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

    Neuronpedia

    INDEX
    Explanations

    expressions of courtesy and closing salutations in correspondence

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

    closing salutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Glit
    -0.44
    Discovery
    -0.40
    createCanvas
    -0.40
    Olympic
    -0.40
     stim
    -0.39
     createSlice
    -0.38
     chandeliers
    -0.38
     muse
    -0.37
    medriver
    -0.37
    Inner
    -0.36
    POSITIVE LOGITS
    Regards
    2.03
     Regards
    1.91
    regards
    1.44
     regards
    1.25
    Cordialement
    1.18
    Gruß
    1.11
    Pozdrawiam
    1.10
    drawiam
    0.91
    Sincerely
    0.90
    Grüße
    0.90
    Act Density 0.003%

    No Known Activations