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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and references to self

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .utf
    -0.14
    isky
    -0.14
     вдÑĢÑĥг
    -0.14
    ÑĤен
    -0.14
    à¸ģรรม
    -0.13
    ospital
    -0.13
    ï¼ħ
    -0.13
    ä¸īä¸ī
    -0.13
    ìĩ
    -0.13
     ðŁĻĤ↵↵
    -0.13
    POSITIVE LOGITS
    pong
    0.14
    ehir
    0.14
    sez
    0.14
    ees
    0.14
    MSG
    0.13
     Ay
    0.13
     Vin
    0.13
    .net
    0.13
    erah
    0.13
    .Net
    0.13
    Act Density 0.076%

    No Known Activations