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

    Neuronpedia

    INDEX
    Explanations

    references to the Washington Post and its reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.06
    2:0.11
    3:0.07
    4:0.04
    5:0.11
    6:0.04
    7:0.03
    8:0.04
    9:0.30
    10:0.07
    11:0.04
    Negative Logits
    onga
    -1.58
     neighbour
    -1.41
     neighbours
    -1.37
    uni
    -1.30
    gart
    -1.28
    ranged
    -1.24
    route
    -1.23
    rouse
    -1.21
    ranch
    -1.20
    range
    -1.19
    POSITIVE LOGITS
     Editorial
    1.58
    kefeller
    1.50
    ��
    1.37
    Fact
    1.35
    ptroller
    1.32
     Watergate
    1.30
     �
    1.29
     Tyrann
    1.28
    leases
    1.28
     Pigs
    1.28
    Act Density 0.025%

    No Known Activations