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

    Neuronpedia

    INDEX
    Explanations

    elements related to character development and performance in films or shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.16
    ibbon
    -0.16
     Sez
    -0.15
    æ³³
    -0.15
    indow
    -0.15
    pta
    -0.15
    ammad
    -0.15
    owy
    -0.14
    hiro
    -0.14
    ório
    -0.14
    POSITIVE LOGITS
    帽
    0.16
    vla
    0.15
    vak
    0.14
     Elis
    0.14
     Bonds
    0.14
    Įĵ
    0.14
     mouseY
    0.13
     è·
    0.13
     Yates
    0.13
    ãĤ§
    0.13
    Act Density 0.029%

    No Known Activations