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

    Neuronpedia

    INDEX
    Explanations

    serious crimes related to violence and harm against individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to severe crimes and violent offenses against people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hers
    -0.70
    rils
    -0.70
    ivities
    -0.70
    achev
    -0.70
    angelo
    -0.69
    DK
    -0.69
    olson
    -0.69
    iets
    -0.67
     Seconds
    -0.67
    hower
    -0.67
    POSITIVE LOGITS
     kidnapping
    1.48
     arson
    1.46
     manslaughter
    1.45
     robbery
    1.44
     rape
    1.43
     extortion
    1.41
     robberies
    1.39
     rapes
    1.38
     murder
    1.34
     kidn
    1.32
    Act Density 0.249%

    No Known Activations