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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and ownership

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

    Text referring to "your" or "my" something

    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
     Bewußt
    -0.46
    aarrggbb
    -0.43
    jalá
    -0.42
     erfü
    -0.40
     affitto
    -0.40
    VersionUID
    -0.39
     profondità
    -0.39
     gioielli
    -0.38
    UrlResolution
    -0.38
     biß
    -0.38
    POSITIVE LOGITS
     behaviour
    0.46
     another
    0.44
    readyState
    0.43
     certains
    0.43
    streng
    0.42
     Langkah
    0.42
    Langkah
    0.41
    ssch
    0.41
     ulter
    0.41
     useDispatch
    0.41
    Act Density 0.268%

    No Known Activations