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

    Neuronpedia

    INDEX
    Explanations

    specific characters or symbols from non-English languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opleft
    -0.17
    onda
    -0.16
    atcher
    -0.15
    füg
    -0.15
    ãĥªãĤ«
    -0.14
    OfWork
    -0.14
    å¨ĺ
    -0.14
    aney
    -0.14
    анÑĮ
    -0.14
    SELL
    -0.14
    POSITIVE LOGITS
    nger
    0.22
    mp
    0.21
    nd
    0.19
    nce
    0.18
    mb
    0.18
    egers
    0.17
    ÈĻi
    0.17
    ng
    0.16
    i
    0.16
    ÅŁi
    0.15
    Act Density 0.004%

    No Known Activations