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

    Neuronpedia

    INDEX
    Explanations

    words related to political or social unity

    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
    ================================================================
    -0.78
    apons
    -0.73
    nov
    -0.71
    resp
    -0.68
    VR
    -0.67
    200000
    -0.67
    nit
    -0.66
    ECH
    -0.66
    aches
    -0.66
    Consumer
    -0.65
    POSITIVE LOGITS
     unity
    0.94
    arity
    0.90
     cohesion
    0.83
     harmony
    0.82
    iversal
    0.79
    halla
    0.78
     unification
    0.78
    ification
    0.74
    fuck
    0.73
    yip
    0.72
    Act Density 0.012%

    No Known Activations