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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myself
    -0.53
     yourself
    -0.52
     καν
    -0.51
    athen
    -0.49
    hamshire
    -0.47
     minta
    -0.47
     Anybody
    -0.47
    box
    -0.47
     fast
    -0.45
     Myself
    -0.45
    POSITIVE LOGITS
     receita
    0.69
    extAlignment
    0.64
     الرياضيه
    0.62
     receitas
    0.62
     pylint
    0.61
    Personensuche
    0.61
    ötzlich
    0.60
     inflación
    0.60
    ypress
    0.60
     समीक्षक
    0.59
    Act Density 0.134%

    No Known Activations