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

    Neuronpedia

    INDEX
    Explanations

    specific names or proper nouns, likely related to academic or scientific references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bourgoin
    -0.74
     ​​
    -0.69
     harian
    -0.68
     vendas
    -0.66
     
    -0.66
    位
    -0.65
     ovan
    -0.64
     McLaughlin
    -0.64
    auen
    -0.63
     Mine
    -0.62
    POSITIVE LOGITS
    Ayy
    1.18
     Azz
    1.09
     OSS
    1.06
    ABB
    1.05
     ABB
    1.04
     Utt
    1.04
     NCC
    1.00
     EDD
    1.00
    pp
    0.99
    edd
    0.99
    Act Density 1.156%

    No Known Activations