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

    Neuronpedia

    INDEX
    Explanations

    positive actions and updates related to progress and changes in a system or project

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creasing
    -0.18
    eti
    -0.14
     pÅĻÃŃ
    -0.14
    geç
    -0.14
     suddenly
    -0.13
    achable
    -0.13
    /reset
    -0.13
    _sdk
    -0.13
    ä¼Ļ
    -0.13
     hurd
    -0.13
    POSITIVE LOGITS
     changes
    0.66
    changes
    0.58
     Changes
    0.54
    Changes
    0.52
     improvements
    0.47
    _changes
    0.46
     modifications
    0.45
    (changes
    0.41
     alterations
    0.38
     изменениÑı
    0.38
    Act Density 0.198%

    No Known Activations