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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to collective actions or intentions

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

    we want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.57
     uLocal
    -0.57
     setTotal
    -0.55
    ⟬
    -0.54
     houſe
    -0.53
     ſmall
    -0.52
    PARATUS
    -0.52
     electrolux
    -0.51
     ambul
    -0.51
     ſte
    -0.50
    POSITIVE LOGITS
     keduanya
    0.44
     cherchés
    0.43
     Eventually
    0.43
    >{@
    0.43
     Trennung
    0.40
     epä
    0.39
    anggap
    0.39
    Essentially
    0.39
    Apparently
    0.38
    Quite
    0.38
    Act Density 0.060%

    No Known Activations