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

    Neuronpedia

    INDEX
    Explanations

    references to technology and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text after certain punctuation/conjunctions

    np_acts-logits-general · gemini-2.0-flash

    lists phrases starting with specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.95
     purpoſe
    -0.94
     themſelves
    -0.94
     raiſ
    -0.91
     ſever
    -0.90
     himſelf
    -0.87
     itſelf
    -0.86
     Monfieur
    -0.86
     pleaſure
    -0.86
     iſt
    -0.85
    POSITIVE LOGITS
     q
    0.59
     commonwealth
    0.59
     pope
    0.58
     y
    0.55
     queen
    0.52
     federal
    0.52
     vu
    0.52
     velas
    0.52
    …~
    0.51
     москве
    0.51
    Act Density 1.419%

    No Known Activations