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

    Neuronpedia

    INDEX
    Explanations

    words related to historical figures and events

    oai_token-act-pair · gpt-3.5-turbo

    names of historical figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.97
    rongh
    -0.70
    yip
    -0.65
     notor
    -0.62
     pestic
    -0.59
     metic
    -0.58
    eatures
    -0.57
     merits
    -0.57
     recounts
    -0.57
    inding
    -0.57
    POSITIVE LOGITS
     ..............
    1.09
     0
    1.04
     ??
    0.94
     1
    0.89
     ........
    0.88
     31
    0.88
     2
    0.87
     00000000
    0.87
     ..........
    0.86
     37
    0.86
    Act Density 0.199%

    No Known Activations