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

    Neuronpedia

    INDEX
    Explanations

    words related to limitations or parameters

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of" in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.46
     Cosponsors
    -0.45
     Pwr
    -0.44
    ertodd
    -0.42
     Quote
    -0.41
     partName
    -0.41
    dayName
    -0.40
     istg
    -0.40
    Enlarge
    -0.40
    Catalog
    -0.39
    POSITIVE LOGITS
     sorts
    0.64
     course
    0.61
     ours
    0.50
     theirs
    0.49
     those
    0.47
     hers
    0.46
     yours
    0.45
     the
    0.43
    course
    0.42
     these
    0.39
    Act Density 0.704%

    No Known Activations