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

    Neuronpedia

    INDEX
    Explanations

    mentions of lawmakers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of lawmakers and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¨ãĥ«
    -0.89
    forest
    -0.69
    --+
    -0.69
    thritis
    -0.68
    Tur
    -0.67
    phal
    -0.67
    omorph
    -0.65
     Carbuncle
    -0.63
     Infinite
    -0.63
     Satanic
    -0.63
    POSITIVE LOGITS
    arians
    0.96
    hip
    0.95
    hips
    0.95
    woman
    0.93
    ervatives
    0.86
    interstitial
    0.82
    rences
    0.80
     unanimously
    0.79
     redist
    0.78
    itol
    0.76
    Act Density 0.028%

    No Known Activations