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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal incidents and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icz
    -0.14
    ERR
    -0.14
    earn
    -0.14
    quo
    -0.14
     dual
    -0.13
     Surveillance
    -0.13
    ATORS
    -0.13
     mor
    -0.13
    icao
    -0.13
    enny
    -0.13
    POSITIVE LOGITS
     crime
    0.16
     Against
    0.15
     Crime
    0.15
     soft
    0.15
    wargs
    0.14
    Against
    0.14
    Crime
    0.14
    kiye
    0.14
    roe
    0.14
     Ign
    0.14
    Act Density 0.346%

    No Known Activations