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

    Neuronpedia

    INDEX
    Explanations

    texts related to politics and socio-political events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    accompan
    -0.72
     eleph
    -0.69
    HEAD
    -0.62
    DeliveryDate
    -0.60
     DEC
    -0.57
    ACC
    -0.55
     TRA
    -0.55
    ipel
    -0.55
     lobbying
    -0.53
     151
    -0.53
    POSITIVE LOGITS
    x
    0.86
    Õ
    0.81
    e
    0.76
    a
    0.76
    uve
    0.73
    swers
    0.71
    u
    0.71
    y
    0.71
    )=(
    0.71
    2
    0.70
    Act Density 1.996%

    No Known Activations