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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and terms

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions and concepts related to statistics and probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vetted
    -0.81
     privacy
    -0.77
     grassroots
    -0.75
     wary
    -0.74
     philanthrop
    -0.73
     quir
    -0.73
     proactive
    -0.73
     ethics
    -0.71
     embroiled
    -0.71
     fundraising
    -0.71
    POSITIVE LOGITS
     ÎĶ
    1.02
     corresponds
    1.01
    \)
    0.99
     \(
    0.99
    orem
    0.96
    Figure
    0.93
     [(
    0.93
     \(\
    0.90
     computed
    0.89
     Calcul
    0.88
    Act Density 0.691%

    No Known Activations