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

    Neuronpedia

    INDEX
    Explanations

    words separated by symbols like "Ċ" hinting at the presence of special characters within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant actions occurring in community settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aditional
    -0.72
     metic
    -0.70
     tremend
    -0.68
     eleph
    -0.66
    ortunately
    -0.65
    senal
    -0.62
     undermin
    -0.62
     practition
    -0.61
     proport
    -0.59
     exha
    -0.57
    POSITIVE LOGITS
    Scroll
    0.73
    DragonMagazine
    0.70
    NULL
    0.70
    thinkable
    0.68
    ³³³³³³³³
    0.68
    Els
    0.67
     isEnabled
    0.66
    ³³³³
    0.66
    Chel
    0.65
    ³³³³³³³³³³³³³³³³
    0.65
    Act Density 0.481%

    No Known Activations