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

    Neuronpedia

    INDEX
    Explanations

    references to places or regions referred to as "hometown."

    oai_token-act-pair · gpt-3.5-turbo

    references to "hometown"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchin
    -0.90
    chnology
    -0.84
    ression
    -0.82
    err
    -0.79
    iasis
    -0.79
    assic
    -0.78
    lda
    -0.78
    ioxide
    -0.78
    ONS
    -0.75
    abeth
    -0.75
    POSITIVE LOGITS
    scape
    0.80
     haunt
    0.76
     Borough
    0.76
     hometown
    0.75
     favorites
    0.74
     favourite
    0.72
     landmarks
    0.70
     favorite
    0.69
    ites
    0.68
     favourites
    0.68
    Act Density 0.008%

    No Known Activations