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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations, with a focus on the city of Geneva

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Geneva and related locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alach
    -0.88
    ramid
    -0.85
    llor
    -0.74
    adding
    -0.74
    vich
    -0.72
    etitive
    -0.72
    transform
    -0.71
    reci
    -0.68
    onent
    -0.67
    ointed
    -0.66
    POSITIVE LOGITS
     Geneva
    0.97
     Hague
    0.86
     franc
    0.80
     seiz
    0.79
     countryside
    0.74
     Vienna
    0.73
     Lumpur
    0.73
    ascus
    0.73
    姫
    0.71
     Switzerland
    0.70
    Act Density 0.007%

    No Known Activations