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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "define" and its variations to identify discussions about definition and clarification of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stm
    -0.16
    ordin
    -0.15
    eros
    -0.14
     finally
    -0.14
    ilet
    -0.14
    idge
    -0.14
    ero
    -0.14
    foundland
    -0.14
    eras
    -0.14
    465
    -0.14
    POSITIVE LOGITS
    -ÑĤо
    0.16
    636
    0.15
    arton
    0.14
    istrov
    0.14
    hower
    0.14
    ÑĮомÑĥ
    0.14
    /method
    0.13
    purpose
    0.13
    vÄĽt
    0.13
    ChangeListener
    0.13
    Act Density 0.062%

    No Known Activations