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

    Neuronpedia

    INDEX
    Explanations

    events involving arrests or criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     homic
    -0.15
     shade
    -0.15
     escaping
    -0.15
     Murder
    -0.15
    etag
    -0.14
     murdered
    -0.14
    shade
    -0.14
     homicide
    -0.14
    ATALOG
    -0.14
     assail
    -0.14
    POSITIVE LOGITS
     raids
    0.33
     raid
    0.32
     Operation
    0.32
     operation
    0.31
    Operation
    0.30
    raid
    0.29
     arrests
    0.28
    operation
    0.27
     bust
    0.26
     crackdown
    0.25
    Act Density 0.150%

    No Known Activations