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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and the format of scholarly references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ua
    -0.19
    ró
    -0.19
     Blind
    -0.17
    etÃŃ
    -0.17
     blind
    -0.15
    éĸĵãģ«
    -0.15
    -blind
    -0.15
     sovere
    -0.15
    ombok
    -0.14
    899
    -0.14
    POSITIVE LOGITS
    tej
    0.15
    361
    0.15
    asar
    0.14
    avras
    0.14
    Millis
    0.14
    宫
    0.14
    incerely
    0.14
    ieu
    0.14
    fu
    0.14
     hatta
    0.13
    Act Density 0.004%

    No Known Activations