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

    Neuronpedia

    INDEX
    Explanations

    information related to crime and investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to allegations or accusations involving serious incidents or crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !).
    -0.66
    !),
    -0.64
    )!
    -0.59
    ankind
    -0.58
    )?
    -0.55
    !.
    -0.55
    }.
    -0.54
    !'
    -0.54
    ependence
    -0.52
    ?).
    -0.52
    POSITIVE LOGITS
     Paddock
    0.66
     pornographic
    0.60
     Blumenthal
    0.59
     improper
    0.58
     inappropriately
    0.58
     unlawful
    0.58
     unlawfully
    0.57
     Defendant
    0.56
     "âĢ¦
    0.56
     inappropriate
    0.55
    Act Density 1.790%

    No Known Activations