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

    Neuronpedia

    INDEX
    Explanations

    special characters or unique symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Georgetown
    -0.15
     Ferrari
    -0.15
    instein
    -0.14
    apiro
    -0.14
     Huang
    -0.14
     Hoover
    -0.14
    ospels
    -0.14
    ä¸Ī
    -0.14
    ız
    -0.14
     Acceler
    -0.14
    POSITIVE LOGITS
     Sans
    0.34
     Roose
    0.29
     Jaime
    0.29
     Bri
    0.29
     Ser
    0.28
     Ary
    0.28
     Tyr
    0.28
     Bron
    0.27
     Bran
    0.27
     Cer
    0.26
    Act Density 0.004%

    No Known Activations