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

    Neuronpedia

    INDEX
    Explanations

    phrases related to textual references and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -1.15
     myſelf
    -1.10
     defaultstate
    -1.06
     تضيفلها
    -1.04
    UnusedPrivate
    -1.04
     ब्रेकडाउन
    -1.01
    aarrggbb
    -1.00
    WithIOException
    -0.97
    GEBURTSDATUM
    -0.97
    ंदीखरीदारी
    -0.94
    POSITIVE LOGITS
    ↵↵
    0.80
    <eos>
    0.72
    <h2>
    0.70
    ↵
    0.57
      
    0.57
    ↵↵↵↵
    0.55
    ↵↵↵
    0.53
     
    0.51
     The
    0.49
    The
    0.49
    Act Density 0.289%

    No Known Activations