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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ound
    -0.15
    uten
    -0.15
     кл
    -0.15
     Bez
    -0.15
    borough
    -0.15
    ou
    -0.14
    aksi
    -0.14
    und
    -0.14
    itize
    -0.14
    æ³ģ
    -0.14
    POSITIVE LOGITS
    以ä¸Ĭ
    0.18
    -plus
    0.16
    ymce
    0.15
    IAS
    0.14
    ÙħÙĤ
    0.14
    Ä©
    0.14
    annel
    0.14
    ινή
    0.14
    s
    0.14
    .Tween
    0.13
    Act Density 0.298%

    No Known Activations