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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to breaking or assembling pieces together

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "pieces" and assembly or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Predators
    -0.84
     Monitor
    -0.83
     Lawyers
    -0.68
    Fight
    -0.66
     colonel
    -0.61
     Lords
    -0.60
     Pione
    -0.60
    Domain
    -0.59
    ESCO
    -0.58
    zee
    -0.57
    POSITIVE LOGITS
    meal
    1.61
     pieces
    1.14
     Pieces
    0.93
    work
    0.90
    umen
    0.90
    glass
    0.82
    ilage
    0.82
    etter
    0.82
     piece
    0.81
    uania
    0.80
    Act Density 0.019%

    No Known Activations