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

    Neuronpedia

    INDEX
    Explanations

    references to alternative options or additional possibilities

    oai_token-act-pair · gpt-3.5-turbo

    references to alternative options or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenant
    -0.74
    ony
    -0.67
    opus
    -0.65
     ç¥ŀ
    -0.65
    cape
    -0.64
    zai
    -0.62
    ouf
    -0.61
     1915
    -0.61
    aban
    -0.61
     EVEN
    -0.61
    POSITIVE LOGITS
    worldly
    2.02
     kinds
    1.08
     aspects
    1.05
     countries
    1.04
     types
    0.99
     avenues
    0.99
     factors
    0.99
     forms
    0.95
     continents
    0.94
    wise
    0.93
    Act Density 0.108%

    No Known Activations