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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs related to looking and perceiving

    oai_token-act-pair · gpt-3.5-turbo

    references to perspectives and viewpoints regarding situations or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unci
    -0.62
    legate
    -0.61
    indal
    -0.59
    edes
    -0.59
    isma
    -0.58
    bia
    -0.58
    packages
    -0.57
    Ĥİ
    -0.57
    Wars
    -0.57
    arters
    -0.57
    POSITIVE LOGITS
     objectively
    1.00
     skept
    1.00
     differently
    0.95
     favorably
    0.91
     mirror
    0.88
     disappro
    0.86
     suspicious
    0.86
     hindsight
    0.86
    orescent
    0.82
     nostalg
    0.81
    Act Density 0.211%

    No Known Activations