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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude and acknowledgment

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

    acknowledgement and apologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    省市镇
    -0.40
    };*/
    -0.38
    specialized
    -0.38
     &___
    -0.38
     podjela
    -0.37
    //};
    -0.36
    ']->
    -0.36
    >--}}
    -0.35
    BufferException
    -0.35
    ibatkan
    -0.35
    POSITIVE LOGITS
     acknowledgement
    0.60
     recognition
    0.60
     acknowledgment
    0.59
     congrat
    0.58
     thanking
    0.55
     acknowledging
    0.52
     appla
    0.51
     acknowled
    0.51
     Recognition
    0.51
     congratulate
    0.50
    Act Density 0.171%

    No Known Activations