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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to computer programming and data management

    oai_token-act-pair · gpt-3.5-turbo

    discussions about complex systems and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lago
    -0.64
    boro
    -0.62
     mosqu
    -0.62
    DAY
    -0.61
    christ
    -0.60
    Legend
    -0.60
    ppa
    -0.59
     Saud
    -0.57
     chapel
    -0.57
     Ranch
    -0.56
    POSITIVE LOGITS
     inherently
    0.87
     inherent
    0.80
     importantly
    0.79
     intrinsically
    0.73
     broadly
    0.73
     fundamentally
    0.73
     intuitive
    0.70
     ultimately
    0.68
     ideally
    0.68
     necessarily
    0.68
    Act Density 1.908%

    No Known Activations