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

    Neuronpedia

    INDEX
    Explanations

    instances of reporting actions to authorities, especially involving criminal or problematic incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of reporting or referring to law enforcement and complaints made to authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Untitled
    -0.72
    rawdownloadcloneembedreportprint
    -0.70
    Synopsis
    -0.68
    ãĥ¯ãĥ³
    -0.68
    Includes
    -0.67
    ãĤ©
    -0.66
     excerpt
    -0.66
    å¦
    -0.65
    clips
    -0.65
    ãĥĻ
    -0.65
    POSITIVE LOGITS
     authorities
    1.38
     police
    1.13
     regulators
    1.11
     superiors
    1.08
     prosecutors
    1.03
     investigators
    1.02
     Internal
    0.98
    police
    0.97
     Customs
    0.94
     Police
    0.94
    Act Density 0.179%

    No Known Activations