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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations or objects within a specific setting

    oai_token-act-pair · gpt-3.5-turbo

    sentences that describe states of being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ients
    -0.87
    imize
    -0.72
    imeters
    -0.71
    iets
    -0.68
    seys
    -0.68
    inventoryQuantity
    -0.67
    uum
    -0.66
    umat
    -0.65
    initial
    -0.63
    players
    -0.63
    POSITIVE LOGITS
     another
    0.94
     inscribed
    0.69
     situated
    0.66
     a
    0.65
     also
    0.64
     an
    0.63
     abundant
    0.61
    phia
    0.60
     lined
    0.60
     engraved
    0.60
    Act Density 0.091%

    No Known Activations