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

    Neuronpedia

    INDEX
    Explanations

    large structures or spaces like buildings, stadiums, rooms, or ships

    oai_token-act-pair · gpt-3.5-turbo

    references to measurement units and capacities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lishes
    -0.75
    blogs
    -0.69
    uther
    -0.66
     Reborn
    -0.64
    much
    -0.63
    ties
    -0.61
    ocrates
    -0.61
     Elves
    -0.60
    killed
    -0.59
    govtrack
    -0.59
    POSITIVE LOGITS
    osterone
    0.75
    rongh
    0.72
     combo
    0.71
     affair
    0.70
    llor
    0.70
    orie
    0.69
    riors
    0.69
    clusive
    0.68
     ult
    0.65
     ordeal
    0.65
    Act Density 0.081%

    No Known Activations