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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and descriptions involving touch screen devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.18
    1:0.07
    2:0.10
    3:0.04
    4:0.04
    5:0.01
    6:0.10
    7:0.12
    8:0.02
    9:0.03
    10:0.18
    11:0.05
    Negative Logits
     Presbyterian
    -2.83
     Ramsay
    -2.81
     turkey
    -2.78
     Sav
    -2.77
     sal
    -2.76
     Su
    -2.75
     Wolves
    -2.72
    ESCO
    -2.69
     Pale
    -2.67
     Sal
    -2.64
    POSITIVE LOGITS
     Dot
    8.89
     DOT
    6.57
    dot
    6.51
     dot
    6.31
     dots
    4.80
     Cot
    3.85
     Bots
    3.29
     DT
    3.23
     TTL
    3.09
     Turing
    3.04
    Act Density 0.007%

    No Known Activations