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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive forms

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

    Possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )_/¯
    -0.69
     vibe
    -0.69
     badass
    -0.69
    ️
    -0.68
     backstory
    -0.67
     _$
    -0.64
     curated
    -0.62
     Heist
    -0.62
    permalink
    -0.60
    +#+
    -0.60
    POSITIVE LOGITS
     daß
    0.62
     muß
    0.59
     own
    0.57
    InstrumentedTest
    0.54
    luß
    0.53
     müßte
    0.52
    own
    0.51
    Boas
    0.48
     hitherto
    0.47
     Own
    0.47
    Act Density 0.303%

    No Known Activations