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

    Neuronpedia

    INDEX
    Explanations

    phrases related to visual presentation or display

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.12
    3:0.03
    4:0.04
    5:0.13
    6:0.08
    7:0.09
    8:0.16
    9:0.06
    10:0.12
    11:0.05
    Negative Logits
    王
    -1.29
     retaliate
    -1.24
    �
    -1.18
    issance
    -1.16
    ドラ
    -1.14
    guard
    -1.13
     conquer
    -1.10
     conquered
    -1.10
     worshipped
    -1.08
    神
    -1.07
    POSITIVE LOGITS
    hov
    1.38
     anomalies
    1.20
    htaking
    1.18
    Leaks
    1.16
     Nielsen
    1.16
     graphs
    1.15
    summary
    1.15
     snapshots
    1.14
    net
    1.13
    NBC
    1.12
    Act Density 0.072%

    No Known Activations