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

    Neuronpedia

    INDEX
    Explanations

    end-of-sentence punctuation and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isposable
    -0.15
    shortcode
    -0.15
    abyrinth
    -0.15
    kke
    -0.15
    andWhere
    -0.14
    ungs
    -0.14
    uncate
    -0.14
    .quality
    -0.14
     Tick
    -0.14
    offee
    -0.13
    POSITIVE LOGITS
    Argb
    0.15
    omit
    0.14
     duplic
    0.14
     åįĥ
    0.14
     ãĤ¬
    0.14
    óng
    0.13
    gross
    0.13
     Vlad
    0.13
    DDS
    0.13
     forKey
    0.13
    Act Density 0.030%

    No Known Activations