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

    Neuronpedia

    INDEX
    Explanations

    countries and nationalities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.74
    ancies
    -0.71
    mble
    -0.68
    naissance
    -0.67
    earable
    -0.67
     activ
    -0.67
    verett
    -0.66
     bets
    -0.64
    IU
    -0.63
    itbart
    -0.63
    POSITIVE LOGITS
    istan
    0.95
     Erit
    0.93
    ese
    0.92
     Airways
    0.92
     Airlines
    0.90
    ican
    0.87
     Albania
    0.87
     Congo
    0.86
     Refugees
    0.86
    ian
    0.84
    Act Density 0.183%

    No Known Activations