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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "of" or reference works and contributions

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

    the work of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poveznice
    -0.44
     typelib
    -0.42
    anzeige
    -0.42
     bioavailability
    -0.42
     emblems
    -0.40
    antino
    -0.40
     Camacho
    -0.39
     bendera
    -0.39
     společnost
    -0.38
     disposição
    -0.38
    POSITIVE LOGITS
     work
    0.93
     Work
    0.92
    Work
    0.90
    work
    0.84
     WORK
    0.84
     works
    0.75
     Works
    0.75
     работы
    0.73
    Работа
    0.71
     WORKS
    0.71
    Act Density 0.008%

    No Known Activations