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

    Neuronpedia

    INDEX
    Explanations

    references to police activity and legal situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mort
    -0.18
     helicopt
    -0.16
    TECTED
    -0.15
     Br
    -0.15
     Fal
    -0.15
     pitched
    -0.14
     carts
    -0.14
    mania
    -0.14
     gate
    -0.14
     frag
    -0.14
    POSITIVE LOGITS
     rear
    0.18
    artz
    0.18
    oux
    0.17
     passenger
    0.17
     hatch
    0.17
    ]={↵
    0.17
    -driver
    0.17
    Seat
    0.16
     dashboard
    0.16
     seats
    0.16
    Act Density 0.113%

    No Known Activations