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

    Neuronpedia

    INDEX
    Explanations

    mentions of public safety-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to public safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raped
    -0.71
    ãĥ£
    -0.70
     salads
    -0.68
    Bone
    -0.68
    amic
    -0.68
    SN
    -0.67
    sonian
    -0.66
    istle
    -0.65
    imates
    -0.65
    ularity
    -0.65
    POSITIVE LOGITS
     emergencies
    0.72
     utilities
    0.71
     safety
    0.69
     dispatcher
    0.69
     Telecommunications
    0.68
    oppable
    0.67
     negligence
    0.66
     enforcement
    0.66
     departments
    0.66
     Safety
    0.65
    Act Density 0.015%

    No Known Activations