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

    Neuronpedia

    INDEX
    Explanations

    references to dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.10
    3:0.03
    4:0.02
    5:0.04
    6:0.06
    7:0.05
    8:0.04
    9:0.02
    10:0.45
    11:0.06
    Negative Logits
     Tradable
    -2.27
    MX
    -2.11
    etus
    -2.09
    apes
    -2.08
     Sik
    -1.98
    Origin
    -1.96
     Tek
    -1.96
     Codec
    -1.95
    esm
    -1.94
     NIC
    -1.93
    POSITIVE LOGITS
    27
    4.13
     27
    3.61
     1927
    3.40
    28
    2.86
     277
    2.71
    277
    2.67
    276
    2.65
    26
    2.57
     1928
    2.54
     279
    2.53
    Act Density 0.009%

    No Known Activations