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

    Neuronpedia

    INDEX
    Explanations

    key concepts and themes related to models and learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haar
    -0.20
    aille
    -0.18
    ishi
    -0.15
    imity
    -0.14
    guns
    -0.14
    profit
    -0.14
    annie
    -0.14
    enido
    -0.14
    ining
    -0.14
    chten
    -0.14
    POSITIVE LOGITS
    odge
    0.18
     Nose
    0.16
     kurz
    0.15
    лам
    0.15
     rap
    0.15
     Ú©ÛĮÙĦ
    0.14
     ----------------------------------------------------------------------------↵
    0.14
    izik
    0.13
    remen
    0.13
    isser
    0.13
    Act Density 0.001%

    No Known Activations