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

    Neuronpedia

    INDEX
    Explanations

    words related to unanticipated outcomes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izations
    -0.16
    usz
    -0.15
    ä¸į好
    -0.15
    isations
    -0.14
    utto
    -0.14
    วà¸ĩ
    -0.14
    izers
    -0.14
    eren
    -0.14
    689
    -0.14
    ä¸įåIJĮçļĦ
    -0.14
    POSITIVE LOGITS
    /un
    0.34
    ably
    0.22
    ly
    0.20
    /il
    0.20
    edly
    0.19
     yet
    0.17
    /non
    0.17
    (Un
    0.17
    /not
    0.16
    ingly
    0.16
    Act Density 0.114%

    No Known Activations