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

    Neuronpedia

    INDEX
    Explanations

    instances of theft or robbery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forCell
    -0.14
     cho
    -0.14
     fier
    -0.14
     заÑģÑĤ
    -0.13
    USR
    -0.13
     cz
    -0.13
     Cho
    -0.13
    Prediction
    -0.13
     massacre
    -0.13
     chatt
    -0.13
    POSITIVE LOGITS
     RTC
    0.16
    otton
    0.16
     officers
    0.16
    999
    0.16
     Officers
    0.15
    uge
    0.15
    sian
    0.15
     understood
    0.15
    olvers
    0.14
    xde
    0.14
    Act Density 0.033%

    No Known Activations