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

    Neuronpedia

    INDEX
    Explanations

    information related to historical figures or individuals and their relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     deterrent
    -0.83
    wcs
    -0.82
     audits
    -0.79
     citations
    -0.75
     redund
    -0.74
     obser
    -0.74
     prosecutions
    -0.74
     deterrence
    -0.74
     calibration
    -0.73
     skies
    -0.72
    POSITIVE LOGITS
     Samantha
    0.96
     Molly
    0.88
     Jessica
    0.88
     Ginny
    0.86
     girlfriend
    0.86
     Sophie
    0.86
     Barbie
    0.85
     prostitutes
    0.85
     Valerie
    0.85
     Eva
    0.84
    Act Density 0.181%

    No Known Activations