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

    Neuronpedia

    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly in the context of age or celebrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.59
     corrupt
    -0.51
     conflic
    -0.47
    icing
    -0.45
     volatile
    -0.45
    imately
    -0.44
    metadata
    -0.44
    ACP
    -0.44
    reads
    -0.44
     curfew
    -0.43
    POSITIVE LOGITS
     anecd
    0.59
     recommends
    0.54
    enegger
    0.50
     Brill
    0.50
     patent
    0.49
     recently
    0.48
     RELE
    0.48
     TED
    0.48
     patents
    0.48
    soDeliveryDate
    0.47
    Act Density 2.229%

    No Known Activations