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

    Neuronpedia

    INDEX
    Explanations

    words related to unity or togetherness in a political or communal context

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of unity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    200000
    -0.70
    Reading
    -0.69
    Journal
    -0.69
    ECH
    -0.67
     Journalists
    -0.66
    Notable
    -0.66
    ================================================================
    -0.66
    cigarette
    -0.65
    odor
    -0.64
     Hastings
    -0.63
    POSITIVE LOGITS
     unity
    1.23
    iversal
    0.99
    halla
    0.94
     unification
    0.92
     harmony
    0.88
     cohesion
    0.85
    unity
    0.79
    eous
    0.76
    hall
    0.74
    nect
    0.74
    Act Density 0.008%

    No Known Activations