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

    Neuronpedia

    INDEX
    Explanations

    references to scores and scoring in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekil
    -0.19
    orp
    -0.18
    ait
    -0.16
    ector
    -0.16
    ìĤ¬íķŃ
    -0.15
    uu
    -0.15
    ENCHMARK
    -0.15
    lad
    -0.15
    oral
    -0.15
    ault
    -0.15
    POSITIVE LOGITS
    card
    0.21
    cards
    0.20
    occo
    0.19
    boards
    0.19
    rupa
    0.17
    ycastle
    0.17
    -UA
    0.16
    board
    0.16
    agli
    0.16
    ุà¸ĩ
    0.16
    Act Density 0.016%

    No Known Activations