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

    Neuronpedia

    INDEX
    Explanations

    mentions of actions or statements made by the police

    oai_token-act-pair · gpt-3.5-turbo

    the repeated usage of the word "said" in relation to police statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¦
    -0.81
    izont
    -0.77
    Õ
    -0.76
    ï¸
    -0.76
    nic
    -0.75
    tes
    -0.75
    bent
    -0.74
    Newsletter
    -0.73
    otin
    -0.72
    WithNo
    -0.72
    POSITIVE LOGITS
    doms
    0.85
     troopers
    0.79
     Trooper
    0.78
     investigators
    0.77
     prelim
    0.77
     Sergeant
    0.76
     Sgt
    0.76
     anecd
    0.75
     trooper
    0.74
     goodbye
    0.73
    Act Density 0.107%

    No Known Activations