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

    Neuronpedia

    INDEX
    Explanations

    names of locations or people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulence
    -1.04
    rals
    -0.91
    ulously
    -0.86
    inals
    -0.86
    ré
    -0.84
    orum
    -0.83
    amily
    -0.81
    icultural
    -0.79
    inatory
    -0.79
    ules
    -0.78
    POSITIVE LOGITS
    NetMessage
    0.99
    heart
    0.86
    joy
    0.81
    ãģį
    0.77
     Hands
    0.74
    burgh
    0.72
    ç·
    0.71
     Skydragon
    0.70
     River
    0.70
     Creed
    0.69
    Act Density 0.050%

    No Known Activations