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

    Neuronpedia

    INDEX
    Explanations

    proper nouns in the context of news articles or similar texts

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Se" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.97
     diplom
    -0.80
    INGTON
    -0.79
     CPC
    -0.73
    £ı
    -0.73
     hoops
    -0.71
    doms
    -0.68
    iants
    -0.67
    70710
    -0.67
     paved
    -0.66
    POSITIVE LOGITS
    eker
    1.23
    vere
    1.15
    ldom
    1.07
    eps
    1.03
    ethe
    1.02
    gments
    0.98
    emed
    0.98
    gment
    0.98
    asons
    0.97
    gregation
    0.96
    Act Density 0.009%

    No Known Activations