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

    Neuronpedia

    INDEX
    Explanations

    phrases related to law enforcement actions

    oai_token-act-pair · gpt-3.5-turbo

    information related to crime and arrests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sacrific
    -0.75
     Travels
    -0.61
     smack
    -0.59
     helic
    -0.58
    Think
    -0.57
    ometimes
    -0.57
    zon
    -0.56
     Architects
    -0.56
    Zone
    -0.56
    haul
    -0.56
    POSITIVE LOGITS
     nor
    0.95
    yet
    0.87
     forthcoming
    0.86
     whatsoever
    0.85
     yet
    0.84
    ounced
    0.78
    nor
    0.78
     pending
    0.76
     disclosed
    0.72
     officially
    0.71
    Act Density 0.170%

    No Known Activations