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

    Neuronpedia

    INDEX
    Explanations

    references to legislative or structural changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.04
    3:0.07
    4:0.13
    5:0.03
    6:0.06
    7:0.39
    8:0.04
    9:0.04
    10:0.06
    11:0.08
    Negative Logits
    ngth
    -1.87
    seekers
    -1.85
    ailability
    -1.68
    riott
    -1.60
    waukee
    -1.53
    erion
    -1.52
    uge
    -1.51
    inki
    -1.49
    ividual
    -1.48
    oppers
    -1.46
    POSITIVE LOGITS
     clocks
    1.78
     rewrite
    1.72
     history
    1.64
     reckon
    1.60
     histories
    1.59
     rewritten
    1.54
     textbooks
    1.46
     Sanskrit
    1.46
     recol
    1.44
     paste
    1.43
    Act Density 0.002%

    No Known Activations