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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or tagging structures within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kovi
    -0.19
    ovÃŃ
    -0.18
    oldown
    -0.15
    esktop
    -0.14
    ctal
    -0.14
     à¤Ńर
    -0.14
    ết
    -0.14
    ÑĪиб
    -0.14
    orgen
    -0.14
    ênh
    -0.14
    POSITIVE LOGITS
    idy
    0.19
     con
    0.15
     Hunger
    0.15
     lä
    0.15
    598
    0.15
    askan
    0.14
    ak
    0.14
    alach
    0.14
    into
    0.14
    chas
    0.14
    Act Density 0.002%

    No Known Activations