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

    Neuronpedia

    INDEX
    Explanations

    terms related to flags, particularly those indicating status or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DBG
    -0.17
    scape
    -0.15
    maal
    -0.15
    olk
    -0.15
    itin
    -0.15
    ive
    -0.15
    Facade
    -0.15
    ronics
    -0.14
    ãĥīãĥ«
    -0.14
    zend
    -0.14
    POSITIVE LOGITS
    ging
    0.35
    pole
    0.32
    staff
    0.32
    rant
    0.29
    ships
    0.27
    ged
    0.27
    ship
    0.26
    ellant
    0.24
    ellar
    0.23
    .DEFINE
    0.23
    Act Density 0.017%

    No Known Activations