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

    Neuronpedia

    INDEX
    Explanations

    information related to crime incidents and arrests

    oai_token-act-pair · gpt-3.5-turbo

    information related to arrests and crime reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ku
    -0.82
    Myth
    -0.73
    sometimes
    -0.66
    icult
    -0.66
    yt
    -0.66
    Think
    -0.65
     tru
    -0.63
    kt
    -0.63
    Pinterest
    -0.62
    pse
    -0.61
    POSITIVE LOGITS
     whatsoever
    1.15
     wrongdoing
    0.97
     nor
    0.92
    arnaev
    0.89
    nor
    0.81
     confir
    0.79
     detectable
    0.79
     except
    0.78
     authorized
    0.76
     markings
    0.75
    Act Density 0.372%

    No Known Activations