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

    Neuronpedia

    INDEX
    Explanations

    terms related to software development, particularly around tracking and managing errors and program states

    oai_token-act-pair · gpt-3.5-turbo

    references to current and previous states or values in a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gging
    -0.79
    leaders
    -0.76
     Schwe
    -0.72
    Sov
    -0.71
    NEWS
    -0.71
    spirit
    -0.70
    NEY
    -0.70
     whistleblowers
    -0.69
    perse
    -0.68
    HCR
    -0.68
    POSITIVE LOGITS
     decimal
    0.94
     node
    0.94
     ancestor
    0.93
     (<
    0.87
     layer
    0.84
     iteration
    0.82
     vertex
    0.80
     dataset
    0.79
     integer
    0.79
     occurrence
    0.79
    Act Density 0.219%

    No Known Activations