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

    Neuronpedia

    INDEX
    Explanations

    expressions of apology or regret

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

    apologizing for mistakes or delays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MenuInflater
    -0.44
    bex
    -0.42
     egli
    -0.42
    quarie
    -0.41
    Leeds
    -0.40
    Nix
    -0.39
     înc
    -0.39
     فت
    -0.39
     knex
    -0.38
     maș
    -0.38
    POSITIVE LOGITS
     sorry
    1.77
     SORRY
    1.56
    sorry
    1.52
     Sorry
    1.42
    Sorry
    1.33
     sorri
    0.75
     apologised
    0.75
     désolés
    0.74
     apologise
    0.73
    抱歉
    0.73
    Act Density 0.003%

    No Known Activations