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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, specifically hometowns

    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
    err
    -0.96
    assic
    -0.91
    ONS
    -0.91
    uchin
    -0.90
    asse
    -0.88
    awed
    -0.84
    owell
    -0.82
    andum
    -0.81
    ynes
    -0.80
    meal
    -0.79
    POSITIVE LOGITS
     Raider
    0.75
     turf
    0.71
     Huck
    0.71
     Electrical
    0.68
     favorite
    0.67
     favourite
    0.67
     homeland
    0.66
     Shake
    0.65
     favorites
    0.65
     hometown
    0.65
    Act Density 0.036%

    No Known Activations