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

    Neuronpedia

    INDEX
    Explanations

    unique character sequences or names within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.39
    2:0.04
    3:0.04
    4:0.03
    5:0.20
    6:0.03
    7:0.02
    8:0.04
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
     KP
    -1.91
     Kard
    -1.81
     reperto
    -1.74
     IST
    -1.73
     prost
    -1.67
     Bagg
    -1.65
     IPM
    -1.65
     CBI
    -1.65
     AST
    -1.62
     videog
    -1.61
    POSITIVE LOGITS
    ne
    3.21
    onne
    2.50
    ene
    2.42
    nian
    2.36
    loe
    2.28
    owitz
    2.17
    rine
    2.16
    enne
    2.14
    inse
    2.13
    ennes
    2.13
    Act Density 0.002%

    No Known Activations