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

    Neuronpedia

    INDEX
    Explanations

    phrases related to crime and ethical issues in documentaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     insults
    -0.07
     insult
    -0.07
    declspec
    -0.06
    ivet
    -0.06
     inj
    -0.06
    oyer
    -0.06
    ivant
    -0.06
    setattr
    -0.06
     Discrim
    -0.06
     rescued
    -0.06
    POSITIVE LOGITS
     crime
    0.11
     Serial
    0.11
     uns
    0.10
     Crime
    0.10
     serial
    0.10
     Uns
    0.09
    Crime
    0.09
    Serial
    0.09
     SERIAL
    0.09
     investigative
    0.09
    Act Density 0.021%

    No Known Activations