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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations or sources of origin

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups or participants from different regions or backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    potion
    -0.76
    luck
    -0.67
    ratulations
    -0.67
    manac
    -0.67
    omy
    -0.65
    staking
    -0.65
    henko
    -0.64
    Order
    -0.64
    mere
    -0.64
    tes
    -0.63
    POSITIVE LOGITS
     across
    1.44
     abroad
    1.34
     afar
    1.30
     diverse
    1.17
     disparate
    1.13
     around
    1.13
     everywhere
    1.10
     various
    1.10
     Across
    1.09
     different
    1.08
    Act Density 0.137%

    No Known Activations