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

    Neuronpedia

    INDEX
    Explanations

    the presence of structured data or formatted elements in the text

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

    preceding hyphenated words or math symbols

    np_acts-logits-general · gemini-2.0-flash

    general way, phase current

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -1.01
     to
    -0.89
     der
    -0.85
     in
    -0.84
     v
    -0.83
     qu
    -0.82
    ↵↵
    -0.80
     b
    -0.80
     sa
    -0.79
     k
    -0.79
    POSITIVE LOGITS
     pleaſure
    1.46
     myſelf
    1.45
     itſelf
    1.43
     purpoſe
    1.34
     ſeveral
    1.30
     leſs
    1.30
     themſelves
    1.30
     Houſe
    1.28
     ſever
    1.26
     houſe
    1.26
    Act Density 0.032%

    No Known Activations