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

    Neuronpedia

    INDEX
    Explanations

    decimal numbers and numerical patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.14
    è¡
    -0.14
    üçük
    -0.14
     targetType
    -0.14
    lotte
    -0.14
    lage
    -0.14
     Mej
    -0.14
    obuf
    -0.13
    scribed
    -0.13
    plier
    -0.13
    POSITIVE LOGITS
    CHIP
    0.16
    ãĥ¼ãĥĵ
    0.15
    jeta
    0.15
    rosso
    0.15
    htable
    0.15
    orman
    0.14
     Jay
    0.14
    urum
    0.14
    elf
    0.14
     Deck
    0.14
    Act Density 0.130%

    No Known Activations