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

    Neuronpedia

    INDEX
    Explanations

    references to crime and criminal plots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abuse
    -0.19
     Abuse
    -0.18
     abuses
    -0.18
     abusive
    -0.17
     abusing
    -0.15
    abus
    -0.15
    丸
    -0.14
    SECRET
    -0.14
    éŀ
    -0.14
     assassin
    -0.14
    POSITIVE LOGITS
     rob
    0.37
     robbed
    0.35
     robbery
    0.35
     robber
    0.34
    rob
    0.33
     getaway
    0.30
     Rob
    0.27
    burg
    0.27
     burgl
    0.26
    Rob
    0.25
    Act Density 0.122%

    No Known Activations