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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations that are considered special or significant to the individual mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "hometown."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chnology
    -0.88
    uchin
    -0.87
    xual
    -0.83
    andum
    -0.82
    lda
    -0.82
    ONS
    -0.80
    iasis
    -0.79
    lled
    -0.78
    assic
    -0.78
    ression
    -0.77
    POSITIVE LOGITS
     Borough
    0.83
    scape
    0.80
     hometown
    0.75
     favorites
    0.72
     Electrical
    0.72
     haunt
    0.71
     favorite
    0.70
     skyline
    0.69
     hero
    0.67
     ZIP
    0.66
    Act Density 0.008%

    No Known Activations