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

    Neuronpedia

    INDEX
    Explanations

    the presence of the term that signifies confirmation codes or related phrases

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

    PO2 and PCO2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Arbeit
    -0.45
     inad
    -0.45
    rood
    -0.44
    userRole
    -0.43
    gdx
    -0.42
    glise
    -0.42
     Germania
    -0.40
     Edy
    -0.40
     intime
    -0.39
     Omaha
    -0.39
    POSITIVE LOGITS
     Po
    0.81
    Po
    0.77
     After
    0.72
     Após
    0.71
     after
    0.70
     після
    0.68
    After
    0.66
     AFTER
    0.66
     после
    0.64
    after
    0.63
    Act Density 0.002%

    No Known Activations