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

    conjunctions and prepositions that begin with 'A' or 'I'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.73
    ç·
    -0.70
    OPLE
    -0.68
    lished
    -0.66
     pinned
    -0.62
    hement
    -0.60
    ĸļ
    -0.59
     noses
    -0.58
     writ
    -0.57
     Rouge
    -0.56
    POSITIVE LOGITS
    ussie
    0.83
    ona
    0.82
    ams
    0.81
    alf
    0.79
    oran
    0.79
    ont
    0.78
    omer
    0.77
    aks
    0.77
    uber
    0.76
    edes
    0.76
    Act Density 0.213%

    No Known Activations