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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to the identity of individuals in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Compare
    -0.78
    alach
    -0.66
    ismo
    -0.65
    lance
    -0.63
    Understanding
    -0.63
    omics
    -0.62
     envy
    -0.62
     Expand
    -0.60
     Contrast
    -0.60
    ageddon
    -0.59
    POSITIVE LOGITS
     witnesses
    1.35
     occupants
    1.29
     participants
    1.24
     victims
    1.24
     claimants
    1.23
     detainees
    1.22
     recipients
    1.20
     persons
    1.17
     guests
    1.17
     beneficiaries
    1.15
    Act Density 0.829%

    No Known Activations