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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation in communication

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

    goodbye or thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.75
    뀜
    -0.55
    iastes
    -0.50
     ролях
    -0.49
     SwitchCompat
    -0.47
    formatics
    -0.46
    EndGlobalSection
    -0.45
    +#+#
    -0.44
    berdayakan
    -0.44
    apimachinery
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.46
    ękuję
    0.41
    begle
    0.40
    ponym
    0.39
     fold
    0.39
    Interview
    0.36
     LUCK
    0.36
     interview
    0.36
    私も
    0.35
     Interview
    0.34
    Act Density 0.003%

    No Known Activations