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

    Neuronpedia

    INDEX
    Explanations

    references to criminal arrests

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "arrest."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pace
    -0.85
    issance
    -0.70
    emonic
    -0.70
    vironment
    -0.69
    soDeliveryDate
    -0.66
     enthus
    -0.65
    ÃŁ
    -0.64
    vana
    -0.64
     embr
    -0.63
    ctory
    -0.63
    POSITIVE LOGITS
    ees
    0.97
     Warrant
    0.90
     warrants
    0.84
     warrant
    0.83
    ments
    0.81
    able
    0.81
     arrest
    0.76
    eering
    0.73
    rained
    0.73
    alties
    0.72
    Act Density 0.031%

    No Known Activations