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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal indictments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of legal indictments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chan
    -0.70
    ques
    -0.67
    eno
    -0.63
    lan
    -0.63
    osh
    -0.60
    rans
    -0.60
     Elf
    -0.59
     Flex
    -0.59
     tucked
    -0.59
     zones
    -0.58
    POSITIVE LOGITS
     indictment
    4.01
     indict
    2.62
     indicted
    2.00
     impeachment
    1.60
     prosecution
    1.49
     accusation
    1.42
     arra
    1.39
     arrest
    1.39
     prosecutions
    1.34
     extradition
    1.31
    Act Density 0.019%

    No Known Activations