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

    Neuronpedia

    INDEX
    Explanations

    instances where the text is marked or formatted in a specific way (e.g., symbols or characters representing a particular style)

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tram
    -0.79
     swall
    -0.77
    ©¶æ
    -0.74
     veter
    -0.72
     disciplines
    -0.72
     trump
    -0.70
     license
    -0.70
     therm
    -0.70
     behaviors
    -0.69
     dece
    -0.68
    POSITIVE LOGITS
    According
    1.30
    However
    1.27
    Since
    1.26
    Meanwhile
    1.26
    While
    1.26
    Speaking
    1.26
    Indeed
    1.23
    Among
    1.23
    Others
    1.23
    But
    1.22
    Act Density 0.304%

    No Known Activations