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

    Neuronpedia

    INDEX
    Explanations

    references to employment and financial compensation

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

    work and pay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jdź
    -0.40
     Wishing
    -0.40
     nonUne
    -0.38
     dirigió
    -0.35
    NameList
    -0.35
    thenReturn
    -0.35
     seperti
    -0.35
     usar
    -0.35
    Kilder
    -0.35
    tvguide
    -0.35
    POSITIVE LOGITS
     informée
    0.58
     otomatig
    0.57
     ब्रेकडाउन
    0.57
     itſelf
    0.57
    rungsseite
    0.56
    pexpr
    0.55
     pleaſure
    0.54
    ſelf
    0.53
     Paglinawan
    0.53
     ſur
    0.50
    Act Density 0.020%

    No Known Activations