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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dates and historical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zby
    -0.16
    íĺij
    -0.15
    .argument
    -0.15
     ÑģÑĤÑĢанÑĭ
    -0.15
    åij¢
    -0.15
    amera
    -0.14
    yslu
    -0.14
     ÏĦαιν
    -0.14
    sled
    -0.14
    lal
    -0.14
    POSITIVE LOGITS
     suo
    0.21
    lo
    0.20
     primo
    0.18
    inea
    0.18
    uso
    0.17
    lean
    0.17
     nostro
    0.17
     secondo
    0.17
    imit
    0.16
     ru
    0.16
    Act Density 0.006%

    No Known Activations