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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unity, partnership, and relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of union in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gone
    -0.68
    irin
    -0.66
    othermal
    -0.66
    trak
    -0.66
    cale
    -0.66
    apons
    -0.66
    trop
    -0.65
    warm
    -0.65
    crow
    -0.65
    tics
    -0.65
    POSITIVE LOGITS
     feder
    1.02
     federation
    0.95
    Union
    0.92
     Confederation
    0.87
     union
    0.85
     Union
    0.77
    istic
    0.75
     anthem
    0.75
    union
    0.75
    ism
    0.74
    Act Density 0.012%

    No Known Activations