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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs in structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.94
    Diweddarwch
    -0.89
     виправивши
    -0.88
    InvalidProtocol
    -0.80
    <eos>
    -0.76
    LookAnd
    -0.72
    IVEREF
    -0.66
     tartalomajánló
    -0.66
     Roskov
    -0.64
    parsedMessage
    -0.64
    POSITIVE LOGITS
    </em>
    0.93
    ConstraintMaker
    0.81
    </i>
    0.79
    الدراسه
    0.66
     وتسجيلات
    0.64
    はじめに
    0.62
     怎样
    0.62
    substack
    0.61
    </u>
    0.61
     autorytatywna
    0.59
    Act Density 0.658%

    No Known Activations