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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to enhancements, progress, and betterment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vic
    -0.17
    kest
    -0.15
    ebek
    -0.14
    Suc
    -0.14
    enames
    -0.14
    noop
    -0.14
     Rut
    -0.14
    æĪ¶
    -0.14
    ually
    -0.13
    chedulers
    -0.13
    POSITIVE LOGITS
    etta
    0.20
     chances
    0.19
    ohl
    0.18
     sûr
    0.17
    -quality
    0.17
    /add
    0.17
    vements
    0.16
    /update
    0.16
    etto
    0.15
    vement
    0.15
    Act Density 0.032%

    No Known Activations