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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals being arrested for criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating arrests and legal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pher
    -0.77
    jar
    -0.70
    phabet
    -0.68
    wolves
    -0.68
    antha
    -0.67
    rians
    -0.65
    holes
    -0.65
    patch
    -0.63
    itar
    -0.63
    oom
    -0.63
    POSITIVE LOGITS
     suspicion
    1.40
     behalf
    1.27
     charges
    1.17
    etime
    1.04
     misdemeanor
    0.95
     grounds
    0.95
     felony
    0.94
     spurious
    0.94
     suspicions
    0.93
     accusations
    0.93
    Act Density 0.081%

    No Known Activations