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

    Neuronpedia

    INDEX
    Explanations

    programming libraries or commands in a text document

    oai_token-act-pair · gpt-3.5-turbo

    mentions of software libraries and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.80
     Oaks
    -0.75
    SPONSORED
    -0.70
     Falls
    -0.67
     Payton
    -0.67
     Pearce
    -0.67
     Forever
    -0.66
    theless
    -0.65
     Frontier
    -0.65
     Dakota
    -0.65
    POSITIVE LOGITS
     lib
    1.19
    itionally
    0.88
    virt
    0.88
    itions
    0.88
    ensibly
    0.86
    ensible
    0.85
     Lib
    0.85
    itives
    0.85
    roth
    0.81
    roxy
    0.81
    Act Density 0.003%

    No Known Activations