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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and economic situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or unpredictability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zona
    -0.66
     authorize
    -0.66
    anus
    -0.66
    boro
    -0.64
    eca
    -0.63
    feed
    -0.62
     utilized
    -0.61
     discharge
    -0.61
     Tradable
    -0.61
    eco
    -0.60
    POSITIVE LOGITS
    Meanwhile
    1.05
    ccording
    0.98
    Experts
    0.92
    JUST
    0.87
    Speaking
    0.86
    Earlier
    0.86
    Officials
    0.81
    Despite
    0.81
     Britons
    0.80
     Ange
    0.79
    Act Density 0.141%

    No Known Activations