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

    Neuronpedia

    INDEX
    Explanations

    references to military and security organizations or personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.04
    3:0.46
    4:0.03
    5:0.07
    6:0.02
    7:0.06
    8:0.05
    9:0.02
    10:0.08
    11:0.05
    Negative Logits
    "—
    -2.21
     ninety
    -2.15
     pacif
    -2.12
    —"
    -2.07
     decre
    -2.03
     punishing
    -2.03
     seventy
    -2.02
     caring
    -1.98
     forb
    -1.97
     recommended
    -1.96
    POSITIVE LOGITS
    utterstock
    3.30
     IMAGES
    3.13
    reenshot
    2.96
     Shutterstock
    2.73
     REUTERS
    2.66
     Courtesy
    2.58
    photo
    2.58
    Photos
    2.53
    photos
    2.52
     Images
    2.46
    Act Density 0.345%

    No Known Activations