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

    Neuronpedia

    INDEX
    Explanations

    sentences that express a sense of urgency or personal reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mergeFrom
    -0.57
     kasarigan
    -0.55
    Hentet
    -0.54
     snippetHide
    -0.53
    OGND
    -0.53
    Autoritní
    -0.53
     فريبيس
    -0.52
    InteropServices
    -0.48
    itinéraire
    -0.47
    iffance
    -0.45
    POSITIVE LOGITS
     ‘
    0.47
    …’
    0.45
    ’:
    0.42
    🏻‍♀️
    0.42
    ‘
    0.40
    🏻
    0.40
    ˾
    0.39
    ‍♂️
    0.38
     defStyleAttr
    0.38
    出版年
    0.38
    Act Density 1.656%

    No Known Activations