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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating ongoing actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uctose
    -0.16
     meg
    -0.15
    utar
    -0.15
    åħ¥åı£
    -0.15
    entry
    -0.15
    istrat
    -0.14
    ç²ī
    -0.14
    Ø®
    -0.14
    rets
    -0.13
    itty
    -0.13
    POSITIVE LOGITS
    oš
    0.14
    esco
    0.14
    fos
    0.14
    Spo
    0.14
    Trou
    0.14
    adt
    0.14
    436
    0.14
     Coat
    0.13
     Venture
    0.13
    _meas
    0.13
    Act Density 0.016%

    No Known Activations