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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LEASE
    -0.77
    Michigan
    -0.71
     Colossus
    -0.71
    IUM
    -0.71
     Westbrook
    -0.69
    CLASSIFIED
    -0.67
    Ohio
    -0.67
    GGGGGGGG
    -0.66
    EEE
    -0.64
    Bloom
    -0.64
    POSITIVE LOGITS
    oub
    1.01
    awar
    0.98
    aya
    0.96
    ulla
    0.94
    iani
    0.93
    hani
    0.92
    ibi
    0.92
    ij
    0.91
    angan
    0.90
    abis
    0.89
    Act Density 0.205%

    No Known Activations