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

    Neuronpedia

    INDEX
    Explanations

    descriptions of scenes involving people and actions

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of gatherings or crowds involving multiple people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.69
    cest
    -0.67
     Factor
    -0.66
     Investor
    -0.66
    ãĤ´ãĥ³
    -0.65
    osate
    -0.63
     Lifetime
    -0.62
    DERR
    -0.62
    opathy
    -0.61
    ONDON
    -0.61
    POSITIVE LOGITS
     chanting
    1.18
    selves
    1.12
     helmets
    1.06
     mouths
    1.05
     themselves
    1.05
     unison
    1.01
     chairs
    1.01
     torches
    0.99
     apiece
    0.98
     clustered
    0.98
    Act Density 0.478%

    No Known Activations