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

    Neuronpedia

    INDEX
    Explanations

    capital 'A' followed by a noun or noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the letter 'A' at the start of sentences or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anism
    -0.71
    antry
    -0.69
    Area
    -0.65
     Orient
    -0.65
     Abortion
    -0.63
     sights
    -0.63
    tones
    -0.61
     Mysteries
    -0.61
     Presents
    -0.60
     proceedings
    -0.60
    POSITIVE LOGITS
    cknowled
    1.46
    cknow
    1.31
    chie
    1.26
     lot
    1.18
     curs
    1.11
     glance
    0.99
    verages
    0.97
     drawback
    0.95
     caveat
    0.94
     recent
    0.94
    Act Density 0.188%

    No Known Activations