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

    Neuronpedia

    INDEX
    Explanations

    sports-related terms, particularly related to player movements and team activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods that signal the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.81
     imagining
    -0.77
     invent
    -0.76
     haunted
    -0.74
     scept
    -0.73
     ingenuity
    -0.73
     dared
    -0.72
    illions
    -0.72
     lately
    -0.71
    obyl
    -0.71
    POSITIVE LOGITS
     Sources
    1.08
    Sources
    1.04
    Prior
    1.02
    According
    1.01
     According
    1.00
     Prior
    0.99
    Statement
    0.99
     Previously
    0.98
    BRE
    0.97
    Assistant
    0.94
    Act Density 0.341%

    No Known Activations