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

    Neuronpedia

    INDEX
    Explanations

    words related to crime and violence

    oai_token-act-pair · gpt-3.5-turbo

    references to ages of individuals involved in incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -1.12
    ernels
    -1.05
    illions
    -1.01
    places
    -1.01
    stocks
    -1.01
    views
    -1.00
     capitals
    -1.00
     havens
    -1.00
    thumbnails
    -0.96
    waves
    -0.96
    POSITIVE LOGITS
     woman
    1.63
     classmate
    1.33
     girl
    1.31
     man
    1.26
     colleague
    1.24
     staffer
    1.24
     employee
    1.22
     teenager
    1.21
     female
    1.20
     protester
    1.19
    Act Density 0.263%

    No Known Activations