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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time or imminent events

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

    just want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pannt
    -0.33
     actionMode
    -0.33
    iquest
    -0.33
     trouvez
    -0.32
    Vaya
    -0.32
    هرست
    -0.31
    secuencias
    -0.30
     préfé
    -0.30
    PreferredItem
    -0.30
     geçen
    -0.30
    POSITIVE LOGITS
    的就是
    0.59
    就是
    0.57
     就是
    0.54
    MigrationBuilder
    0.51
     ddelweddau
    0.51
    就会
    0.50
    就
    0.49
    就會
    0.49
    DockStyle
    0.49
    就要
    0.49
    Act Density 0.019%

    No Known Activations