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

    Neuronpedia

    INDEX
    Explanations

    references to violent incidents and subsequent investigations involving law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.17
     Abuse
    -0.16
    ccione
    -0.15
    ophobia
    -0.14
     Prosecutor
    -0.14
    regor
    -0.14
    victim
    -0.14
    rezent
    -0.14
     assassination
    -0.14
    elay
    -0.13
    POSITIVE LOGITS
     cul
    0.46
     culprit
    0.35
     suspects
    0.33
     offenders
    0.32
    cul
    0.32
     suspect
    0.31
     Cul
    0.30
     accused
    0.29
     criminals
    0.28
     offender
    0.28
    Act Density 0.287%

    No Known Activations