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

    Neuronpedia

    INDEX
    Explanations

    expressions of improvement or suggestions for betterment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LIKELY
    -0.15
    USR
    -0.15
     Stateless
    -0.15
     ucwords
    -0.14
    íĥ
    -0.14
    obl
    -0.14
    Variable
    -0.14
    utters
    -0.14
    TN
    -0.14
    é¡ĺãģĦ
    -0.14
    POSITIVE LOGITS
    harma
    0.18
    etur
    0.15
    ullo
    0.15
    aData
    0.14
     Midi
    0.14
     Wick
    0.14
     Nik
    0.14
     Jarvis
    0.14
    ाà¤Ĺत
    0.14
    avel
    0.13
    Act Density 0.129%

    No Known Activations