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

    Neuronpedia

    INDEX
    Explanations

    words related to individuals such as names, pronouns, and possessives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.73
    icipated
    -0.71
    Scroll
    -0.66
    pleted
    -0.65
     Supports
    -0.64
    imentary
    -0.62
    ounter
    -0.62
    ð
    -0.62
     Additional
    -0.61
    ESE
    -0.61
    POSITIVE LOGITS
     certainly
    1.29
     undeniably
    1.14
     indeed
    1.13
     definitely
    1.07
     hardly
    1.07
     undoubtedly
    1.06
     surely
    1.03
     obviously
    1.02
     notoriously
    1.00
     ALWAYS
    1.00
    Act Density 0.490%

    No Known Activations