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

    Neuronpedia

    INDEX
    Explanations

    tenses and expressions indicating time or continuity

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

    preceding "then" or "since"

    np_acts-logits-general · gemini-2.0-flash

    time passing since an event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kaieteur
    -0.58
    principalColumn
    -0.56
    ]--;
    -0.56
    BIÉN
    -0.51
    umerable
    -0.50
    oux
    -0.49
    dillera
    -0.49
    Lähteet
    -0.48
    しく
    -0.48
    heroku
    -0.48
    POSITIVE LOGITS
     then
    3.32
     entonces
    2.63
    then
    2.59
     Then
    2.43
    Then
    2.41
     allora
    2.41
     THEN
    2.29
     тогда
    2.27
     então
    2.26
     wtedy
    2.18
    Act Density 0.374%

    No Known Activations