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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of the word "work" in various contexts

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

    work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.38
     餐廳
    -0.36
     dispozici
    -0.35
    ecio
    -0.34
    üglich
    -0.34
    ături
    -0.33
     Heute
    -0.33
    Sprintf
    -0.33
     餐厅
    -0.33
     eeuw
    -0.32
    POSITIVE LOGITS
     work
    0.65
     WORK
    0.60
     Work
    0.60
     trabajo
    0.59
    WORK
    0.57
    Work
    0.55
     pekerjaan
    0.54
    DNEY
    0.54
     works
    0.53
    OfWork
    0.53
    Act Density 0.023%

    No Known Activations