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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a contrast or difference

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "other" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orney
    -0.66
     2024
    -0.63
     1915
    -0.61
    zai
    -0.61
    ony
    -0.60
     1937
    -0.60
    utenant
    -0.60
     1962
    -0.60
    etition
    -0.59
    PET
    -0.59
    POSITIVE LOGITS
    worldly
    1.94
    wise
    0.83
    world
    0.82
    parts
    0.81
    omon
    0.80
     kinds
    0.78
     aspects
    0.78
    swer
    0.76
     senses
    0.75
    iating
    0.74
    Act Density 0.108%

    No Known Activations