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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.06
    3:0.04
    4:0.06
    5:0.03
    6:0.22
    7:0.04
    8:0.11
    9:0.24
    10:0.03
    11:0.02
    Negative Logits
     gy
    -3.93
     Dh
    -3.90
     Belarus
    -3.89
    Ash
    -3.87
     cuff
    -3.68
     Chel
    -3.65
     Fit
    -3.62
    �
    -3.61
     Chain
    -3.51
     Ash
    -3.47
    POSITIVE LOGITS
     Newman
    11.49
     Swanson
    4.64
     Werner
    4.45
     Wynne
    4.43
     Gomez
    4.42
     Rudolph
    4.33
     Queensland
    4.27
     Nelson
    4.19
     Newt
    4.18
     Christie
    4.15
    Act Density 0.003%

    No Known Activations