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

    Neuronpedia

    INDEX
    Explanations

    references to law enforcement and investigative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cken
    -0.17
    sip
    -0.16
    sword
    -0.14
    Signing
    -0.14
     Signing
    -0.14
    REFERRED
    -0.14
    Benchmark
    -0.14
    elper
    -0.13
    )))),
    -0.13
    @student
    -0.13
    POSITIVE LOGITS
     located
    0.27
     recovered
    0.25
     pie
    0.23
     determined
    0.22
     learned
    0.22
     found
    0.22
     traced
    0.20
    located
    0.20
     believe
    0.20
     arrested
    0.20
    Act Density 0.068%

    No Known Activations