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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violent acts or crimes

    oai_token-act-pair · gpt-3.5-turbo

    references to violent acts, particularly killings and murders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cola
    -0.87
    Stud
    -0.72
    amina
    -0.70
    aque
    -0.70
    Radio
    -0.67
     Tire
    -0.66
    Student
    -0.65
     Plex
    -0.63
    ais
    -0.63
    Jer
    -0.62
    POSITIVE LOGITS
     killings
    1.14
     murders
    1.04
     shootings
    0.99
     spree
    0.98
     homicides
    0.98
    poons
    0.95
    ongs
    0.89
     slaying
    0.88
     slay
    0.82
     shooting
    0.81
    Act Density 0.015%

    No Known Activations