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

    Neuronpedia

    INDEX
    Explanations

    references to specific people, particularly those named Sofia or Sophia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bail
    -0.16
     bail
    -0.15
    ickle
    -0.15
     dam
    -0.14
    iese
    -0.14
    ìŀĶ
    -0.14
    uel
    -0.14
     Bol
    -0.14
    .GetService
    -0.13
     Kann
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĥĨãĤ£
    0.17
    ãĥ¼ãĤ¯
    0.15
    ëŁī
    0.15
    eken
    0.14
    âu
    0.14
    ska
    0.14
    LOB
    0.14
    arov
    0.14
     Lightweight
    0.14
    ipped
    0.14
    Act Density 0.006%

    No Known Activations