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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Wright."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inators
    -0.83
    uate
    -0.75
    ãĥ´
    -0.74
    alities
    -0.73
    abwe
    -0.72
    amaz
    -0.72
    ators
    -0.71
    ATES
    -0.68
    och
    -0.68
    icts
    -0.66
    POSITIVE LOGITS
    esome
    0.89
    yard
    0.84
     Wright
    0.81
    wright
    0.78
    edge
    0.76
    sburg
    0.76
    y
    0.76
    nut
    0.74
     Mills
    0.74
     Industries
    0.73
    Act Density 0.031%

    No Known Activations