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

    Neuronpedia

    INDEX
    Explanations

    references to North Korea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.09
    4:0.09
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.08
    10:0.08
    11:0.06
    Negative Logits
     dwarves
    -3.17
     ["
    -2.92
     performers
    -2.80
     contestants
    -2.79
     entrants
    -2.76
    casters
    -2.71
     strikers
    -2.65
     comparable
    -2.65
     Ghostbusters
    -2.65
     portrayal
    -2.58
    POSITIVE LOGITS
    iece
    3.55
    apeake
    3.16
    grain
    3.03
     dow
    2.94
    rils
    2.94
    enges
    2.92
    hum
    2.87
    ignt
    2.81
    ruce
    2.79
    dn
    2.78
    Act Density 0.000%

    No Known Activations