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

    Neuronpedia

    INDEX
    Explanations

    references to police or law enforcement officers

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Cop" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.76
    Downloadha
    -0.75
    WAYS
    -0.73
    Ń·
    -0.72
    WAY
    -0.66
    pport
    -0.66
    itably
    -0.64
    AAAA
    -0.64
    AAAAAAAA
    -0.64
    çĦ
    -0.64
    POSITIVE LOGITS
    yrights
    1.21
    eland
    1.03
    tic
    1.00
    rodu
    0.94
    Cop
    0.92
    ulative
    0.87
    yright
    0.86
     Cop
    0.83
    aque
    0.82
    ilon
    0.81
    Act Density 0.007%

    No Known Activations