
    -1.77
    ads
    -1.74
    <?
    -1.72
    tics
    -1.53
    itute
    -1.47
     Enemies
    -1.45
    ,,,,,,,,
    -1.45
     @@
    -1.45
     imitate
    -1.42
    POSITIVE LOGITS
     vacated
    1.74
     intervened
    1.62
    soon
    1.59
     Jub
    1.57
     flooded
    1.56
     Tuc
    1.52
     exited
    1.51
    Untitled
    1.50
     Marqu
    1.48
     later
    1.46
    Act Density 0.073%

    No Known Activations