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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recognised
    -0.74
     recognise
    -0.72
     realised
    -0.72
     programme
    -0.70
     ageing
    -0.67
     civilisation
    -0.66
     realise
    -0.65
     concentrate
    -0.64
     endeavour
    -0.63
     downwards
    -0.63
    POSITIVE LOGITS
    ADVERTISEMENT
    1.26
    GOP
    0.86
     âĢķ
    0.84
    Sen
    0.77
    Trump
    0.75
    Ark
    0.73
    Morning
    0.73
     POLITICO
    0.72
    esson
    0.71
    Ore
    0.71
    Act Density 0.106%

    No Known Activations