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

    Neuronpedia

    INDEX
    Explanations

    quotations or spoken dialogue

    oai_token-act-pair · gpt-3.5-turbo

    quoted statements or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favour
    -0.92
     favourable
    -0.89
     favoured
    -0.83
     authorised
    -0.77
     analys
    -0.73
     mediated
    -0.72
     criticised
    -0.70
     parliamentary
    -0.69
     imperialist
    -0.69
     Corbyn
    -0.68
    POSITIVE LOGITS
    Hopefully
    1.37
    Everybody
    1.31
    Obviously
    1.27
    Absolutely
    1.23
    Certainly
    1.21
     Hopefully
    1.15
    Basically
    1.13
    We
    1.11
    They
    1.10
    Kids
    1.08
    Act Density 0.298%

    No Known Activations