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

    Neuronpedia

    INDEX
    Explanations

    repeated and contextually significant instances of the word "used" and similar action verbs

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

    when + past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     הזה
    -0.38
     vœ
    -0.34
    זה
    -0.33
     wey
    -0.31
    väg
    -0.31
     Perak
    -0.30
     which
    -0.30
     éc
    -0.30
    et
    -0.29
    연
    -0.29
    POSITIVE LOGITS
     autorytatywna
    1.05
    fromnode
    0.82
    таратура
    0.74
     ProtoMessage
    0.66
     nakalista
    0.64
    MigrationBuilder
    0.63
     NSCoder
    0.63
     Administrativna
    0.62
    /**
    0.62
     Италијани
    0.62
    Act Density 0.043%

    No Known Activations