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

    Neuronpedia

    INDEX
    Explanations

    information about criminal charges and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of legal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Remastered
    -0.69
    angular
    -0.67
    patch
    -0.65
    atters
    -0.61
    align
    -0.61
    ophe
    -0.60
    echo
    -0.60
     migr
    -0.60
     illusion
    -0.59
    Begin
    -0.59
    POSITIVE LOGITS
    heet
    1.15
     criminally
    1.09
    llah
    1.00
    illo
    0.83
     indict
    0.82
     charges
    0.82
     indicted
    0.80
     perjury
    0.75
     indictment
    0.73
     Guilty
    0.72
    Act Density 0.035%

    No Known Activations