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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning both sides or multiple entities in a comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Both" indicating comparisons or contrasts between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugu
    -0.82
    uez
    -0.79
    istle
    -0.75
    uable
    -0.75
    agine
    -0.74
    opian
    -0.73
    udic
    -0.72
    plete
    -0.71
    biz
    -0.71
    renheit
    -0.69
    POSITIVE LOGITS
     sexes
    1.33
     halves
    1.30
     sides
    1.25
     genders
    1.11
     parties
    1.05
     sets
    0.87
     kinds
    0.83
     ends
    0.81
     factions
    0.79
     thirds
    0.79
    Act Density 0.056%

    No Known Activations