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

    Neuronpedia

    INDEX
    Explanations

    specific years and temporal markers in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.17
    3:0.14
    4:0.15
    5:0.02
    6:0.03
    7:0.09
    8:0.09
    9:0.03
    10:0.12
    11:0.09
    Negative Logits
    ��
    -1.60
    ��
    -1.51
    enemy
    -1.46
    advant
    -1.43
    osta
    -1.42
    friends
    -1.42
    itte
    -1.41
    acus
    -1.41
    icts
    -1.39
    sleep
    -1.39
    POSITIVE LOGITS
    Operation
    1.39
     Chung
    1.33
     Mund
    1.32
     Ples
    1.32
     Roh
    1.29
     compounded
    1.27
     Crunch
    1.27
     accelerated
    1.26
     intensified
    1.26
     culminating
    1.25
    Act Density 0.030%

    No Known Activations