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

    Neuronpedia

    INDEX
    Explanations

    country names

    oai_token-act-pair · gpt-3.5-turbo

    country names or references to nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ«
    -0.70
    TA
    -0.69
    kt
    -0.68
    atu
    -0.67
    sta
    -0.67
    ista
    -0.67
    Ult
    -0.66
    Tan
    -0.66
    Tab
    -0.65
     Tab
    -0.64
    POSITIVE LOGITS
    gray
    0.85
    311
    0.79
    GN
    0.78
    310
    0.77
    Gray
    0.76
    GP
    0.74
     Gre
    0.73
    361
    0.73
    hin
    0.73
     Gray
    0.72
    Act Density 0.468%

    No Known Activations