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

    "sorry" or apologies

    np_acts-logits-general · gemini-2.0-flash

    expressions of apology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.45
     Manzan
    -0.39
    نیم
    -0.39
    modelBuilder
    -0.38
    /*:
    -0.37
    etCode
    -0.37
     Consultez
    -0.37
    новништво
    -0.36
    listdir
    -0.36
    Activités
    -0.35
    POSITIVE LOGITS
     Sorry
    0.82
     SORRY
    0.81
    sorry
    0.80
     sorry
    0.79
    Sorry
    0.78
     apologized
    0.71
     apologize
    0.70
     apologise
    0.67
     forgive
    0.64
    Forgive
    0.64
    Act Density 0.065%

    No Known Activations