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

    Neuronpedia

    INDEX
    Explanations

    references to dates and numerical sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Julian
    -0.15
    -Jul
    -0.15
    ÙİÙī
    -0.14
    егод
    -0.14
    転
    -0.14
    jÃł
    -0.14
    аÑĤо
    -0.14
    éºĹ
    -0.13
    ivan
    -0.13
     smr
    -0.13
    POSITIVE LOGITS
    .gg
    0.17
    amat
    0.15
     stir
    0.15
     Stir
    0.15
    辺
    0.14
    anton
    0.14
    838
    0.14
     INTERRUPTION
    0.14
    173
    0.14
    erra
    0.14
    Act Density 0.014%

    No Known Activations