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

    Neuronpedia

    INDEX
    Explanations

    statements or descriptions of various societal and political issues

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibles
    -0.75
    ©¶æ
    -0.75
    izons
    -0.75
    anyl
    -0.70
     Asgard
    -0.70
     miniature
    -0.67
     elig
    -0.66
    İĭ
    -0.65
    Ĥ¬
    -0.65
     hoard
    -0.63
    POSITIVE LOGITS
     Anyway
    1.05
     srfAttach
    0.89
     Nevertheless
    0.87
    Anyway
    0.84
     Nonetheless
    0.83
     Interestingly
    0.82
     Similarly
    0.81
     Fortunately
    0.80
     Lastly
    0.78
     Besides
    0.78
    Act Density 0.124%

    No Known Activations