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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusivity or differentiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.68
    ########.
    -0.65
    fromnode
    -0.65
    yntaxException
    -0.59
     виправивши
    -0.58
     betweenstory
    -0.54
    transQ
    -0.54
    makeConstraints
    -0.53
    MigrationBuilder
    -0.53
     IFTT
    -0.52
    POSITIVE LOGITS
    不止
    0.56
    不仅仅
    0.50
     nejen
    0.48
    不仅
    0.46
    不僅
    0.42
    delà
    0.41
    NotEmpty
    0.40
    だけではなく
    0.37
    だけでなく
    0.36
     Beyond
    0.35
    Act Density 0.207%

    No Known Activations