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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to historic figures and political leaders

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals named Winston

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.85
    loo
    -0.82
    estial
    -0.79
    ois
    -0.78
    gy
    -0.78
    folk
    -0.73
    bies
    -0.71
    oras
    -0.71
    iris
    -0.70
    uria
    -0.68
    POSITIVE LOGITS
    ufact
    0.83
    nee
    0.76
    forcement
    0.74
    heit
    0.73
     Oaks
    0.72
    PLIED
    0.71
    agement
    0.71
    alez
    0.70
     compr
    0.69
    entimes
    0.68
    Act Density 0.105%

    No Known Activations