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

    Neuronpedia

    INDEX
    Explanations

    terms related to architectural features or facades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.29
    4:0.02
    5:0.02
    6:0.11
    7:0.10
    8:0.05
    9:0.04
    10:0.07
    11:0.13
    Negative Logits
     Zeal
    -1.13
     helium
    -1.05
    wcs
    -1.05
     Indra
    -1.04
     sled
    -1.03
     comma
    -1.01
     Wem
    -1.01
    pent
    -1.00
     scraps
    -0.99
     frivol
    -0.98
    POSITIVE LOGITS
    MRI
    1.39
    uman
    1.22
    ocked
    1.12
    thood
    1.10
    HR
    1.03
    rest
    1.02
    checking
    1.01
    assing
    1.01
     guiActiveUn
    1.01
    auga
    0.99
    Act Density 0.003%

    No Known Activations