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

    Neuronpedia

    INDEX
    Explanations

    high-importance proper nouns and technical terms, especially in specific contexts such as programming or cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å±±å¸Ĥ
    -0.15
    preter
    -0.14
    ourg
    -0.14
    lea
    -0.14
    uj
    -0.14
     пен
    -0.14
    abet
    -0.14
    inia
    -0.13
     ë¡
    -0.13
    kus
    -0.13
    POSITIVE LOGITS
    ÂĿ
    0.15
    ghan
    0.14
    arde
    0.14
    plain
    0.13
    =batch
    0.13
    udes
    0.13
    unn
    0.13
    :>
    0.13
    ·
    0.13
    undred
    0.13
    Act Density 0.055%

    No Known Activations