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

    Neuronpedia

    INDEX
    Explanations

    code or programming-related terms, particularly involving errors and data structures

    oai_token-act-pair · gpt-3.5-turbo

    underscores that are part of variable names or identifiers in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Casey
    -0.81
     JPM
    -0.78
     Eggs
    -0.77
     Pearce
    -0.77
     Leilan
    -0.76
     Cutting
    -0.75
     Manson
    -0.74
     Vide
    -0.74
     Sachs
    -0.73
    quished
    -0.72
    POSITIVE LOGITS
    modules
    1.18
    mode
    1.18
    gradient
    1.17
    chance
    1.16
    enabled
    1.15
    func
    1.15
    index
    1.15
    type
    1.15
    prefix
    1.14
    pressed
    1.14
    Act Density 0.024%

    No Known Activations