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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations or events

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a punctuation mark, particularly a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defe
    -0.83
     dips
    -0.80
     disemb
    -0.74
     babys
    -0.73
     renegoti
    -0.70
     toug
    -0.69
    aukee
    -0.69
     elbow
    -0.69
     graft
    -0.69
     temperament
    -0.69
    POSITIVE LOGITS
     Whilst
    1.62
     Firstly
    1.36
     Unfortunately
    1.29
     Needless
    1.28
     Interestingly
    1.27
     However
    1.27
     Additionally
    1.26
     Below
    1.26
     Furthermore
    1.24
     Luckily
    1.23
    Act Density 0.662%

    No Known Activations