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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being arrested or charged with violations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal issues and crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nos
    -0.80
    20439
    -0.65
    jas
    -0.60
    dit
    -0.58
    oris
    -0.56
     Koh
    -0.56
     Levi
    -0.55
    john
    -0.54
    idas
    -0.54
     Martian
    -0.53
    POSITIVE LOGITS
    izoph
    0.73
    ificate
    0.67
    tein
    0.64
    ulent
    0.63
    unia
    0.62
    netflix
    0.61
     Citadel
    0.61
    zilla
    0.59
    wright
    0.59
    anooga
    0.58
    Act Density 0.402%

    No Known Activations