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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     upwards
    -0.35
     respectfully
    -0.31
     alternatively
    -0.31
     respectively
    -0.31
     hohen
    -0.31
     oficialmente
    -0.30
     amongst
    -0.30
     Treue
    -0.30
     lamang
    -0.30
     onwards
    -0.29
    POSITIVE LOGITS
     Италијани
    0.82
     ModelExpression
    0.73
     Савезне
    0.69
     Italijanski
    0.69
     تضيفلها
    0.68
    parsedMessage
    0.67
     informée
    0.67
    BufferException
    0.66
    protoimpl
    0.63
     queſta
    0.63
    Act Density 0.007%

    No Known Activations