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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &___
    -0.73
    ndorf
    -0.58
    ReusableCell
    -0.57
    hundreds
    -0.56
     Regel
    -0.55
    dollis
    -0.53
    nearby
    -0.53
    Activités
    -0.52
    Ecotoxicity
    -0.52
    IDENTAL
    -0.52
    POSITIVE LOGITS
     ſtate
    0.74
     تضيفلها
    0.71
     houſe
    0.68
     faſt
    0.67
     perſon
    0.64
     Anſ
    0.61
     Inſ
    0.58
     ſta
    0.58
     ſen
    0.58
     kautta
    0.56
    Act Density 0.301%

    No Known Activations