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

    Neuronpedia

    INDEX
    Explanations

    references to programming and function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.07
    4:0.07
    5:0.07
    6:0.07
    7:0.09
    8:0.09
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
    elsen
    -2.73
     advisors
    -2.62
     [&
    -2.59
    gew
    -2.49
    isle
    -2.47
     settlement
    -2.46
    ipel
    -2.46
    iners
    -2.42
     reinforcement
    -2.39
    chini
    -2.38
    POSITIVE LOGITS
     rpm
    2.71
     Aut
    2.47
     Quartz
    2.43
    PT
    2.42
     Punjab
    2.41
     Vulkan
    2.39
    beat
    2.34
     Barber
    2.33
     Tibet
    2.32
     Eminem
    2.31
    Act Density 0.000%

    No Known Activations