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

    Neuronpedia

    INDEX
    Explanations

    references to trivialities or unnecessary complications in situations

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

    fuss is about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PyLong
    -0.49
     Weeknd
    -0.46
    RunWith
    -0.45
    ModelMap
    -0.41
     насељу
    -0.39
    LEn
    -0.38
     słon
    -0.38
     Heineken
    -0.38
    mobileqq
    -0.38
    Jereo
    -0.36
    POSITIVE LOGITS
     fuss
    1.94
    fuss
    1.45
     fussy
    1.43
     Fuss
    1.36
     fus
    1.16
    fus
    1.04
     Fus
    1.03
    Fus
    0.82
    fuzz
    0.73
     fuzz
    0.71
    Act Density 0.003%

    No Known Activations