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

    Neuronpedia

    INDEX
    Explanations

    acronyms and proper nouns related to organizations or political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or entities involved in political or governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chest
    -0.98
    lets
    -0.90
    stocks
    -0.78
    gery
    -0.76
    gers
    -0.75
     Strait
    -0.74
    geant
    -0.73
    strap
    -0.72
    ger
    -0.71
    bull
    -0.71
    POSITIVE LOGITS
     NEC
    1.06
    ESS
    1.01
    ODE
    0.98
    ISION
    0.95
    IZ
    0.94
    ORN
    0.92
    OUN
    0.89
    ORD
    0.88
    IVES
    0.88
     reluct
    0.86
    Act Density 0.022%

    No Known Activations