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

    Neuronpedia

    INDEX
    Explanations

    sentences with a recurring structure of introducing a topic followed by a statement or description

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hug
    -0.82
     portrait
    -0.77
     advis
    -0.75
     silent
    -0.73
     dictate
    -0.70
     administrator
    -0.69
     withd
    -0.69
     trusted
    -0.69
     posture
    -0.69
     lap
    -0.68
    POSITIVE LOGITS
     However
    1.28
     Unfortunately
    1.25
     Additionally
    1.25
     Interestingly
    1.18
     Meanwhile
    1.18
     Similarly
    1.17
     Fortunately
    1.15
     Luckily
    1.14
     Afterwards
    1.13
     Furthermore
    1.13
    Act Density 0.615%

    No Known Activations