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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -1.01
     mating
    -0.72
    »Ĵ
    -0.71
     sustainable
    -0.71
    isher
    -0.70
    onite
    -0.70
     aquatic
    -0.70
     nuts
    -0.69
     overboard
    -0.69
     manif
    -0.69
    POSITIVE LOGITS
     Its
    1.01
     Initially
    1.01
     However
    1.00
     Previously
    0.98
     Each
    0.97
     Whilst
    0.97
     Doctors
    0.95
    txt
    0.92
     Firstly
    0.92
     Twice
    0.91
    Act Density 0.655%

    No Known Activations