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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to relevance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ston
    -0.17
    maal
    -0.16
    ecycle
    -0.15
    rador
    -0.14
     finalize
    -0.14
    LOBAL
    -0.14
    ymes
    -0.13
     ov
    -0.13
    ayo
    -0.13
    mdi
    -0.13
    POSITIVE LOGITS
    oles
    0.17
    ening
    0.15
    etÃŃ
    0.15
    etrics
    0.15
    ubit
    0.15
    þ
    0.15
    ekce
    0.14
    les
    0.14
     WithEvents
    0.14
    etter
    0.14
    Act Density 0.014%

    No Known Activations