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

    Neuronpedia

    INDEX
    Explanations

    terminology related to programming and technology, such as programming languages, coding practices, and system components

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems, connections, and organization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angelo
    -0.79
    ufact
    -0.71
    avorite
    -0.70
    ©¶æ¥µ
    -0.66
    PDATE
    -0.65
    ãĤ¢ãĥ«
    -0.64
    owe
    -0.64
    76561
    -0.63
    ij士
    -0.61
    rake
    -0.61
    POSITIVE LOGITS
     Dialogue
    0.59
     motions
    0.57
     Pv
    0.57
    apters
    0.55
     folders
    0.55
     Perception
    0.52
    ourses
    0.52
    isively
    0.51
     modes
    0.51
     poles
    0.50
    Act Density 1.165%

    No Known Activations