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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases with a very strong emotional tone

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express strong opinions or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiz
    -0.81
     mosqu
    -0.79
    onga
    -0.73
     conduc
    -0.72
    usalem
    -0.70
    conservancy
    -0.70
    appropriately
    -0.68
    asha
    -0.67
     escort
    -0.67
    zens
    -0.66
    POSITIVE LOGITS
     Regardless
    1.15
     Nonetheless
    1.14
     Nevertheless
    1.13
     Especially
    1.12
     However
    1.07
     Whereas
    1.04
     Therefore
    1.02
     Fortunately
    1.00
     Though
    0.99
     Perhaps
    0.98
    Act Density 0.866%

    No Known Activations