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

    Neuronpedia

    INDEX
    Explanations

    keywords related to structure or organization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to structure and organizational frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BACK
    -0.71
     thirds
    -0.68
     Wynne
    -0.62
     Sisters
    -0.59
     steep
    -0.59
     foremost
    -0.59
    FORE
    -0.58
     Leone
    -0.56
    butt
    -0.56
     Ashe
    -0.55
    POSITIVE LOGITS
    ured
    2.55
    ures
    2.44
    uring
    2.30
    urer
    2.15
    urers
    2.10
    ure
    2.07
    urally
    2.07
    uration
    1.86
    ural
    1.84
    urable
    1.83
    Act Density 0.078%

    No Known Activations