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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names related to politics, government, and international affairs

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms or references to entities and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ournals
    -0.83
    cloth
    -0.72
    agues
    -0.70
    Compare
    -0.69
     Compare
    -0.68
    lin
    -0.67
    lator
    -0.67
     apart
    -0.66
    roup
    -0.66
    cells
    -0.65
    POSITIVE LOGITS
     insistence
    1.30
     refusal
    1.28
     inability
    1.28
     unwillingness
    1.24
     involvement
    1.23
     willingness
    1.20
     efforts
    1.18
     penchant
    1.17
     reluctance
    1.16
     assertion
    1.14
    Act Density 0.288%

    No Known Activations