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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the configuration or setup of a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owing
    -0.17
    ately
    -0.17
     Moor
    -0.17
    oure
    -0.16
    bian
    -0.15
    ones
    -0.15
    íĥ
    -0.15
    wick
    -0.15
    t
    -0.15
    oral
    -0.15
    POSITIVE LOGITS
    pers
    0.22
    ãģ°
    0.20
    /down
    0.17
    ILON
    0.17
    atron
    0.17
    datable
    0.16
    dater
    0.16
    uations
    0.16
    ilon
    0.16
    gradable
    0.16
    Act Density 0.038%

    No Known Activations