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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to persons or places

    oai_token-act-pair · gpt-3.5-turbo

    references to "Islam" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bats
    -0.76
     Zot
    -0.60
     corrid
    -0.58
    session
    -0.56
     Rockies
    -0.55
     ACTIONS
    -0.54
     Bloody
    -0.54
     succeeding
    -0.54
     incent
    -0.54
     lodge
    -0.53
    POSITIVE LOGITS
    ibo
    0.87
    orio
    0.86
    iaz
    0.81
    uable
    0.76
    omal
    0.74
    auri
    0.71
    hya
    0.70
    STEM
    0.70
    wer
    0.69
    eni
    0.69
    Act Density 0.066%

    No Known Activations