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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "goodness" and related concepts of morality or virtue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ottie
    -0.15
    ÃŃrk
    -0.14
    Exposed
    -0.14
    bubble
    -0.14
    cab
    -0.14
    _Filter
    -0.14
    CHO
    -0.13
    инов
    -0.13
     Callable
    -0.13
    ItemId
    -0.13
    POSITIVE LOGITS
    bye
    0.18
    eker
    0.16
    ëĭ´
    0.15
    och
    0.15
    ride
    0.15
    iage
    0.14
     Premi
    0.14
    rides
    0.14
    ãĥ¼ãĥĹ
    0.14
    ypsum
    0.14
    Act Density 0.008%

    No Known Activations