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

    Neuronpedia

    INDEX
    Explanations

    descriptions of violent actions involving physical harm

    oai_token-act-pair · gpt-3.5-turbo

    references to violent or criminal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blueprint
    -0.81
     Ranking
    -0.73
     Topics
    -0.73
     Authors
    -0.72
     niche
    -0.71
     Innovation
    -0.70
     Historically
    -0.69
    ahime
    -0.67
    iets
    -0.67
     mainline
    -0.67
    POSITIVE LOGITS
     police
    1.23
    police
    1.18
     paramedics
    1.14
    Police
    1.10
     detectives
    1.08
     ransom
    1.07
    nsics
    1.04
     robbers
    1.03
     cops
    1.03
     custody
    1.01
    Act Density 0.664%

    No Known Activations