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

    Neuronpedia

    INDEX
    Explanations

    specific letters or codes associated with certain characters or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.73
     Савезне
    -0.47
    r
    -0.46
    u
    -0.42
     дописавши
    -0.42
    Ifc
    -0.41
    UnsafeEnabled
    -0.40
    p
    -0.40
    Референце
    -0.39
    at
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.75
    setVerticalGroup
    0.70
    :+:
    0.66
     &___
    0.63
     stället
    0.61
    fjspx
    0.60
    parsedMessage
    0.60
     المعيارى
    0.58
    writeFieldEnd
    0.58
    存于互联网档案馆
    0.58
    Act Density 0.262%

    No Known Activations