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

    Neuronpedia

    INDEX
    Explanations

    mentions of cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arial
    -0.84
    chnology
    -0.75
    gotten
    -0.74
    iece
    -0.73
    tsy
    -0.72
    raviolet
    -0.72
    iasis
    -0.71
    --+
    -0.70
    uchs
    -0.70
    yip
    -0.70
    POSITIVE LOGITS
    scape
    0.96
     mayors
    0.94
    chool
    0.84
    wide
    0.84
     skyline
    0.82
     landmarks
    0.81
     cities
    0.79
    hare
    0.79
     museums
    0.78
     parks
    0.78
    Act Density 0.032%

    No Known Activations