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

    Neuronpedia

    INDEX
    Explanations

    quotations and reported speech marked by punctuation and phrases indicating communication

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation in a variety of formats and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otin
    -0.75
     discard
    -0.66
    lor
    -0.65
     tide
    -0.65
     expiration
    -0.62
    acea
    -0.61
    roo
    -0.61
    oult
    -0.59
     beneficiaries
    -0.59
    rely
    -0.58
    POSITIVE LOGITS
    iott
    0.73
    VICE
    0.72
     Juliet
    0.72
     Hardcore
    0.72
     Observer
    0.71
    iasm
    0.70
     Radio
    0.69
     Correspond
    0.69
    imes
    0.65
    icter
    0.62
    Act Density 0.243%

    No Known Activations