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

    Neuronpedia

    INDEX
    Explanations

    important capitalized nouns or phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "THE"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fired
    -0.73
    ulsion
    -0.69
    iod
    -0.67
    olt
    -0.67
    opol
    -0.67
    auc
    -0.66
    fitting
    -0.65
     Judith
    -0.64
    pport
    -0.63
    ãĥĥãĥĪ
    -0.62
    POSITIVE LOGITS
    ORY
    1.17
    ISM
    1.06
     STORY
    1.02
    oret
    0.98
     LAST
    0.96
     IMAGES
    0.92
    ATER
    0.91
     Basics
    0.91
     PRESIDENT
    0.90
     DARK
    0.89
    Act Density 0.011%

    No Known Activations