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

    Neuronpedia

    INDEX
    Explanations

    proper nouns indicating people's names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isite
    -0.74
    rates
    -0.72
     Extend
    -0.71
    isites
    -0.71
    bits
    -0.68
    osate
    -0.68
    velt
    -0.63
    idth
    -0.62
     Requirements
    -0.62
     Costs
    -0.62
    POSITIVE LOGITS
     arrested
    1.12
     apprehended
    1.11
     transported
    1.09
     hospitalized
    1.06
     arra
    1.05
     taken
    1.04
     pronounced
    1.04
     reportedly
    1.04
     interviewed
    1.03
     identified
    1.03
    Act Density 0.142%

    No Known Activations