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

    Neuronpedia

    INDEX
    Explanations

    pairs of values and their corresponding indices in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ä«
    -0.14
    addtogroup
    -0.14
    ACS
    -0.14
    akh
    -0.13
    Manifest
    -0.13
    oho
    -0.13
    Sink
    -0.13
    ixa
    -0.13
    glass
    -0.13
    ÈĻ
    -0.13
    POSITIVE LOGITS
     Lever
    0.17
    raquo
    0.17
     pragma
    0.16
    anut
    0.15
    assi
    0.15
     guards
    0.15
    ENUM
    0.14
    ENSE
    0.14
    isin
    0.14
    tep
    0.14
    Act Density 0.044%

    No Known Activations