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

    Neuronpedia

    INDEX
    Explanations

    terms related to law enforcement and police activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.74
     pleaſure
    -0.71
    ſelves
    -0.70
     purpoſe
    -0.69
     houſe
    -0.69
     myſelf
    -0.68
     ſtre
    -0.67
    -0.65
     contextLoads
    -0.64
    存于互联网档案馆
    -0.63
    POSITIVE LOGITS
    Sheriff
    0.45
     Sheriff
    0.45
     sheriff
    0.40
     Police
    0.37
    police
    0.34
     POLICE
    0.33
     police
    0.33
     rück
    0.33
     cops
    0.31
     Sgt
    0.31
    Act Density 0.400%

    No Known Activations