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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals or businesses

    oai_token-act-pair · gpt-3.5-turbo

    references to David Bowie and concepts related to tailoring and laundry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essee
    -0.98
    ica
    -0.89
    ivity
    -0.87
    ative
    -0.86
    oran
    -0.85
    ions
    -0.83
    ansas
    -0.82
    icals
    -0.81
    iva
    -0.81
    ivities
    -0.80
    POSITIVE LOGITS
     blinded
    0.71
    BALL
    0.69
     Peninsula
    0.67
    mercial
    0.67
    pton
    0.67
     Wilde
    0.65
     propriet
    0.64
     lodge
    0.62
    plete
    0.61
    yang
    0.60
    Act Density 0.109%

    No Known Activations