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

    Neuronpedia

    INDEX
    Explanations

    references to options or choices available to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.73
     '\\;'
    -0.71
    ThroughAttribute
    -0.65
     Mahar
    -0.61
     useDispatch
    -0.59
     الرياضيه
    -0.59
     EnglishChoose
    -0.58
     SwiftUI
    -0.58
     PTT
    -0.58
     Eſ
    -0.58
    POSITIVE LOGITS
    lavia
    0.50
    leistungs
    0.47
    vature
    0.47
    iley
    0.45
    gods
    0.44
    ppone
    0.43
    raine
    0.43
    tefan
    0.43
    ценка
    0.42
    mstyle
    0.42
    Act Density 0.156%

    No Known Activations