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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of opinion or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     only
    -0.18
    only
    -0.15
     pretty
    -0.14
    ceased
    -0.14
    lut
    -0.14
     Only
    -0.14
    weets
    -0.14
     =
    -0.14
     seulement
    -0.14
    CB
    -0.13
    POSITIVE LOGITS
    onet
    0.17
     exactly
    0.17
    оÑĢи
    0.17
    enet
    0.16
    (æľ¨
    0.16
     Exactly
    0.15
    FileVersion
    0.15
    ÄįÃŃ
    0.14
    gain
    0.14
     ELSE
    0.14
    Act Density 0.077%

    No Known Activations