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

    Neuronpedia

    INDEX
    Explanations

    phrases related to effort and tasks that need completion

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

    work or do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poli
    -0.37
     dé
    -0.33
     شع
    -0.33
    denly
    -0.33
     gener
    -0.32
     polí
    -0.32
     expression
    -0.31
    cost
    -0.31
    ポリ
    -0.30
     costing
    -0.29
    POSITIVE LOGITS
     مشين
    0.65
     desmotivaciones
    0.61
    aarrggbb
    0.61
    uxxxx
    0.57
     Wikiseite
    0.56
    ulongan
    0.55
    دانشنامهٔ
    0.55
     Geiſt
    0.52
    utuhkan
    0.52
    alakip
    0.51
    Act Density 0.031%

    No Known Activations