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

    Neuronpedia

    INDEX
    Explanations

    references to coding syntax and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.04
    2:0.06
    3:0.06
    4:0.04
    5:0.05
    6:0.17
    7:0.05
    8:0.17
    9:0.14
    10:0.04
    11:0.05
    Negative Logits
     Chinatown
    -3.62
    PIN
    -3.61
     Hust
    -3.56
    zai
    -3.52
     POW
    -3.40
     Zhao
    -3.40
     butcher
    -3.39
     Budd
    -3.34
     Uzbek
    -3.29
     Murdoch
    -3.22
    POSITIVE LOGITS
     ES
    9.23
    ES
    5.00
     es
    4.28
    esm
    4.17
    Es
    4.09
     GOODMAN
    4.07
    eson
    4.06
     node
    3.95
     Brees
    3.88
     console
    3.74
    Act Density 0.003%

    No Known Activations