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

    Neuronpedia

    INDEX
    Explanations

    locations, specifically cities and states

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     teras
    -0.92
     teka
    -0.91
    astéro
    -0.88
     ù
    -0.86
     Walkover
    -0.85
     Minangkabau
    -0.84
     kamb
    -0.82
     pama
    -0.81
    SourceChecksum
    -0.80
    ImageContext
    -0.79
    POSITIVE LOGITS
     Byp
    1.02
     McInt
    0.93
     suscep
    0.92
     Pamph
    0.91
     impra
    0.91
     Thx
    0.89
     cushi
    0.87
     McLaugh
    0.81
     disreg
    0.80
    Utilization
    0.80
    Act Density 0.097%

    No Known Activations