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

    Neuronpedia

    INDEX
    Explanations

    numbers related to physical weight or quantity

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing skepticism or irony, particularly regarding societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palestin
    -0.73
     mathemat
    -0.72
     elig
    -0.70
     prolifer
    -0.67
     incorpor
    -0.66
     blitz
    -0.64
     pyramid
    -0.63
     conspicuous
    -0.62
     scattering
    -0.62
     notor
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.12
    ï¸
    0.90
    ever
    0.83
    iversary
    0.81
    eal
    0.76
    mas
    0.76
    weed
    0.74
    sed
    0.72
    âĶĢâĶĢâĶĢâĶĢ
    0.71
    laughs
    0.71
    Act Density 0.488%

    No Known Activations