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

    Neuronpedia

    INDEX
    Explanations

    terms related to crime and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /pi
    -0.17
    rl
    -0.16
    olit
    -0.15
    ocket
    -0.15
     Murder
    -0.14
    quila
    -0.14
    iglia
    -0.14
    cluster
    -0.14
     Whisper
    -0.14
    iences
    -0.13
    POSITIVE LOGITS
     rob
    0.24
     vault
    0.23
     robbery
    0.23
     bank
    0.22
     banks
    0.21
     robber
    0.21
    vault
    0.20
     Bank
    0.20
     robbed
    0.19
     BANK
    0.19
    Act Density 0.090%

    No Known Activations