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

    Neuronpedia

    INDEX
    Explanations

    instances of speech or statements made by individuals

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

    reported speech attribution noun and pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьаж
    -0.46
    LLocation
    -0.45
     propa
    -0.43
     @"";
    -0.40
     eyelids
    -0.37
    wegg
    -0.37
    ſelf
    -0.36
    grapher
    -0.36
    AppData
    -0.35
    кипедия
    -0.35
    POSITIVE LOGITS
    AsStream
    0.58
     stället
    0.49
     <>",
    0.45
    rungsseite
    0.44
     ANCHE
    0.43
     antaranya
    0.43
     AssemblyCompany
    0.43
    attutto
    0.42
    Fordítás
    0.42
     nakalista
    0.41
    Act Density 0.004%

    No Known Activations