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

    Neuronpedia

    INDEX
    Explanations

    dates written in a specific format (month/day/year) followed by a short description or event

    oai_token-act-pair · gpt-3.5-turbo

    the article 'a' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grounds
    -0.83
    Enjoy
    -0.79
    <?
    -0.76
    posts
    -0.74
    coins
    -0.73
    Engine
    -0.72
    ãĥ´
    -0.72
    Edit
    -0.71
    ettle
    -0.71
    EXP
    -0.71
    POSITIVE LOGITS
     lengthy
    1.11
     spate
    1.07
     protracted
    1.02
     flurry
    1.00
     concerted
    1.00
     slew
    1.00
     decade
    0.98
     brief
    0.98
     prolonged
    0.98
     successful
    0.95
    Act Density 0.173%

    No Known Activations