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

    Neuronpedia

    INDEX
    Explanations

    instances where it is deemed important to take note of specific information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of noting something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atan
    -0.73
    ravel
    -0.71
    quer
    -0.70
    atom
    -0.67
    namese
    -0.67
    iffe
    -0.66
    soever
    -0.65
    oing
    -0.64
    adesh
    -0.64
    estern
    -0.63
    POSITIVE LOGITS
    ably
    0.83
    books
    0.79
    lessly
    0.75
    book
    0.73
     how
    0.72
    ATURE
    0.70
     noting
    0.69
     Keeper
    0.69
    BOOK
    0.69
    ATURES
    0.68
    Act Density 0.013%

    No Known Activations