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

    Neuronpedia

    INDEX
    Explanations

    references to different police departments

    oai_token-act-pair · gpt-3.5-turbo

    references to police departments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    term
    -0.70
    table
    -0.69
    figure
    -0.68
    sed
    -0.68
    sett
    -0.68
     clot
    -0.67
    bent
    -0.66
    ulative
    -0.65
    alien
    -0.65
    isin
    -0.64
    POSITIVE LOGITS
    OA
    0.77
    imore
    0.75
    abulary
    0.75
     brass
    0.75
     Employees
    0.75
     superintendent
    0.75
     subst
    0.72
     paramed
    0.71
     personnel
    0.69
     Inspector
    0.69
    Act Density 0.043%

    No Known Activations