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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Lamborghini"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Lam" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.70
     Subtle
    -0.64
    GROUND
    -0.63
    ãģį
    -0.63
     steroid
    -0.60
     union
    -0.60
     gradient
    -0.59
    HEAD
    -0.58
    ģĸ
    -0.58
     wart
    -0.57
    POSITIVE LOGITS
    borgh
    1.59
    inated
    1.09
    bs
    1.02
    oufl
    1.01
    iami
    1.00
    othe
    0.99
    pling
    0.99
    ont
    0.98
    essage
    0.97
    endment
    0.97
    Act Density 0.037%

    No Known Activations