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

    Neuronpedia

    INDEX
    Explanations

    references to social media interactions and public communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.17
    1:0.07
    2:0.07
    3:0.05
    4:0.04
    5:0.04
    6:0.13
    7:0.08
    8:0.02
    9:0.05
    10:0.18
    11:0.04
    Negative Logits
    psey
    -3.02
    yss
    -2.95
     Mane
    -2.87
     Raptors
    -2.78
     Anim
    -2.74
     BT
    -2.73
     Bark
    -2.72
     Rapt
    -2.71
     ly
    -2.68
     ISS
    -2.68
    POSITIVE LOGITS
     Juan
    8.12
     Jorge
    4.94
     Puerto
    4.76
     Fernandez
    4.63
     Dominican
    4.57
     José
    4.31
     Gian
    4.27
     Guan
    4.26
     Haitian
    4.23
     Hond
    4.12
    Act Density 0.002%

    No Known Activations