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

    Neuronpedia

    INDEX
    Explanations

    expressions related to guarantees and making certain of outcomes

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

    making sure of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🟤
    -0.48
     виправивши
    -0.44
    ніципалі
    -0.43
     invitation
    -0.43
    énario
    -0.42
     MUD
    -0.41
     skyl
    -0.41
    enties
    -0.41
     Dil
    -0.40
    TemporalType
    -0.40
    POSITIVE LOGITS
     thoſe
    0.59
    Ensure
    0.59
     Pastikan
    0.57
     ensure
    0.55
     ensuring
    0.55
     ensures
    0.52
     sikre
    0.49
     bahwa
    0.48
     bezpiecze
    0.48
     Masyarakat
    0.48
    Act Density 0.009%

    No Known Activations