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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location named "Hobart."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or location named "Hobart."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.89
    xual
    -0.89
     Sheen
    -0.71
    ç¥ŀ
    -0.68
     polarized
    -0.64
     Ibid
    -0.62
     Titanic
    -0.61
     separation
    -0.61
    mble
    -0.61
    backer
    -0.61
    POSITIVE LOGITS
    bies
    1.35
    gob
    1.35
    bie
    1.10
    nob
    1.07
    oken
    1.03
    bage
    1.02
    aby
    0.99
    urst
    0.96
    rod
    0.91
    bled
    0.90
    Act Density 0.012%

    No Known Activations