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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and names, particularly related to the media and entertainment industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.88
    icles
    -0.74
    atana
    -0.72
    ied
    -0.71
    aan
    -0.71
    Ry
    -0.70
    ively
    -0.68
    cer
    -0.68
    nered
    -0.68
    arij
    -0.68
    POSITIVE LOGITS
     Fallon
    0.87
    robe
    0.72
    Wiki
    0.69
     recomm
    0.69
     Manning
    0.68
    vation
    0.65
    itri
    0.64
     Nept
    0.64
     Gib
    0.63
     Ended
    0.62
    Act Density 0.034%

    No Known Activations