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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with apologies or making excuses

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

    excuse me, excuse yourself, excused

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.59
     étoit
    -0.55
     fubject
    -0.54
     anſ
    -0.54
     faſt
    -0.52
     cauſe
    -0.52
     avoient
    -0.50
    secuencias
    -0.50
    findpost
    -0.50
     poffe
    -0.49
    POSITIVE LOGITS
     Excuse
    0.94
    Excuse
    0.92
     excused
    0.89
    excuse
    0.82
     Pardon
    0.81
     excuse
    0.74
    Pardon
    0.72
     pardon
    0.71
    pardon
    0.64
    失礼
    0.61
    Act Density 0.006%

    No Known Activations