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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names and affiliations related to publications and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.25
    1:0.04
    2:0.02
    3:0.07
    4:0.11
    5:0.06
    6:0.07
    7:0.03
    8:0.05
    9:0.13
    10:0.03
    11:0.09
    Negative Logits
    etheless
    -2.67
    again
    -2.26
    theless
    -2.13
    Dave
    -2.01
    Again
    -2.00
     fortunately
    -1.91
     thankfully
    -1.89
     Mub
    -1.89
    aleb
    -1.89
    Josh
    -1.89
    POSITIVE LOGITS
     paras
    2.21
    ,
    2.12
     Encyclopedia
    2.11
     Retrieved
    2.10
    .,
    1.90
     specialty
    1.88
    .;
    1.84
     +++
    1.79
    -,
    1.78
     vol
    1.76
    Act Density 0.001%

    No Known Activations