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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code syntax related to programming structures and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.88
     snippetHide
    -0.85
     queſta
    -0.74
     betweenstory
    -0.71
    nezeu
    -0.68
     виправивши
    -0.68
    :✨
    -0.68
    GEBURTSDATUM
    -0.68
    Portail
    -0.67
    Datuak
    -0.66
    POSITIVE LOGITS
     also
    0.68
     too
    0.42
     aswell
    0.41
    ↵↵
    0.41
     either
    0.41
     Also
    0.40
     тоже
    0.40
    ↵
    0.39
     has
    0.39
     ebenfalls
    0.39
    Act Density 0.725%

    No Known Activations