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

    Neuronpedia

    INDEX
    Explanations

    references to political caucuses

    oai_token-act-pair · gpt-3.5-turbo

    references to caucuses in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    skinned
    -0.82
    comfort
    -0.71
    sa
    -0.71
    unc
    -0.70
    oric
    -0.69
    ahime
    -0.68
    ãĤ¨ãĥ«
    -0.68
    ews
    -0.67
    cus
    -0.66
    thin
    -0.66
    POSITIVE LOGITS
     caucus
    1.42
     caucuses
    1.26
     Caucus
    1.09
    goers
    0.98
    atoon
    0.85
    halla
    0.78
    eers
    0.75
     polls
    0.74
    naires
    0.74
     elector
    0.74
    Act Density 0.007%

    No Known Activations