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

    Neuronpedia

    INDEX
    Explanations

    phrases related to police investigations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to police activity and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.86
    married
    -0.77
    die
    -0.74
    milo
    -0.72
     womb
    -0.72
    çľ
    -0.71
    âķ
    -0.69
     contrace
    -0.68
    Creat
    -0.67
     grapes
    -0.66
    POSITIVE LOGITS
     investigating
    0.98
     Detect
    0.97
     checkpoints
    0.88
    nsics
    0.88
     patrols
    0.86
     arrests
    0.86
     detain
    0.86
     Constable
    0.85
     investigate
    0.84
    nsic
    0.83
    Act Density 0.342%

    No Known Activations