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

    Neuronpedia

    INDEX
    Explanations

    references to events and actions in a chronological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.00
    2:0.21
    3:0.20
    4:0.09
    5:0.02
    6:0.02
    7:0.11
    8:0.05
    9:0.06
    10:0.11
    11:0.07
    Negative Logits
     :(
    -1.68
     endif
    -1.63
    !!!!
    -1.54
    artments
    -1.53
    cellence
    -1.49
    soType
    -1.49
    Db
    -1.48
     🙂
    -1.48
    ��
    -1.45
    joice
    -1.44
    POSITIVE LOGITS
     dated
    1.81
     titled
    1.59
     Cummings
    1.54
     Barber
    1.50
     Springer
    1.42
     Stevens
    1.42
     reporters
    1.35
     Tuesday
    1.35
     revealing
    1.34
     Swift
    1.32
    Act Density 0.139%

    No Known Activations