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

    Neuronpedia

    INDEX
    Explanations

    news events related to violence and crime

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     monopol
    -0.86
     royalty
    -0.84
     enriched
    -0.83
     fulfil
    -0.82
     envis
    -0.81
     extinct
    -0.81
     indispensable
    -0.80
     challeng
    -0.80
     taboo
    -0.79
     pudding
    -0.79
    POSITIVE LOGITS
     Investigators
    1.62
     Witnesses
    1.47
     Authorities
    1.46
     Officials
    1.40
    Investigators
    1.27
     According
    1.23
     Officers
    1.21
     Luckily
    1.21
    Authorities
    1.20
     Fortunately
    1.19
    Act Density 0.407%

    No Known Activations