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

    Neuronpedia

    INDEX
    Explanations

    conversational greetings and expressions of gratitude or appreciation

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

    Followed by a French word or phrase

    np_acts-logits-general · gemini-2.0-flash

    greetings and conversational phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الصفحه
    -0.53
    trze
    -0.47
     reasoned
    -0.46
    ecap
    -0.44
    ciaż
    -0.42
    otto
    -0.42
     under
    -0.42
    日在
    -0.41
    arki
    -0.41
    $($
    -0.41
    POSITIVE LOGITS
     noDo
    0.89
     nahilalakip
    0.89
    enderror
    0.81
     дописавши
    0.80
     NSCoder
    0.76
    addGap
    0.74
     '\\;'
    0.73
    addContainerGap
    0.72
     Pleasure
    0.70
     pleasure
    0.70
    Act Density 0.070%

    No Known Activations