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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structure in text, such as symbols, layouts, or references in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.74
     becauſe
    -0.69
     Theſe
    -0.65
     Efq
    -0.65
     Greenway
    -0.63
    jectory
    -0.63
     gql
    -0.63
    )";
    -0.62
    ՚
    -0.62
     dépenses
    -0.61
    POSITIVE LOGITS
    ⓘ
    0.50
    <eos>
    0.46
    ,
    0.44
    DataAnnotations
    0.44
     pros
    0.43
     numerus
    0.43
    ~
    0.42
     request
    0.41
     препратки
    0.41
    –
    0.40
    Act Density 0.386%

    No Known Activations