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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific crimes, particularly homicides

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     triomphe
    -0.88
     shenan
    -0.88
     !...
    -0.85
     snoopy
    -0.84
     maît
    -0.84
     poff
    -0.82
     aquarelle
    -0.82
     Ename
    -0.80
     vhs
    -0.79
     wattpad
    -0.79
    POSITIVE LOGITS
     deaths
    0.79
     homicide
    0.72
     fatalities
    0.69
     murders
    0.64
     incid
    0.62
     incidence
    0.59
     statistics
    0.59
     homic
    0.58
     fatal
    0.58
     killings
    0.58
    Act Density 0.493%

    No Known Activations