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

    Neuronpedia

    INDEX
    Explanations

    flowery or exaggerated language, particularly in a style reminiscent of Victorian-era or overly formal writing.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @johnny

    references to authority and judgment

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

    Follows first-person pronouns

    np_acts-logits-general · gemini-2.0-flash

    precedent for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.84
     perſon
    -0.82
     uſed
    -0.81
     Jefus
    -0.81
     faſt
    -0.81
     uſe
    -0.81
     ſeveral
    -0.80
     Deshalb
    -0.79
     lots
    -0.78
    いろいろな
    -0.78
    POSITIVE LOGITS
    已然
    1.13
     gänzlich
    0.98
    に於
    0.94
     requisite
    0.91
     herein
    0.91
     iż
    0.91
     således
    0.90
    这般
    0.87
     אשר
    0.87
     myriad
    0.86
    Act Density 3.007%

    No Known Activations