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

    Neuronpedia

    INDEX
    Explanations

    mentions of countries' independence and related historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hubb
    -0.15
    ingo
    -0.14
    endar
    -0.14
    гл
    -0.14
     Cosby
    -0.14
    itary
    -0.14
    ocket
    -0.13
    ÃŃr
    -0.13
    olik
    -0.13
    arya
    -0.13
    POSITIVE LOGITS
     independence
    0.77
     Independence
    0.68
    Independ
    0.66
     independ
    0.59
    çĭ¬ç«ĭ
    0.53
     independent
    0.52
    Independent
    0.47
     Independent
    0.47
     Independ
    0.47
    -independent
    0.44
    Act Density 0.146%

    No Known Activations