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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing results or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thro
    -0.47
     fé
    -0.43
    参
    -0.42
     like
    -0.42
    e
    -0.42
    elser
    -0.42
     như
    -0.42
    FOUND
    -0.41
     giống
    -0.41
     câ
    -0.41
    POSITIVE LOGITS
     оригіналу
    1.05
    AndEndTag
    0.86
    GEBURTSDATUM
    0.84
    UnusedPrivate
    0.84
     BoxDecoration
    0.84
    .*")]
    0.83
     الرياضيه
    0.83
     itſelf
    0.79
     obstante
    0.79
    kloped
    0.77
    Act Density 0.229%

    No Known Activations