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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.17
    2:0.08
    3:0.12
    4:0.07
    5:0.12
    6:0.03
    7:0.03
    8:0.09
    9:0.03
    10:0.03
    11:0.11
    Negative Logits
    SPONSORED
    -2.82
    .」
    -2.45
    aband
    -2.45
     Patt
    -2.42
    ?」
    -2.39
     Ballard
    -2.36
     darts
    -2.31
     Rupert
    -2.27
     lawy
    -2.20
    stakes
    -2.20
    POSITIVE LOGITS
    undle
    2.61
    asin
    2.57
     Skydragon
    2.52
    Enable
    2.48
    Enh
    2.40
    Config
    2.39
    Emb
    2.39
    Secondly
    2.39
    Ut
    2.38
     0
    2.37
    Act Density 0.000%

    No Known Activations