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

    Neuronpedia

    INDEX
    Explanations

    words related to political delegates and their activities

    oai_token-act-pair · gpt-3.5-turbo

    references to delegates in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     à¨
    -0.78
     Bomber
    -0.75
    scape
    -0.72
    okin
    -0.70
    à¨
    -0.70
     Gim
    -0.69
     Seah
    -0.67
    à©
    -0.67
     commer
    -0.66
    MAT
    -0.66
    POSITIVE LOGITS
    legates
    1.30
     delegates
    1.06
     delegate
    0.96
    legate
    0.92
    aire
    0.88
    aires
    0.85
    ference
    0.84
     caucuses
    0.82
    esses
    0.81
    aucus
    0.81
    Act Density 0.024%

    No Known Activations