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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erman
    -0.21
    esse
    -0.17
    ying
    -0.17
    lint
    -0.16
    nio
    -0.15
    ãĥ¥ãĥ¼
    -0.14
    ãģ®ãģ¯
    -0.14
    etch
    -0.14
    iced
    -0.14
    ogenerated
    -0.14
    POSITIVE LOGITS
    readcr
    0.18
    smith
    0.18
    undance
    0.15
    TEGER
    0.15
    ongan
    0.15
    gow
    0.14
    .uk
    0.14
    ensively
    0.14
    о
    0.14
    acer
    0.14
    Act Density 0.240%

    No Known Activations