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

    Neuronpedia

    INDEX
    Explanations

    references to specific web domains and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.04
    2:0.12
    3:0.13
    4:0.16
    5:0.05
    6:0.13
    7:0.03
    8:0.04
    9:0.07
    10:0.07
    11:0.04
    Negative Logits
     outwe
    -1.57
     bribes
    -1.57
     criminals
    -1.48
     Joker
    -1.47
     intact
    -1.46
     lies
    -1.45
     prostitutes
    -1.42
     selves
    -1.41
     bumps
    -1.36
     SHALL
    -1.35
    POSITIVE LOGITS
    ipedia
    2.16
    info
    2.05
    library
    2.00
    archive
    1.95
    pedia
    1.91
    ipl
    1.79
    useum
    1.78
    utorial
    1.67
    web
    1.66
    Blog
    1.66
    Act Density 0.023%

    No Known Activations