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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence community (IC) terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -0.67
     Elys
    -0.66
     CDs
    -0.64
     Faust
    -0.63
    ãģ®éŃĶ
    -0.62
     Amtrak
    -0.60
    abouts
    -0.60
     Jackets
    -0.59
    wards
    -0.59
     subject
    -0.59
    POSITIVE LOGITS
    ANN
    1.00
    orns
    0.93
    orned
    0.92
    overed
    0.91
    rosso
    0.90
    ests
    0.87
    urst
    0.86
    racted
    0.85
    ategory
    0.85
    ues
    0.82
    Act Density 0.093%

    No Known Activations