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

    Neuronpedia

    INDEX
    Explanations

    names of historical figures, particularly political leaders

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent political figures and historical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.85
    externalActionCode
    -0.78
    ĻĤ
    -0.77
    agram
    -0.77
    states
    -0.75
    HUD
    -0.72
     Janeiro
    -0.71
    gered
    -0.69
    lez
    -0.67
     Sharing
    -0.66
    POSITIVE LOGITS
     Thatcher
    0.84
     Downs
    0.82
     Majesty
    0.79
     Churchill
    0.74
    loo
    0.74
    ite
    0.73
    igham
    0.72
    oyal
    0.69
    essage
    0.68
     Beckham
    0.68
    Act Density 0.009%

    No Known Activations