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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diversity and a variety of options or choices

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to variety, stability, and balance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.58
    Library
    -0.58
    ICLE
    -0.56
     Sect
    -0.55
     ADA
    -0.55
    Il
    -0.55
     majority
    -0.54
    onga
    -0.54
     Principal
    -0.54
    Corn
    -0.53
    POSITIVE LOGITS
    fulness
    1.20
    iness
    1.04
    lessness
    0.99
    iveness
    0.93
    FUL
    0.89
    abl
    0.86
    liness
    0.86
    worthiness
    0.85
    lust
    0.84
    ability
    0.83
    Act Density 0.463%

    No Known Activations